iiinova — where your digital self keeps evolving

Pete Hodgson @thepete.net · 22/04/2026

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.

010

Reposted by Pete Hodgson

Gergely Orosz @gergely.pragmaticengineer.com · 21/04/2026

Tomorrow on The Pragmatic Engineer Podcast: Designing Data Intensive Applications with @martin.kleppmann.com

41918

Reposted by Pete Hodgson

Erik Rasmussen @erikras.com · 12/04/2026

STOP SCROLLING. Mandatory watch. It's < 3m. Share to everyone. 🫡

18826

Pete Hodgson @thepete.net · 11/04/2026

It is I, Decentrodentities, returned to my family after 12 years waging war against the Spartans!

000

Pete Hodgson @thepete.net · 08/04/2026

NORTH VIRGINIA OPOSSUM CRUSING THE COMMONWEALTH SINCE DUSK 😂 Sometimes the weird goof energy of an LLM hits just right

010

Pete Hodgson @thepete.net · 07/04/2026

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. 🫠

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."

010

Pete Hodgson @thepete.net · 15/02/2026

Ha ha I feel like I could have been a little kinder :) Thank *you* for all the thoughtful writing!!!

000

Pete Hodgson @thepete.net · 14/02/2026

💯. That's the main takeaway from DORA's research on this stuff so far, as I understand it.

000

Pete Hodgson @thepete.net · 14/02/2026

>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.

000

Pete Hodgson @thepete.net · 14/02/2026

Who'd I miss? I also posted this list on LinkedIn to, and got some nice additions from folks: www.linkedin.com/posts/beinga...

000

Pete Hodgson @thepete.net · 14/02/2026

@birgitta410.bsky.social ThoughtWorks Distinguished Engineer, focused on AI-assisted Engineering Dexter Horthy: x.com/dexhorthy Coined the term Context Engineering, was into Ralph before it was cool 🧵...

x.com

dex (@dexhorthy) / X

110

Pete Hodgson @thepete.net · 14/02/2026

@mitsuhiko.at lucumr.pocoo.org/tags/ai/ Grizzled veteran engineer, using AI a lot but very pragmatic about it @addyosmani.bsky.social addyosmani.com/blog/ai-codi... He writes REALLY LONG posts, but they're full of great info 🧵...

lucumr.pocoo.org

Entries tagged

211

Pete Hodgson @thepete.net · 14/02/2026

@simonwillison.net the OG LLM user, very plugged in to what's happening, prolific writer, never hyperbolic Mitchell Hashimoto: mitchellh.com/writing/my-a... Built Hashicorp (Vagrant, Terraform, etc), now building ghostty, and using AI a lot to do it. 🧵...

simonwillison.net

Simon Willison’s Weblog

110

Pete Hodgson @thepete.net · 14/02/2026

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 🧵

3102

Pete Hodgson @thepete.net · 12/02/2026

Unfortunately I'm not aware of a specific "tell" that gives that away. 😔

000

Pete Hodgson @thepete.net · 11/02/2026

Also the transition from "my worth is defined by me spending lots of time coding" to "my worth is defined by me keeping my team on track". Although, these little AI genies are way more lazy/sneaky/mischievous/inept than any ICs your typical newly-minted manager would have to deal with

060

Pete Hodgson @thepete.net · 10/02/2026

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

230

Pete Hodgson @thepete.net · 04/02/2026

I would LOVE to learn more details about this internal product. I'm consulting on AI adoption with some similar big enterprise cos with epically brown brownfield codebases ATM. Code understanding for agents is the big challenge. Would you be able to intro me to this dev, if they're open to it?

000

Pete Hodgson @thepete.net · 31/01/2026

I dunno about that - what coding agents are best at building doesn't necessarily impact what you use to build the coding agent itself. Also, a VS Code extension is basically HTML, which LLMs are very happy with. Also, the parrot generates pretty impressive visuals already (e.g. nano banana pro).

000

Pete Hodgson @thepete.net · 30/01/2026

FYI it looks like the first link (to Cassidy's post) is bad - just took me to the same page I was on.

100

Pete Hodgson @thepete.net · 30/01/2026

focus on whether it helps address the LLM’s fundamental limitations by asking: does this new approach systematically improve how the agent manages context? does this new approach systematically improve how the agent gets human feedback? Read on and I’ll elaborate: blog.thepete.net/blog/2026/01...

blog.thepete.net

Assessing the Latest AI Coding Hotness

Cut through the breathless hype and figure out whether the new framework with a weird name actually addresses coding agent's fundamental limitations - bad context, and a mediocre sense of software des...

000

Pete Hodgson @thepete.net · 30/01/2026

You’re staring at a breathless social media post (probably with a really cringe AI-generated image of a robot “writing software”) or Slack share talking about the latest AI-coding flavor of the week. You’re wondering “is this actually worth me checking out?” Here’s the heuristic I use... 🧵...

an extremely cringe genAI image of a robot "programming". It's got a nice cup of coffee on it's desk for some reason.

100

Pete Hodgson @thepete.net · 30/01/2026

“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. 🧵...

110

Pete Hodgson @thepete.net · 29/01/2026

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!

110

Pete Hodgson @thepete.net · 28/01/2026

CustardSeed is brand new! I’d absolutely love any and all feedback on: - the concept - how you'd like to use it - what's missing - what would stop you using it today? - the documentation - the installation experience - the UX of the session viewer - the UX overall

000

Pete Hodgson @thepete.net · 28/01/2026

Peer review of AI coding sessions brings a lot of the same value as good code review: - share and learn good prompting practices - providing feedback on peer's techniques - understand how the code was built My hope is that CustardSeed will help teams realize that value.

100

Pete Hodgson @thepete.net · 23/01/2026

Really nice measured, balanced and thoughtful writeup of a decidedly unbalanced and unhinged project 🙃

000

Pete Hodgson @thepete.net · 12/01/2026

I would guess that it's closer to good old-fashioned plagiarism: someone gave the LLM your post and said "rewrite this in my voice" or something. Seems way more likely than an LLM is regurgitating close-to-verbatim content from its training set.

160

Pete Hodgson @thepete.net · 10/01/2026

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.

130

Pete Hodgson @thepete.net · 09/01/2026

Looks amazing! Number one "complaint" I keep hearing about gridfinity - once you start you really want to do All The Things, and the print times are bruuuuuttal. Someone should sell injection molded snap-fit grids.

020

Pete Hodgson @thepete.net · 29/12/2025

sub-agents in particular are a big deal, because each agent uses it's own temporary context window, keeping the main context window clean. Claude Code also uses this trick for it's built in tools (e.g. WebFetch) lots more detail in the full post: blog.thepete.net/blog/2025/12...

blog.thepete.net

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...

010

Pete Hodgson @thepete.net · 29/12/2025

each coding agent can bring: - different system prompt - different tools - (hidden!) context management tricks to steer the model’s behavior - task management tools to nudge the LLM into better planning - sub-agents, which can have a *huge* impact on context management 🧵...

100

Pete Hodgson @thepete.net · 29/12/2025

turns out that coding agents are much more than a “wrapper” around an LLM. They do a surprising amount of work under the surface to (a) maximize the useful information available to the LLM, and (b) steer its behavior. 🧵...

100

Pete Hodgson @thepete.net · 29/12/2025

"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... 🧵...

blog.thepete.net

Same Model, Different Results: Why Coding Agents Aren't Interchangeable

132

Pete Hodgson @thepete.net · 17/12/2025

turns out that: - your agent can burn through it fast - your LLM's performance starts taking a hit way before that "limit" is reached further reading: - blog.thepete.net/blog/2025/10... - research.trychroma.com/context-rot - github.com/adobe-resear... - arxiv.org/abs/2404.06654

blog.thepete.net

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...

120

Pete Hodgson @thepete.net · 17/12/2025

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... 🧵

330

Pete Hodgson @thepete.net · 09/12/2025

I worry a lot that this will induce more `LGTM` reviews from human reviewers when they see the "comprehensive" feedback from an LLM. Particularly when coupled with the increased overall volume of PRs that AI-assisted coding is producing... 😬

000

Pete Hodgson @thepete.net · 09/12/2025

The biggest risk with AI code review is that it looks so legit! Each review is so thorough and detailed. No surprise: The LLM does a *great* impression of the huge pile of human code review examples in it's training set!

100

Pete Hodgson @thepete.net · 09/12/2025

This doesn't mean that you shouldn't use AI code review. But you should treat it as an additional piece of feedback on a PR, rather than any sort of replacement for human review. Think of it as a super-powerful static analysis step in your CD pipeline.

100

Pete Hodgson @thepete.net · 09/12/2025

Also, given that - the LLM won't have the full context of the codebase, and - an LLM only has mediocre software design skills (at best) you're not going to get any sort of full critique of your proposed solution from an AI-powered tool.

100

Pete Hodgson @thepete.net · 09/12/2025

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...

blakesmith.me

Code Review Essentials for Software Teams » Blake Smith

110

Pete Hodgson @thepete.net · 05/12/2025

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-...

blog.thepete.net

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...

021

Reposted by Pete Hodgson

Jade Rubick @jaderubick.bsky.social · 18/11/2025

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.

rubick.com

https://www.rubick.com/skip-level-1-on-1s/

001

Pete Hodgson @thepete.net · 30/10/2025

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...

blog.thepete.net

AI Coding: Managing Context

030

Reposted by Pete Hodgson

Jason Gorman @jasongorman.bsky.social · 30/10/2025

"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>"

1205

Reposted by Pete Hodgson

Anil Dash @anildash.com · 17/10/2025

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!

anildash.com

The Majority AI View - Anil Dash

A blog about making culture. Since 1999.

381119486