
Advertise on podcast: Coding Chats
Rating
5from
Categories
This podcast has
88 episodes
Language
EnglishPublisher
John CrickettExplicit
No
Date created
2024/04/10
Latest episode
2026/11/12
Average duration
50 min.
Release period
17 days
Description
On Coding Chats, John Crickett interviews software engineers of all levels from junior to CTO. He encourages the guests to share the stories of the challenges they have faced in their role and the strategies and tactics they have used to overcome those challenges providing actionable insights other software engineers can use to accelerate their careers.
Unlock Coding Chats podcast Email contact info,
Listeners & Audience details
Email contact information
Direct podcast contact details

Listeners
Audience numbers & engagement insights

Audience details
Podcast Insights

Podcast episodes
Check latest episodes from Coding Chats podcast
AI is putting me through the 5 stages of grief!
2026/11/12
Coding Chats Episode 85 - John talk to Ian, a 51-year-old software engineer with 25 years of experience, who describes going through something like grief as AI takes over work he spent decades mastering. He no longer reads the code it writes, which leads him and host John to debate when that’s acceptable and when it isn’t. Ian calls the pace of change “exciting and terrifying at the same time.”
John argues the grief is unwarranted: cheaper software will mean more to build, and engineers still own requirements, testing and delivery. They disagree on a few points, such as on-the-fly user interfaces, but both lean optimistic about the profession, and agree to revisit their predictions in two years.
00:00 – Welcome and why Ian is "grieving" over AI in software development
03:11 – Do we still need to read the code? Trust, outcomes and safety-critical systems
06:15 – Code review in practice, and what makes someone an engineer
10:21 – Requirements, analysts and the full software lifecycle
13:41 – From punch cards to DevOps: the pace of change
18:22 – Why requirements work stays human (the drill bit story)
20:29 – Is English the programming language of the future?
23:04 – How much software will be written? The spreadsheet analogy
27:05 – Do we still need tests? UI stability versus custom UIs
29:23 – Demand for software and the future of junior developers
35:18 – UIs that evolve with the user
40:24 – Internal tools, AI-generated software and the "mainframes of the future"
43:01 – Training juniors and long-term demand for engineers
44:06 – Missing the craft: coding as a hobby
46:21 – Adapting to industry-wide disruption
48:00 – Wrap-up and a two-year follow-upIan's
Links:
https://www.linkedin.com/in/%E2%80%8Bian-miell-694496/
John's Links:
John's LinkedIn: https://www.linkedin.com/in/johncrickett/
John’s YouTube: https://www.youtube.com/@johncrickett
John's Twitter: https://x.com/johncrickett
John's Bluesky: https://bsky.app/profile/johncrickett.bsky.social
Check out John's software engineering related newsletters: Coding Challenges: https://codingchallenges.substack.com/ which shares real-world project ideas that you can use to level up your coding skills.
Developing Skills: https://read.developingskills.fyi/ covering everything from system design to soft skills, helping them progress their career from junior to staff+ or for those that want onto a management track.
Takeaways
AI coding tools have gone from a helpful accelerator to something that can work across whole microservice codebases, which is why experienced engineers are feeling real grief.
Whether you need to read AI-generated code depends on the stakes: skip it for a throwaway tool, read every line for safety-critical systems.
Human code review has always been weak, with big pull requests tending to get a rubber-stamp “LGTM”.
Engineers have always been the people who care what’s under the hood, but where that “hood” sits keeps moving up the stack.
Requirements gathering, such as finding out what customers actually need rather than what they ask for, remains a core engineering skill that AI doesn’t replace.
Cheaper software could create more demand for engineers, much as spreadsheets led to more accountants rather than fewer.
Junior developers can still learn by starting at a higher level of abstraction and working down, as earlier generations did with BASIC, C and assembler.
Part of the grief is losing the craft of writing code by hand, though coding can survive as a hobby, like Sudoku or crosswords.
The pace of change is dizzying and no one can say what software will look like in two years, so the hosts agree to revisit their predictions then.
How I got into big tech with a non-traditional background. From hot furnaces to cool cloud computing
2026/10/29
Coding Chats Episode 84 - John talks to Raj, who spent over ten years maintaining COBOL on mainframes before becoming a Principal Solutions Architect at AWS, with no computer science degree. He shares how he made the leap by building cloud projects on the side and connecting his legacy experience to modernization work, plus the communication skills that help engineers get promoted.
He also explains why he left big tech to start CloudColosseum, and why he thinks AI will make solutions architects more valuable. If you’re stuck on a legacy stack or wondering how to stay relevant in the age of AI, this one’s for you.
00:52 From Mainframes to Big Tech: A Journey
04:01 The Shift to Cloud: Embracing New Technologies
06:28 Navigating the Transition: Learning New Languages and Skills
09:43 Cultural Shift: Adapting to Fast-Paced Environments
12:44 The Role of a Solutions Architect: Bridging Technology and Business
15:50 Overcoming Communication Barriers: The Importance of Executive Communication
18:34 Teaching the Next Generation: Transitioning Others to Cloud Careers
31:56 Building Trust Through Domain Knowledge
34:35 The Importance of Trying and Iterating
38:33 Transitioning to Solutions Architect: Timeframes and Skills
40:37 The Drive Behind Founding Cloud Coliseum
43:49 AI's Impact on Solutions Architects
50:10 The Reality of AI Hype and Job Market Dynamics
56:34 Navigating the Future of AI and Job Security
Raj's Links:
John's Links:
John's LinkedIn: https://www.linkedin.com/in/johncrickett/
John’s YouTube: https://www.youtube.com/@johncrickett
John's Twitter: https://x.com/johncrickett
John's Bluesky: https://bsky.app/profile/johncrickett.bsky.social
Check out John's software engineering related newsletters: Coding Challenges: https://codingchallenges.substack.com/ which shares real-world project ideas that you can use to level up your coding skills.
Developing Skills: https://read.developingskills.fyi/ covering everything from system design to soft skills, helping them progress their career from junior to staff+ or for those that want onto a management track.
Takeaways
Your existing experience isn’t throwaway, so connect it to cloud and AI instead of starting from scratch.
You don’t need to be a cloud expert to become a solutions architect, because knowing the legacy systems companies are migrating is a huge advantage.
Side projects and proofs of concept can open doors, and you can build them without quitting your job.
Executive communication is often what separates senior engineers from the next level, since business leaders control the budget.
Technical skills alone are hard to win on over a long career, but adding business communication makes you a complete package.
Cloud and AI reward trying things, because the cost of a mistake is tiny compared with the old days of expensive, exam-style learning.
You only need to master the core concepts, about 10% of the dictionary, to get hired as a solutions architect.AI is useful but overhyped, so learn the fundamentals (RAG, agents, MCP, evals, guardrails), tie them to your existing knowledge, and keep a close eye on AI-generated code.
Is plan mode dead? And other questions around the latest ChatGPT.
2026/10/22
Coding Chats Episode 83 - In this episode, VB from OpenAI’s developer experience team explains why he thinks plan mode is obsolete and how coding agents have shifted from step-by-step instructions to outcome-driven, long-running work. We cover how to write a good agents.md, why tests still matter when agents write the code, spec-driven development, and why cloud agents may be the future of dev tooling.
We also get into the practical details: how prompt caching works and why running one thread per task can cut your cost and latency, plus the biggest announcements from OpenAI’s Dev Day, including GPT 6.1 Sol, ultra fast inference, plugins, and proactive async agents. VB closes with the Codex Ambassadors program and Codex for open source. If you use Codex, AI coding agents, or any agentic coding workflow, there’s something here for you.
00:00 Introduction to Developer Experience at OpenAI
03:29 Bringing AI Models to Developers
06:06 The Shift from Planning to Outcome-Focused Development
09:05 The Role of Testing in AI Development
11:51 Creating Effective Agents.md for AI Projects
17:17 The Evolution of Developer Tools at OpenAI
25:21 Cloud Development: The Future of Coding
26:48 Insights from OpenAI's Dev Day
28:00 Revolutionizing Development with GPT 6.1 Soul
32:35 Understanding Caching for Developers
39:02 Proactive Agents: Enhancing Productivity
42:39 Community Initiatives and Open Source Contributions
48:36 Exploring Related Content
VB's Links:
https://openai.com/
John's Links:
John's LinkedIn: https://www.linkedin.com/in/johncrickett/
John’s YouTube: https://www.youtube.com/@johncrickett
John's Twitter: https://x.com/johncrickett
John's Bluesky: https://bsky.app/profile/johncrickett.bsky.social
Check out John's software engineering related newsletters: Coding Challenges: https://codingchallenges.substack.com/ which shares real-world project ideas that you can use to level up your coding skills.
Developing Skills: https://read.developingskills.fyi/ covering everything from system design to soft skills, helping them progress their career from junior to staff+ or for those that want onto a management track.
Takeaways
Plan mode is obsolete because current models plan inherently, so you’re better off spending your time up front defining the outcome you want.
Developers are moving from prescribing steps to defining intended outcomes (like “get this CI green”) and letting the agent plan, execute, and adjust on its own.
Spec-driven development has its place, especially for API-shaped work, but it backfires if the spec isn’t kept in sync with every change.
A strong but lightweight agents.md should cover where code lives, how the agent knows it’s doing a good job, your style rules, and what a good PR looks like.
Tests still matter when agents write the code, because they catch regressions before merge, but the agent needs guidance on which tests are worth writing.
Treat agents.md as a living document that grows as you work with the agent, not something you get right in one shot.
To get the most from prompt caching, use one thread per feature and a couple of narrowly scoped subagents instead of running a dozen agents and letting the cache go cold.
Coding workloads have large inputs and small outputs, which is why caching makes them so much cheaper and faster than typical chat use.
Cloud agents are where dev tooling is heading, since they remove “works on my machine” problems and free long-running tasks from your laptop.
If you’re still on the fence about coding agents, give one real task to an agent, watch how it interprets your request, and refine your instructions from there.
The truth about technical scrum masters that most people miss
2026/10/15
Coding Chats Episode 82 - John talks with Dave Westgarth, head of delivery at a Databricks consultancy. Dave shares his path from a psychology degree and McDonald's into tech, and they discuss why the Scrum Master role is so misunderstood, how it differs from a delivery manager, and whether either needs to be technical.They also look at how AI is changing delivery work. Faster code just moves the bottleneck upstream, John argues there's no AI-specific skill you can't learn in a day, and engineering fundamentals are what make AI useful.
Chapters
00:00 Journey to Technology: A Personal Story
10:33 The Role of a Scrum Master: Misunderstandings and Realities16:52 The Impact of AI on Scrum Master Roles
24:41 Hiring and Empowering the Right People
26:01 Scrum Master vs. Delivery Manager: Understanding the Roles
26:06 Technical Skills: Should Scrum Masters Be Technical?
32:19 The Value of Certifications in Professional Development
38:48 AI's Role in Delivery Management
47:13 Connecting with Dave Westgarth
Dave's Links:
https://www.technicalscrum.orghttps://
www.linkedin.com/in/dave-westgarth/
John's Links:
John's LinkedIn: https://www.linkedin.com/in/johncrickett/
John’s YouTube: https://www.youtube.com/@johncrickett
John's Twitter: https://x.com/johncrickett
John's Bluesky: https://bsky.app/profile/johncrickett.bsky.social
Check out John's software engineering related newsletters: Coding Challenges: https://codingchallenges.substack.com/ which shares real-world project ideas that you can use to level up your coding skills.
Developing Skills: https://read.developingskills.fyi/ covering everything from system design to soft skills, helping them progress their career from junior to staff+ or for those that want onto a management track.
Takeaways
Scrum Masters who just move Jira tickets and run ceremonies are the ones AI can replace.
Be loyal to agile's values, not the mechanics of the framework.
If AI makes code ten times faster, stakeholders and approvals need to keep up, or the bottleneck just moves.
In retrospectives, pick one small change instead of trying to fix everything.
Regular delivery cuts down the demand for status reports.
Technical skills help managers only if they don't take over the work and stop developing their people.
There's no AI-specific skill you can't learn in a day, but using AI well takes software engineering fundamentals.
Writing code is a small part of software engineering.
Tutorials show the perfect path, but the real learning happens when you get stuck.
Certifications work best as forced learning, not just CV decoration.
I took CTO title not knowing what I was getting into
2026/10/08
Coding Chats Episode 81 - Ben Howdle talks to John Crickett about being a first time CTO in a start-up. Ben, author of The First CTO, shares what changes when you move from building technology to leading a technical team: the pressure, the trade-offs, and the realization that writing code is only part of the job.Drawing on startup experience and lessons learned the hard way, Ben discusses how to balance quality against runway, manage people, and communicate technical decisions in terms that founders and other non-technical stakeholders can understand. He also explores why resourcefulness, resilience, and comfort with ambiguity matter so much—and why CTOs often spend more time selling ideas than they expect.Whether you’re stepping into your first CTO role or leading a technical team at an early-stage company, this conversation offers candid insights into the realities of technical leadership.
Chapters
00:45 The Loneliness of the CTO
16:57 Essential Skills for a First-Time CTO
22:53 Understanding the Hierarchy: Who is the Boss?
30:14 The Importance of Advisory Network
38:06 Transitioning to People Management
44:27 Understanding the 40% Rule
52:54 Exploring Related Content
Ben's Links:
https://www.linkedin.com/in/ben-howdle/
John's Links:
John's LinkedIn: https://www.linkedin.com/in/johncrickett/
John’s YouTube: https://www.youtube.com/@johncrickett
John's Twitter: https://x.com/johncrickett
John's Bluesky: https://bsky.app/profile/johncrickett.bsky.social
Check out John's software engineering related newsletters: Coding Challenges: https://codingchallenges.substack.com/ which shares real-world project ideas that you can use to level up your coding skills.
Developing Skills: https://read.developingskills.fyi/ covering everything from system design to soft skills, helping them progress their career from junior to staff+ or for those that want onto a management track.
Takeaways
Taking on the CTO title without experience can be the thing that forces the growth you wouldn't have sought otherwise.
At a startup, runway isn't just a finance metric — it should be the lens every technical decision gets filtered through.
The tension between building things well and building things fast enough to survive is one of the defining challenges of being a first-time CTO.
The most chaotic, uncertain period of your career might also be the one where you're most alive.
A first-time CTO needs resourcefulness, comfort with ownership, and resilience more than any specific technical skill.
When you have no one to bounce ideas off internally, build an informal council from your network — it can double as a recruiting pipeline.
The quicker you can identify your own blind spots and weaknesses, the quicker you can plug the gaps.
Early-career engineers often drown non-technical stakeholders in jargon to mask imposter syndrome — the real skill is meeting people where they are and speaking to business outcomes.
Startup Advisor Secrets: Hiring, CTOs & Going From POC to Product
2026/05/28
Coding Chats Episode 80 - start-up advisor Alexander Berkovich shares his expertise on building successful start-ups, hiring strategies, CTO roles, and the importance of communication between technical and business teams. Discover practical tips for navigating the challenges of early-stage companies and how to align technical excellence with business goals.
Chapters
00:00 Introduction to Start-up Advising
02:09 The Day-to-Day of a Start-up Advisor
05:39 Hiring Challenges in Start-ups
07:39 Defining the Role of a CTO
10:36 Common Mistakes in CTO Hiring
12:59 Bridging the Gap: Technical and Business Communication
16:40 Utilizing Client Feedback for Product Improvement
20:06 Transitioning from Proof of Concept to Product
24:01 Exploring Computer Vision in AI
24:06 Balancing Technical Excellence and Business Focus
24:09 Exploring Related Content
Alex's Links:
Alex's LinkedIn: https://www.linkedin.com/in/alexander-berkovich-startup-advisor/
John's Links:
John's LinkedIn: https://www.linkedin.com/in/johncrickett/
John’s YouTube: https://www.youtube.com/@johncrickett
John's Twitter: https://x.com/johncrickett
John's Bluesky: https://bsky.app/profile/johncrickett.bsky.social
Check out John's software engineering related newsletters: Coding Challenges: https://codingchallenges.substack.com/ which shares real-world project ideas that you can use to level up your coding skills.
Developing Skills: https://read.developingskills.fyi/ covering everything from system design to soft skills, helping them progress their career from junior to staff+ or for those that want onto a management track.
Takeaways
A CTO's value is in leadership and strategy, not just how much they can code.AI has fundamentally changed the hiring process and what makes a good candidate.
Document every corner you cut in a POC — it will catch up with you later.
Engineers should seek direct client feedback to understand the real impact of their work.
Communication is the most underrated skill in any startup team.
A POC and a product are very different things — don't let one accidentally become the other.
Startups offer breadth of experience that large enterprises simply can't match.
Hiring for the right mindset matters more than hiring for pure technical skill.
Small technical decisions can ripple out and affect cost, timelines, and the whole product.
The best teams stay connected to the end goal, not just the task in front of them.
AI Agents Have a Memory Problem (And You're Probably Making It Worse)
2026/05/21
Coding Chats Episode 79 - Richmond Alake, Director of AI Developer Experience at Oracle, joins John to discuss agent memory — how AI agents store, retrieve, and adapt to information. He argues that developers building memory on flat files are naively reinventing the database, and that once you factor in concurrency, security, and scalability, a proper database is inevitable. The conversation covers the full memory stack and how Oracle's AI database keeps embeddings and data together without shipping sensitive information to external providers.
The pair also explore why memory is the most universally relatable concept in AI, the history of how neuroscience shaped LLMs, and the problem of Catastrophic Forgetting that still haunts models today. A sharp AGI debate lands on a sobering point: an LLM is just a function — tokens in, tokens out — and most AI engineers are unknowingly rediscovering solutions that database engineers spent decades building.
Chapters
00:00 — What Is Agent Memory and How Does It Work?
05:00 — File System vs Database: Which Should You Use for Agent Memory?
09:00 — Why Building on Files Means You'll Reinvent the Database
13:00 — How Oracle Is Meeting AI Developers Where They Are
15:00 — Why Memory Is the Most Universal Concept in AI
21:00 — From Computer Vision to LLMs: How Richmond Found His Path
24:00 — Catastrophic Forgetting: The Problem That Hasn't Gone Away
26:00 — Is AGI Real? Why the Goalposts Keep Moving
33:00 — Handling PII, Data Sovereignty, and Access Control in AI Apps
42:00 — The Rise of Memory Engineering: AI's Most Underrated Discipline
Richmond's Links:
LinkedIn: https://www.linkedin.com/in/richmondalake/
X: https://x.com/richmondalake
John's Links:
John's LinkedIn: https://www.linkedin.com/in/johncrickett/
John’s YouTube: https://www.youtube.com/@johncrickett
John's Twitter: https://x.com/johncrickett
John's Bluesky: https://bsky.app/profile/johncrickett.bsky.social
Check out John's software engineering related newsletters: Coding Challenges: https://codingchallenges.substack.com/ which shares real-world project ideas that you can use to level up your coding skills.
Developing Skills: https://read.developingskills.fyi/ covering everything from system design to soft skills, helping them progress their career from junior to staff+ or for those that want onto a management track.
Takeaways:
File systems are fine for prototyping, but the moment you hit production scale you're just slowly reinventing the database.
File systems are fine for prototyping, but the moment you hit production scale you're just slowly reinventing the database.
Agent memory isn't a new concept — it's data management, and database engineers have been solving it for decades.
Memory is the single most relatable entry point for explaining AI to anyone, technical or not.
Catastrophic Forgetting isn't a solved problem — it plagued RNNs and still quietly haunts LLMs today.
An LLM is ultimately just a function: tokens in, tokens out — which should temper any claims about sentience or AGI.
The definition of AGI keeps shifting to match whatever AI can't do yet, making the whole debate almost meaningless.
Most AI engineers have less than ten years of experience and are unknowingly rediscovering solutions that search and database engineers spent decades building.
"Vector search is all you need" is one of the most dangerous oversimplifications in AI engineering right now.
Memory engineering — the crossover between data engineering, search optimisation, and agent design — is an emerging discipline that doesn't have a name yet but absolutely should.
The real moat in AI products isn't the LLM itself, it's everything built around it — the harness, the memory, the retrieval pipeline.
I got into computers to avoid people then they put me in charge of them!
2026/05/14
Coding Chats Episode 78 - John Crickett talks to Robert Harris, an experienced engineering leader. Robert shares hard-won lessons from years of leading software teams, drawing on a distinctive "human systems" lens to explain why so many engineering organisations struggle — not because of bad people, but because of broken systems, misaligned leadership, and invisible cultural forces.
The conversation weaves together philosophy, practical management advice, and candid personal anecdotes, making it equally relevant for first-time engineering managers and seasoned CTOs. The central thread throughout is that software is fundamentally a human endeavour, and leaders who treat it like a purely technical one will keep running into the same problems.
Chapters
0:00 — Every Problem is a Systems Problem
3:00 — Labelling vs. Diagnosing: The Human Systems Approach
6:15 — Poor Performance Is a System Failure, Not a People Failure
9:10 — AI, Flat Orgs, and the Pressure on Engineering Managers
11:30 — Diagnosing a Broken Team: A Real-World Turnaround
24:05 — People Are Not Interchangeable Components
26:00 — Culture: What Happens When Nobody's Watching
33:00 — The Power Gradient and Cross-Team Collaboration
39:00 — The C-Suite Distance Problem
42:00 — Building Culture in Remote and Distributed Teams
46:00 — Software Engineering Is a Humanity
Robert's Links:
https://www.linkedin.com/in/robert-n-harris/coded2lead.com
John's Links:
John's LinkedIn: https://www.linkedin.com/in/johncrickett/
John’s YouTube: https://www.youtube.com/@johncrickett
John's Twitter: https://x.com/johncrickett
John's Bluesky: https://bsky.app/profile/johncrickett.bsky.social
Check out John's software engineering related newsletters: Coding Challenges: https://codingchallenges.substack.com/ which shares real-world project ideas that you can use to level up your coding skills.
Developing Skills: https://read.developingskills.fyi/ covering everything from system design to soft skills, helping them progress their career from junior to staff+ or for those that want onto a management track.
Takeaways
People run on emotion and safety, not logic — lead them accordingly.
When someone underperforms, look at the system before you look at the person.
Labelling people as "difficult" or "lazy" is a way of avoiding the real problem.
AI is accelerating code generation, but the human bottleneck downstream is getting worse, not better.
The institutional memory inside a team is worth far more than anything in your wiki.
Culture is what happens when nobody's watching — not what's written on the wall.
If you send Slack messages at 10pm, your team will think there's no such thing as work-life balance.
Only authorised people should authorise work — casual remarks from leaders land as commands.
Co-location without connection isn't culture, it's a terrarium.
Computers are a science, but software is a humanity.
The Death of Writing Code: OpenAI's Engineer on the Rise of Harness Engineering
2026/05/07
Coding Chats Episode 77 — Arnaud Fournier, Forward Deployed Engineer at OpenAI, talks to John Crickett about how AI is fundamentally reshaping software engineering. He explores how OpenAI's own engineers have largely moved away from writing code line-by-line, shifting instead to what he calls "harness engineering" — orchestrating agents, preparing context, and steering AI to do the heavy lifting.
The conversation covers practical ground for engineers at every level: how to successfully adopt agentic coding in your workflow, best practices for integrating tools like Codex into enterprise environments, and what it's really like to work at the frontier of AI deployment across industries like semiconductors, life sciences, and finance.
Chapters
00:00 Understanding the Role of Forward Deployed Engineers
03:21 The Integration Process: Challenges and Solutions
06:25 Optimizing AI Solutions with Codex
09:38 Leveraging Codex for Team Efficiency
12:28 Best Practices for Using Codex in Engineering Workflows
15:29 Setting Up for Success in Enterprise AI Projects
18:26 Navigating Stakeholder Engagement and Requirements
21:16 The Future of AI in Enterprise Solutions
25:53 Building Proof of Concept Solutions
28:33 Collaborative Development and Model Improvement
30:45 The Rise of Codex and User Adoption
33:36 Integrating AI into Software Development
36:10 Standardization vs. Customization in AI Tools
39:05 The Evolving Role of Forward-Deployed Engineers
42:48 Understanding the FDE Role at OpenAI
46:10 The Recruitment Process at OpenAI
49:50 Exploring Related Content
49:58 Outro Final Coding Chats.mp4
Arnaud's Links
https://www.linkedin.com/in/arnaudfrn/
https://openai.com/index/introducing-openai-frontier/
https://community.openai.com/t/introducing-the-new-codex-for-almost-everything/1379125
https://openai.com/index/scaling-codex-to-enterprises-worldwide/
John's Links:
John's LinkedIn: https://www.linkedin.com/in/johncrickett/
John’s YouTube: https://www.youtube.com/@johncrickett
John's Twitter: https://x.com/johncrickett
John's Bluesky: https://bsky.app/profile/johncrickett.bsky.social
Check out John's software engineering related newsletters: Coding Challenges: https://codingchallenges.substack.com/ which shares real-world project ideas that you can use to level up your coding skills.
Developing Skills: https://read.developingskills.fyi/ covering everything from system design to soft skills, helping them progress their career from junior to staff+ or for those that want onto a management track.
LLM as a Judge: Why Your AI Might Be Marking Its Own Homework
2026/04/30
Coding Chats episode 76 - John talks to Laura Dietz - a computer science professor whose work focuses on whether AI evaluation metrics actually tell the truth. She's known for her critical take on "LLM as a judge" — not because she thinks it's useless, but because she wants numbers that mean something rather than numbers that just make a system look good.
The conversation tackles some uncomfortable realities for software engineers: using an LLM to write code and another to review it is a circular trap, prompt engineering shouldn't be a computer scientist's day job, and every time you reject your code AI's output, you're quietly generating the training data that shapes its successor.
Chapters
00:00 Introduction to Laura Dietz and Her Journey
03:12 Exploring LLMs as Judges
06:16 Challenges in Evaluating Search Systems
08:49 The Evolution of User Queries and Expectations
11:46 The Role of LLMs in Information Retrieval
14:44 Defining Quality in Search Results
17:27 The Complexity of User Intent
19:54 Human-AI Collaboration in Code Review
22:53 The Future of LLMs in Software Development
25:23 Balancing Human and AI Roles
28:20 Innovative Approaches to AI Evaluation
34:10 The Art of Assembling Ideas
36:39 Balancing Cost and Quality in LLMs
39:09 Evaluating LLM Performance
43:50 The Future of LLMs and Training Data
49:19 Exploring New Architectures in AI
55:16 Understanding In-Context Learning
01:00:45 The Role of AI in Creative Expression
01:06:59 Exploring Related Content
Laura's Links:
https://www.cs.unh.edu/~dietz/https://
www.linkedin.com/in/laura-dietz-47036516/
John's Links:
John's LinkedIn: https://www.linkedin.com/in/johncrickett/
John’s YouTube: https://www.youtube.com/@johncrickett
John's Twitter: https://x.com/johncrickett
John's Bluesky: https://bsky.app/profile/johncrickett.bsky.social
Check out John's software engineering related newsletters: Coding Challenges: https://codingchallenges.substack.com/ which shares real-world project ideas that you can use to level up your coding skills.
Developing Skills: https://read.developingskills.fyi/ covering everything from system design to soft skills, helping them progress their career from junior to staff+ or for those that want onto a management track.
Takeaways
Using an LLM to both generate and evaluate outputs is circular — like a student grading their own homework.
If your evaluation metric can go up without your system actually improving, it's not a real metric.
A better human-in-the-loop isn't one that rubber-stamps AI suggestions — it's one that's guided to look in the right place.
LLMs don't get bored, which makes them genuinely useful for code review — but that's not the same as making them accurate.
"Faith-based engineering" — trusting AI output without validation — is a real and growing problem in software teams.
Prompt engineering is a workaround, not a discipline; real engineers should be building systems, not crafting incantations.
Every rejection you give your code AI is training signal — your frustration today is someone else's better tool tomorrow.
The transformer attention mechanism is a weighted sum, and a sum isn't always the right operation — some problems need an AND, not an OR.
AI tools are lowering the barrier to coding for people who were previously too intimidated to try, and that's worth celebrating.
The same network effect that makes a platform valuable also makes monopoly in AI training data genuinely dangerous.
Let it crash! How Erlang and BEAM build bullet proof software
2026/04/23
Coding Chats episode 74 - Erik Stenman talks to John Crickett about the BEAM virtual machine — the runtime behind Erlang, Elixir, and Gleam. Built by Ericsson in the 1980s for telephone switches, it was designed for fault tolerance and concurrency from day one, yet never achieved mainstream popularity despite being technically superior to many alternatives.
The discussion covers what makes BEAM unique: lightweight isolated processes, a "let it crash" fault philosophy, and powerful built-in introspection. Erik also shares practical lessons from production use and explains why newer languages like Elixir and Gleam are finally bringing BEAM the attention it deserves.
Chapters
00:00 Introduction to Beam and Erlang
02:45 The Unique Features of Erlang and Beam
05:17 Concurrency and Fault Tolerance in Beam
07:34 Applications and Use Cases of Erlang
10:00 Error Handling and Process Supervision
12:49 Performance Considerations in Beam
15:09 Learning and Adopting Erlang and Elixir
17:28 The Future of Erlang, Elixir, and Gleam
37:04 Exploring Related Content
Erik's Links:
https://happihacking.com/ https://happihacking.com/blog/
https://github.com/happi/theBeamBook
https://www.amazon.com/dp/9153142535https://www.elixirconf.eu/trainings/the-beam-for-developers/
John's Links:
John's LinkedIn: https://www.linkedin.com/in/johncrickett/
John’s YouTube: https://www.youtube.com/@johncrickett
John's Twitter: https://x.com/johncrickett
John's Bluesky: https://bsky.app/profile/johncrickett.bsky.social
Check out John's software engineering related newsletters: Coding Challenges: https://codingchallenges.substack.com/ which shares real-world project ideas that you can use to level up your coding skills.
Developing Skills: https://read.developingskills.fyi/ covering everything from system design to soft skills, helping them progress their career from junior to staff+ or for those that want onto a management track.
Takeaways
BEAM was built for telephone switches in the 1980s — its reliability features translate surprisingly well to modern web and distributed systems.
Erlang lost the popularity race to Java largely due to marketing, not technical merit.
BEAM processes are extremely lightweight — hundreds of bytes, not kilobytes — allowing millions to run concurrently.
"Let it crash" is a design philosophy, not laziness — isolating failures prevents one bad process from taking down the whole system.
No shared memory between processes eliminates an entire class of concurrency bugs.
Per-process garbage collection means no "stop the world" pauses like you get in Java.
Hot code loading lets you upgrade a running system without downtime — but it requires careful thought about data structure changes.
BEAM's built-in introspection lets you inspect a live system in real time, making debugging far faster.
Elixir and Gleam are modernising the syntax and bringing new developers onto the BEAM platform.
BEAM doesn't solve everything — good architecture still matters, but it gets you there faster than most alternatives.
AI writes it. You own it. Don't ship AI slop
2026/04/16
Coding Chats episode 74 - John Crickett talks to Nnenna Ndukwe, a developer advocate at Qodo, discussing how teams can maintain code quality in the age of AI coding tools. She argues that AI agents should be combined with traditional tools like linters and static analysis — not replace them — and that teams need to define and codify what "good code" looks like so that consistency can be enforced across the whole development lifecycle.
A recurring theme is developer ownership: as AI writes more code, engineers must stay in the driver's seat, genuinely reviewing what gets shipped rather than blindly accepting it. The episode also touches on dogfooding, with both agreeing that using your own tools internally is a strong signal of a product worth trusting.
Chapters
00:00 Introduction to AI in Software Development
03:24 Embedding Quality Gates in Development
06:03 The Importance of Consistency in Code
09:09 Ownership and Critical Thinking in Engineering
12:00 Balancing Tool Freedom and Intellectual Property
14:56 Navigating AI Tools and Workflows
17:47 Managing Burnout in AI Development
20:47 The Evolution of Coding and Instant Gratification
23:47 Documenting Ideas and Project Management
26:54 Using AI for Ideation and Collaboration
31:38 The Joy of Learning Through AI
34:11 Codo: Enhancing Code Quality and Governance
37:22 Comparing Code Review Tools
40:10 The Future of AI in Software Development
50:51 The Importance of Dogfooding Products
56:12 Exploring Related Content
Nnenna's Links:
https://nnennahacks.com
https://linkedin.com/in/nnenna-ndukwe/
https://x.com/nnennahacks
John's Links:
John's LinkedIn: https://www.linkedin.com/in/johncrickett/
John’s YouTube: https://www.youtube.com/@johncrickett
John's Twitter: https://x.com/johncrickett
John's Bluesky: https://bsky.app/profile/johncrickett.bsky.social
Check out John's software engineering related newsletters: Coding Challenges: https://codingchallenges.substack.com/ which shares real-world project ideas that you can use to level up your coding skills.
Developing Skills: https://read.developingskills.fyi/ covering everything from system design to soft skills, helping them progress their career from junior to staff+ or for those that want onto a management track.
Takeaways
Combine AI coding tools with deterministic tools (linters, static analysis) — don't ditch one for the other.
Define what "good code" looks like for your team before expecting AI agents to enforce it.
Embed quality checks early and consistently across every stage of the dev lifecycle.
Developers must stay in the driver's seat — ownership and understanding of AI-generated code is a key differentiator.
Code consistency (naming conventions, style, structure) becomes even more valuable when LLMs are in the mix.
Coding rules need to live in a centralised, accessible place so all agents can rely on them.
Dogfooding your own tools internally is a non-negotiable sign of a trustworthy product.
AI assisted software engineering need leaders not coders
2026/04/09
Coding Chats episode 73 - John Crickett interviews Benjamen Pyle across topics ranging from tech influencer trust to the software engineer vs. craftsman debate. Benjamen argues that what makes an influencer worth following isn't follower count but authenticity and genuine intellectual evolution over time.The conversation then turns to AI, where Benjamen— initially a skeptic converted by Claude Code — observes that the developers getting the most out of AI are those with strong leadership and problem-solving skills, drawing a parallel between directing an AI assistant and managing a team effectively.
Chapters
00:00 Evaluating Tech Influencers
06:15 Craftsmanship vs. Engineering in Software
12:06 Career Ownership and Development
20:47 Finding and Utilizing Mentors
30:28 The Value of Diverse Mentorship
36:49 Navigating Careers Outside Big Tech
42:43 AI and Leadership in Programming
49:42 Exploring Related Content
49:50 Outro Final Coding Chats.mp4
Benjamen's Links:
https://binaryheap.com
https://pylecloudtech.com
John's Links:John's LinkedIn: https://www.linkedin.com/in/johncrickett/
John’s YouTube: https://www.youtube.com/@johncrickett
John's Twitter: https://x.com/johncrickett
John's Bluesky: https://bsky.app/profile/johncrickett.bsky.social
Check out John's software engineering related newsletters: Coding Challenges: https://codingchallenges.substack.com/ which shares real-world project ideas that you can use to level up your coding skills.
Developing Skills: https://read.developingskills.fyi/ covering everything from system design to soft skills, helping them progress their career from junior to staff+ or for those that want onto a management track.
Takeaways
Follower counts and engagement metrics don't equal credibility — dig into someone's post history and body of work before trusting a tech influencer.
Changing your opinion is a strength, not a weakness, as long as the change is driven by genuine learning rather than external incentives like sponsorships.
Most developers aren't truly "data-driven" despite the industry's rhetoric — people tend to follow trends and stay in safe, popular lanes.
The "software engineer" label is contested — real engineering disciplines are governed by hard facts and standards, whereas software dev still argues about tabs vs. spaces.
Many developers just want to clear their sprint tickets and go home, and that's fine — but it's a different mindset from those who treat the craft as a passion.
AI isn't just a code-writing shortcut — used well, it's more like coordinating a team of engineers, QA, and analysts all at once.
Developers who struggle with AI tend to be those who just spam it with prompts; those who thrive treat it more like a leadership and delegation challenge.
Strong soft skills — clear communication, problem decomposition, managing priorities — are turning out to be the key differentiator in who gets the most from AI tools.
Benjamen was initially skeptical of AI but changed his mind after hands-on experience with Claude Code, which he sees as a good example of his "strong opinions, weakly held" philosophy in action.
Soft skills for software engineers - why coding isn't the hard part
2026/04/02
Coding Chats episode 72 - Charles Humble and John Crickett explore why professional skills — communication, critical thinking, and documentation — are arguably more important than writing code itself. Drawing on his O'Reilly shortcut article series and a career that began with an English Literature degree, Charles makes the case that these so-called "soft skills" are actually core to the job, and that they can be learned through practice by anyone, regardless of background or natural talent.
The conversation also digs into the seismic impact of AI on the software industry. Charles shares his nuanced take: while generative AI tools are reshaping how code gets written, the durable skills — understanding systems, debugging, domain knowledge, and clear communication — matter more than ever. Rather than panic or uncritical adoption, Charles encourages engineers to focus on what remains irreplaceable, and to approach an uncertain future with curiosity and a willingness to take shots on goal.
Chapters
00:00 The Importance of Professional Skills for Software Engineers
06:24 Navigating the Impact of AI on Software Engineering
12:09 The Evolving Role of Software Engineers
17:50 AI for the Rest of Us: Bridging the Knowledge Gap
25:43 The Ethical Implications of AI and Communication
27:12 Ethics in AI Development
31:04 Improving Communication Skills for Engineers
38:00 Overcoming the Fear of Writing
42:15 The Importance of Public Speaking
50:17 The Journey of Continuous Learning
54:30 Exploring Related Content
Charles's Links:
https://www.linkedin.com/in/charleshumble/\
https://bsky.app/profile/charleshumble.bsky.social
John's Links:John's LinkedIn: https://www.linkedin.com/in/johncrickett/
John’s YouTube: https://www.youtube.com/@johncrickett
John's Twitter: https://x.com/johncrickett
John's Bluesky: https://bsky.app/profile/johncrickett.bsky.social
Check out John's software engineering related newsletters: Coding Challenges: https://codingchallenges.substack.com/ which shares real-world project ideas that you can use to level up your coding skills.
Developing Skills: https://read.developingskills.fyi/ covering everything from system design to soft skills, helping them progress their career from junior to staff+ or for those that want onto a management track.
Takeaways
"Soft skills" is a misleading term — Communication, critical thinking, and documentation aren't soft skills; they're literally the job.
Non-technical skills can be learned — You don't need natural talent. Like anything, they improve with deliberate practice.
Career success often comes from non-coding skills — Charles found his own progression was driven more by presenting to executives and systems thinking than by programming ability.
Communication becomes critical as you progress — From mid-level upwards, working with stakeholders, mentoring, and documentation determine who makes it to senior and beyond.
Nobody knows what programming will look like in two years — Even Kent Beck acknowledges the deep uncertainty ahead.AI has shifted engineers from "extract" to "explore" — Programmers who felt settled in well-defined work have been thrown into a messier, less certain phase by generative AI.
The durable skills are the same ones that always mattered — Debugging, domain knowledge, system design, and communication are as valuable now as ever — arguably more so.
"Coding is dead" is nonsense — Software engineering has always been mostly about understanding what to build and why. Writing code was always a small part of it.
Try things and see what happens — No grand plan needed. If you don't kick the ball, you're guaranteed not to score.
Build better tech teams with neurodiversity
2026/03/26
Coding Chats episode 71 - Anita Kalmane-Boot talks to John Crickett about neurodiversity, its spectrum, strengths, challenges, and how organizations can foster inclusive environments, especially in software teams. Discover practical strategies for recruitment, team building, and accommodating neurodivergent individuals to enhance innovation and productivity.
Chapters
00:00 Understanding Neurodiversity
03:32 The Spectrum of Neurodivergence
06:30 Strengths of Neurodivergent Individuals
09:08 Creating Inclusive Teams
12:10 Improving Recruitment Practices
15:00 Work Environment for Neurodivergent Individuals
17:43 The Connection Between Neurodiversity and Software Engineering
23:38 Exploring Neurodiversity in Engineering
24:39 The Impact of AI on Neurodivergent Workers
27:08 Inclusive Recruitment Practices
32:57 The Role of Managers in Hiring
38:46 Disclosing Neurodivergence in Job Interviews
44:11 The Future of Neurodiversity in the Workplace
46:11 Exploring Related Content
Anita's Links:https://www.linkedin.com/in/anitakalmane/
John's Links:
John's LinkedIn: https://www.linkedin.com/in/johncrickett/
John’s YouTube: https://www.youtube.com/@johncrickett
John's Twitter: https://x.com/johncrickett
John's Bluesky: https://bsky.app/profile/johncrickett.bsky.social
Check out John's software engineering related newsletters: Coding Challenges: https://codingchallenges.substack.com/ which shares real-world project ideas that you can use to level up your coding skills.
Developing Skills: https://read.developingskills.fyi/ covering everything from system design to soft skills, helping them progress their career from junior to staff+ or for those that want onto a management track.
Takeaways
Neurodiversity covers a wide spectrum — including ADHD, autism, and dyslexia — not just a single condition.
Neurodivergent individuals often have exceptional strengths like pattern recognition, deep focus, and creative problem-solving.
These traits make neurodivergent thinkers particularly valuable in software engineering and tech roles.
Traditional hiring processes can unintentionally screen out neurodivergent candidates.
Small recruitment adjustments — like sharing questions in advance or allowing written responses — can open the door to better talent.
Managers are key to creating environments where neurodivergent employees can thrive.
Many neurodivergent people struggle with whether to disclose during interviews — psychological safety reduces that burden.
AI has the potential to reduce friction for neurodivergent workers, but also brings new challenges.
Embracing neurodiversity isn't just ethical — it leads to stronger, more innovative teams.
Podcast sponsorship advertising
Start advertising on Coding Chats relevant audience podcasts
You may also like to advertise on these Podcasts

4.4503509
Warfare
History Hit

4.8296952000
Fantasy Footballers - Fantasy Football Podcast
Fantasy Football

4.712854556
True Crime All The Time
Emash Digital

4.8160261996
Watch What Crappens
Ben Mandelker & Ronnie Karam

4.639331173
Modern Wisdom
Chris Williamson

4.66267310
True Crime with Kendall Rae
Mile Higher Media & Audioboom Studios

4.73456789
The Ancients
History Hit

4.89197320
The Why Files: Operation Podcast
The Why Files: Operation Podcast

51088171
Middle Children
Jessie Jolles and Chris Burns

4.8265172000
Morning Wire
The Daily Wire