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.

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.

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.

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.

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.

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.

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.

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.