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.

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

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

💯💯💯 bcantrill.dtrace.org/2026/04/12/t...

NORTH VIRGINIA OPOSSUM 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. 🫠

>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.

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 🧵

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

“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. 🧵...

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!

Devs should be regularly sharing coding agent sessions with colleagues. 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 🙃

who hurt you?

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.

"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... 🧵...

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... 🧵

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...

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-...

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...

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...

"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>"

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%

Super interesting proof-of-concept exploit against an AI agent via GH pull request. Very sneaky prompt injection which convinces an AI coding agent to subtly inject a remote backdoor into a codebase. A great example of @simonwillison.net's Lethal Trifecta! blog.trailofbits.com/2025/08/06/p...

Good example of why it's important to monitor your LLM-powered features in prod. Apparently some bug in Amazon's AI assistant where the product description isn't in it's prompt. Pre-production evals are super important, but wouldn't catch this. Monitoring some key metrics in prod would.

Such a nice way to illustrate the point

they should be taken to The Hague for this graph crime

There are some amazing pro-tips for AI coding in this session: github.com/hellovai/ai-... Specifically, really good advice on how to manage agent context (which can have a big impact on the LLMs performance). If nothing else, just skim the summary and see if anything looks interesting. /🧵...

Hi #AWS -using friends. I’ve been writing some articles about fundamental AWS ops for small-medium companies, all oriented around AWS Organizations. So far I’ve covered org structure, Accounts, managing human users, IaC. I have another 4 or so articles still to come, so am about half way. (1/3)

This continues to shock and confuse me: the proportion of devs who are still not getting any active encouragement from their employers to start experimenting w. AI-assisted coding. Also goes to show how silly the "all devs will be replaced by AI in 2 years" claims are. /via @angiejones.tech

Github have a lot of good general advice on code review in an AI coding world here: github.blog/ai-and-ml/ge... 🧵 I have some thoughts...

Nice post from Korny Sietsma on trying to find the middle ground between the AI coding Maximalists and the AI coding luddites. blog.korny.info/2025/07/19/c... 🧵...

Pete Hodgson continues his excellent writing on Gen AI by proposing an approach to leading engineers towards an AI-assisted future, centered around a the concept of aligned autonomy. blog.thepete.net/blog/2025/06... @thepete.net

“Listen, I’m wondering if our engineers are doing enough with AI…” your CEO says, as the two of you sit down for your 1:1. Wouldn't it be great to have a true strategy in place for adopting AI-assisted coding? I've got you covered! blog.thepete.net/blog/2025/06...

I've seen a surge of discussions recently about large AI-generated change sets that are impossible to review by humans, paired with speculation if we still need to care about the code in the future. I expect to continue to care, especially if I'm on call for it martinfowler.com/articles/exp...

The replies in this thread are fascinating. Way different from the constant breathless hype I'm used to seeing in general. A bit depressing though.

A great way to get started with feature flags!

Days like today I can't believe I get to live here

Cool, so we’ll get amazing productivity boosts with agentic AI, we just have to build Earth 2 as a test environment first…

The rule holds: if it wasn't DNS, then it was probably a config change. #hugops status.cloud.google.com/incidents/ow...

You can already read the full, unedited version of the book online at craftingengstrategy.com (most of those have also come out on my blog over the past 18 months as I wrote)

*Lots* of really good guidance and concrete tips on AI-assisted coding in this post!

Zeno: okay team, we're half way through the sprint

Yep, same. I had the exact same experience, going from really enjoying it to just not wanting to use it at all. I switched to Gemini's voice chat 🤷

Interesting analysis of the commit history for a cloudflare library where the (AI skeptic) developer tried to use Claude Code as much as possible. Seems like it went surprisingly well. www.maxemitchell.com/writings/i-r...

Detailed dissection of an async coding agent (Codex) autonomously working through a (v. simple) task. I'm perhaps beating this metaphor to death, but it really does feel like the inner monologue of a junior engineer working solo through their first ticket after joining a new team. Act accordingly.

How do you move fast, with safety? Out today, our new eBook brings together some of the brightest minds in software development from organisations like @openfeature.dev and eBay to answer this question with a practical guide to introducing feature flags at scale. www.flagsmith.com/ebook/scalin...