Pete Hodgson
@thepete.net
Outside expert helping engineering teams adopt AI
This new benchmark is an apt metaphor for the AIs ability to gaslight humans with legit-looking-but-wrong output.
Oh, you can't find the raccoon? Huh. Sorry you're having trouble with that, meatsack. I tried to not make it TOO hard for you, lil bud, but I'll make it even easier next time.
Oh, you can't find the raccoon? Huh. Sorry you're having trouble with that, meatsack. I tried to not make it TOO hard for you, lil bud, but I'll make it even easier next time.
I came up with a somewhat foolish new benchmark for testing image generation models, to exercise the new ChatGPT Images 2.0:
"Do a where's Waldo style image but it's where is the raccoon holding a ham radio"
simonwillison.net/2026/Apr/21/...
"Do a where's Waldo style image but it's where is the raccoon holding a ham radio"
simonwillison.net/2026/Apr/21/...
Where’s the raccoon with the ham radio? (ChatGPT Images 2.0)
OpenAI released ChatGPT Images 2.0 today, their latest image generation model. On the livestream Sam Altman said that the leap from gpt-image-1 to gpt-image-2 was equivalent to jumping from GPT-3 …
simonwillison.net
April 22, 2026 at 2:04 AM
This new benchmark is an apt metaphor for the AIs ability to gaslight humans with legit-looking-but-wrong output.
Oh, you can't find the raccoon? Huh. Sorry you're having trouble with that, meatsack. I tried to not make it TOO hard for you, lil bud, but I'll make it even easier next time.
Oh, you can't find the raccoon? Huh. Sorry you're having trouble with that, meatsack. I tried to not make it TOO hard for you, lil bud, but I'll make it even easier next time.
Reposted by Pete Hodgson
Tomorrow on The Pragmatic Engineer Podcast: Designing Data Intensive Applications with @martin.kleppmann.com
April 21, 2026 at 8:07 PM
Tomorrow on The Pragmatic Engineer Podcast: Designing Data Intensive Applications with @martin.kleppmann.com
Reposted by Pete Hodgson
STOP SCROLLING. Mandatory watch. It's < 3m.
Share to everyone. 🫡
Share to everyone. 🫡
April 12, 2026 at 8:02 AM
STOP SCROLLING. Mandatory watch. It's < 3m.
Share to everyone. 🫡
Share to everyone. 🫡
Reposted by Pete Hodgson
April 12, 2026 at 6:37 PM
NORTH VIRGINIA OPOSSUM
CRUSING THE COMMONWEALTH SINCE DUSK
😂 Sometimes the weird goof energy of an LLM hits just right
CRUSING THE COMMONWEALTH SINCE DUSK
😂 Sometimes the weird goof energy of an LLM hits just right
From the comments: /* Earring sparkle */, , , ... static.simonwillison.net/static/2026/...
April 8, 2026 at 3:19 AM
NORTH VIRGINIA OPOSSUM
CRUSING THE COMMONWEALTH SINCE DUSK
😂 Sometimes the weird goof energy of an LLM hits just right
CRUSING THE COMMONWEALTH SINCE DUSK
😂 Sometimes the weird goof energy of an LLM hits just right
Reminder for whoever needs to hear it, today's cutting edge AI models are still very jagged in their "PhD-level intelligence".
Put more bluntly, Opus 4.6 Extended sometimes can't count to 2. 🫠
Put more bluntly, Opus 4.6 Extended sometimes can't count to 2. 🫠
![transcript from a Claude.ai session with Opus 4.6 Extended which includes:
"push the [training run] from Tuesday to Thursday. That gives your lungs 3 more days."](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:ij4rzg5tbdfjjln5u2abun73/bafkreigcef3jbw2qbwnwgzhmzpyaia5r7vv6gbkwtj35ziflysl6qrd7by)
April 7, 2026 at 2:11 AM
Reminder for whoever needs to hear it, today's cutting edge AI models are still very jagged in their "PhD-level intelligence".
Put more bluntly, Opus 4.6 Extended sometimes can't count to 2. 🫠
Put more bluntly, Opus 4.6 Extended sometimes can't count to 2. 🫠
>As we’re entering the phase of single-use plastic software, we might be moving the whole layer of responsibility elsewhere.
"single-use plastic software" is a really a striking way of framing it. It feels very accurate, and I'm not sure how I feel about it.
"single-use plastic software" is a really a striking way of framing it. It feels very accurate, and I'm not sure how I feel about it.
Today Thorsten Ball said he's the bottleneck. I too am the bottleneck and it made me think. lucumr.pocoo.org/2026/2/13/th...
The Final Bottleneck
AI speeds up writing code, but accountability and review capacity still impose hard limits.
lucumr.pocoo.org
February 14, 2026 at 5:26 AM
>As we’re entering the phase of single-use plastic software, we might be moving the whole layer of responsibility elsewhere.
"single-use plastic software" is a really a striking way of framing it. It feels very accurate, and I'm not sure how I feel about it.
"single-use plastic software" is a really a striking way of framing it. It feels very accurate, and I'm not sure how I feel about it.
It's hard to find balanced opinions on AI coding. Lots of the people pushing the envelope on AI-Assisted Engineering also have somewhat bonkers AI-maximalist perspectives.
Here's some people who're in the thick of it, advancing the field but who I also trust to bring a thoughtful, balanced take
🧵
Here's some people who're in the thick of it, advancing the field but who I also trust to bring a thoughtful, balanced take
🧵
February 14, 2026 at 5:20 AM
It's hard to find balanced opinions on AI coding. Lots of the people pushing the envelope on AI-Assisted Engineering also have somewhat bonkers AI-maximalist perspectives.
Here's some people who're in the thick of it, advancing the field but who I also trust to bring a thoughtful, balanced take
🧵
Here's some people who're in the thick of it, advancing the field but who I also trust to bring a thoughtful, balanced take
🧵
Hot-ish take: devs should be spending time now learning out how to be *efficient* with the tokens in their agent's context windows
1) it makes the agent perform better
2) tokens are gonna start costing more over the next couple of years
These Ralph shenanigans might look real silly in retrospect
1) it makes the agent perform better
2) tokens are gonna start costing more over the next couple of years
These Ralph shenanigans might look real silly in retrospect
February 10, 2026 at 5:40 AM
Hot-ish take: devs should be spending time now learning out how to be *efficient* with the tokens in their agent's context windows
1) it makes the agent perform better
2) tokens are gonna start costing more over the next couple of years
These Ralph shenanigans might look real silly in retrospect
1) it makes the agent perform better
2) tokens are gonna start costing more over the next couple of years
These Ralph shenanigans might look real silly in retrospect
“Have you tried out Ralph Wiggum loop?!”
“Are you still using beads?”
“Is Gas Town actually legit?”
“Know anyone who’s into BMAD?”
These days I’m glad my family doesn’t know what my Serious Work Conversations sound like. It’s embarrassing.
Let’s talk about how to deal with all this noise.
🧵...
“Are you still using beads?”
“Is Gas Town actually legit?”
“Know anyone who’s into BMAD?”
These days I’m glad my family doesn’t know what my Serious Work Conversations sound like. It’s embarrassing.
Let’s talk about how to deal with all this noise.
🧵...
January 30, 2026 at 3:33 PM
“Have you tried out Ralph Wiggum loop?!”
“Are you still using beads?”
“Is Gas Town actually legit?”
“Know anyone who’s into BMAD?”
These days I’m glad my family doesn’t know what my Serious Work Conversations sound like. It’s embarrassing.
Let’s talk about how to deal with all this noise.
🧵...
“Are you still using beads?”
“Is Gas Town actually legit?”
“Know anyone who’s into BMAD?”
These days I’m glad my family doesn’t know what my Serious Work Conversations sound like. It’s embarrassing.
Let’s talk about how to deal with all this noise.
🧵...
Claude Code is an amazing product. It does amazing things. I love it. Amazing.
It's also most typically used as a CLI tool.
This does not mean that Claude Code is an amazing product BECAUSE it's a CLI.
Tell me why I'm wrong!
It's also most typically used as a CLI tool.
This does not mean that Claude Code is an amazing product BECAUSE it's a CLI.
Tell me why I'm wrong!
January 29, 2026 at 9:08 PM
Claude Code is an amazing product. It does amazing things. I love it. Amazing.
It's also most typically used as a CLI tool.
This does not mean that Claude Code is an amazing product BECAUSE it's a CLI.
Tell me why I'm wrong!
It's also most typically used as a CLI tool.
This does not mean that Claude Code is an amazing product BECAUSE it's a CLI.
Tell me why I'm wrong!
Devs should be regularly sharing coding agent sessions with colleagues.
I made a thing to make this super duper easy: custardseed.com
🧵...
I made a thing to make this super duper easy: custardseed.com
🧵...
CustardSeed - Publish Claude Code Sessions
Instantly share your Claude Code sessions online. Turn your sessions into shareable web pages with a simple slash command. Store sessions as GitHub Gists and view them beautifully rendered.
custardseed.com
January 28, 2026 at 2:59 AM
Devs should be regularly sharing coding agent sessions with colleagues.
I made a thing to make this super duper easy: custardseed.com
🧵...
I made a thing to make this super duper easy: custardseed.com
🧵...
Really nice measured, balanced and thoughtful writeup of a decidedly unbalanced and unhinged project 🙃
I have Gas Town derangement syndrome and spent the last few weeks writing thousands of words on agent orchestration patterns; how they shift our bottlenecks and force us to ask whether and when we should stop looking at code
maggieappleton.com/gastown
maggieappleton.com/gastown
Gas Town’s Agent Patterns, Design Bottlenecks, and Vibecoding at Scale
On agent orchestration patterns, why design and critical thinking are the new bottlenecks, and whether we should let go of looking at code
maggieappleton.com
January 23, 2026 at 11:38 PM
Really nice measured, balanced and thoughtful writeup of a decidedly unbalanced and unhinged project 🙃
Gonna start saying "Clod" when referring to Claude Code.
I've felt a need to use its full name to disambiguate between the Claude Code - the coding agent - vs Claude - the general purpose chat bot, but it's so tedious to type it out in full.
It's either CC or Clod, and Clod is more fun.
I've felt a need to use its full name to disambiguate between the Claude Code - the coding agent - vs Claude - the general purpose chat bot, but it's so tedious to type it out in full.
It's either CC or Clod, and Clod is more fun.
January 10, 2026 at 3:43 AM
Gonna start saying "Clod" when referring to Claude Code.
I've felt a need to use its full name to disambiguate between the Claude Code - the coding agent - vs Claude - the general purpose chat bot, but it's so tedious to type it out in full.
It's either CC or Clod, and Clod is more fun.
I've felt a need to use its full name to disambiguate between the Claude Code - the coding agent - vs Claude - the general purpose chat bot, but it's so tedious to type it out in full.
It's either CC or Clod, and Clod is more fun.
"Why is Claude Code better/worse than [other coding agent] - they’re both using the same models under the hood?"
A reasonable question, so I spent some time reverse-engineering Claude Code's interactions with the model to illustrate why coding agent matters
blog.thepete.net/blog/2025/12...
🧵...
A reasonable question, so I spent some time reverse-engineering Claude Code's interactions with the model to illustrate why coding agent matters
blog.thepete.net/blog/2025/12...
🧵...
Same Model, Different Results: Why Coding Agents Aren't Interchangeable
Reverse-engineering Claude Code reveals why it performs differently from other agents that use the same Anthropic models. The answer lies in sophisticated context engineering and tool orchestration hi...
blog.thepete.net
December 29, 2025 at 5:37 PM
"Why is Claude Code better/worse than [other coding agent] - they’re both using the same models under the hood?"
A reasonable question, so I spent some time reverse-engineering Claude Code's interactions with the model to illustrate why coding agent matters
blog.thepete.net/blog/2025/12...
🧵...
A reasonable question, so I spent some time reverse-engineering Claude Code's interactions with the model to illustrate why coding agent matters
blog.thepete.net/blog/2025/12...
🧵...
I continue to believe that context management is the #1 skill to develop if you want to get the most out of coding agents.
But why? Modern models have a context limit of 200,000 tokens! That seems like a lot!
There's a couple of reasons why...
🧵
But why? Modern models have a context limit of 200,000 tokens! That seems like a lot!
There's a couple of reasons why...
🧵
December 17, 2025 at 9:35 PM
I continue to believe that context management is the #1 skill to develop if you want to get the most out of coding agents.
But why? Modern models have a context limit of 200,000 tokens! That seems like a lot!
There's a couple of reasons why...
🧵
But why? Modern models have a context limit of 200,000 tokens! That seems like a lot!
There's a couple of reasons why...
🧵
This is a great summary of what code review is REALLY for.
It also demonstrates why AI-powered code review does not help AT ALL with the most important aspects of code review: aligning the team around software design (#1 and #3 in the hierarchy).
blakesmith.me/2015/02/09/c...
It also demonstrates why AI-powered code review does not help AT ALL with the most important aspects of code review: aligning the team around software design (#1 and #3 in the hierarchy).
blakesmith.me/2015/02/09/c...
Code Review Essentials for Software Teams » Blake Smith
blakesmith.me
December 9, 2025 at 6:51 PM
This is a great summary of what code review is REALLY for.
It also demonstrates why AI-powered code review does not help AT ALL with the most important aspects of code review: aligning the team around software design (#1 and #3 in the hierarchy).
blakesmith.me/2015/02/09/c...
It also demonstrates why AI-powered code review does not help AT ALL with the most important aspects of code review: aligning the team around software design (#1 and #3 in the hierarchy).
blakesmith.me/2015/02/09/c...
AI WON'T turn you into a 10x engineer but it CAN accelerate your day-to-day work.
I'm hosting a live workshop early next month to help experienced devs level up from copilot to coding agents.
No breathless hype, no "learn this one magical prompt" BS, I promise!
blog.thepete.net/ai-assisted-...
I'm hosting a live workshop early next month to help experienced devs level up from copilot to coding agents.
No breathless hype, no "learn this one magical prompt" BS, I promise!
blog.thepete.net/ai-assisted-...
AI-assisted Engineering Workshop Series
Level up from copilot to coding agents in this practical online workshop teaching AI-assisted Engineering practices for experienced developers. No breathless claims about 10x productivity. No suggesti...
blog.thepete.net
December 5, 2025 at 4:46 PM
AI WON'T turn you into a 10x engineer but it CAN accelerate your day-to-day work.
I'm hosting a live workshop early next month to help experienced devs level up from copilot to coding agents.
No breathless hype, no "learn this one magical prompt" BS, I promise!
blog.thepete.net/ai-assisted-...
I'm hosting a live workshop early next month to help experienced devs level up from copilot to coding agents.
No breathless hype, no "learn this one magical prompt" BS, I promise!
blog.thepete.net/ai-assisted-...
Reposted by Pete Hodgson
One thing you can do with skip levels is ask questions about things you believe you've communicated. You'll be surprised how often people haven't really internalized it.
https://www.rubick.com/skip-level-1-on-1s/
www.rubick.com
November 18, 2025 at 3:14 PM
One thing you can do with skip levels is ask questions about things you believe you've communicated. You'll be surprised how often people haven't really internalized it.
Slides from my #kubecon talk today
Feature Flags Suck! - The Problems With Feature Flagging and How To Avoid Them
speakerdeck.com/phodgson/fea...
Feature Flags Suck! - The Problems With Feature Flagging and How To Avoid Them
speakerdeck.com/phodgson/fea...
Feature Flags Suck! - KubeCon Atlanta 2025
<strong>Feature Flags Suck! - The Problems With Feature Flagging and How To Avoid Them</strong>
OK, feature flags are actually pretty awesome, but if…
speakerdeck.com
November 13, 2025 at 5:13 PM
Slides from my #kubecon talk today
Feature Flags Suck! - The Problems With Feature Flagging and How To Avoid Them
speakerdeck.com/phodgson/fea...
Feature Flags Suck! - The Problems With Feature Flagging and How To Avoid Them
speakerdeck.com/phodgson/fea...
Blurghed about managing you AI coding agent's context.
Proactively trimming and refining the context your agent is working with is probably THE best way to improve the quality of it's work.
But there's more to it than firing off a `/compact` every now and then.
blog.thepete.net/blog/2025/10...
Proactively trimming and refining the context your agent is working with is probably THE best way to improve the quality of it's work.
But there's more to it than firing off a `/compact` every now and then.
blog.thepete.net/blog/2025/10...
AI Coding: Managing Context
Managing your coding agent's context is super important - a bloated context window will erode the quality of your agent's work over time. Learn some new techniques for trimming irrelevant details from...
blog.thepete.net
October 30, 2025 at 4:45 PM
Blurghed about managing you AI coding agent's context.
Proactively trimming and refining the context your agent is working with is probably THE best way to improve the quality of it's work.
But there's more to it than firing off a `/compact` every now and then.
blog.thepete.net/blog/2025/10...
Proactively trimming and refining the context your agent is working with is probably THE best way to improve the quality of it's work.
But there's more to it than firing off a `/compact` every now and then.
blog.thepete.net/blog/2025/10...
Reposted by Pete Hodgson
"Many developers are surprised by the changes they have to make to their workflow when they're using AI. For example, <proceeds to describe eXtreme Programming>"
October 30, 2025 at 4:01 AM
"Many developers are surprised by the changes they have to make to their workflow when they're using AI. For example, <proceeds to describe eXtreme Programming>"
Reposted by Pete Hodgson
Okay, for the folks who asked: here's the majority AI view, writing up the reasonable, thoughtful view on AI that the vast majority of people in tech hold, that gets overshadowed by the bluster and hype of the tycoons trying to shill their nonsense. anildash.com/2025/10/17/t... Please share!
The Majority AI View - Anil Dash
A blog about making culture. Since 1999.
anildash.com
October 17, 2025 at 7:29 PM
Okay, for the folks who asked: here's the majority AI view, writing up the reasonable, thoughtful view on AI that the vast majority of people in tech hold, that gets overshadowed by the bluster and hype of the tycoons trying to shill their nonsense. anildash.com/2025/10/17/t... Please share!
1000000%
I feel like how we feel about smoking on airplanes is how the next generation will feel about us just mainlining social media.
October 3, 2025 at 4:30 PM
1000000%