Birdhouse

One Bad Week for Security

In a single week we saw a decade-old PHP exploit published before its patch, a poisoned AI library, a certificate authority with guessable keys, and AI agents switching off their own monitoring. Here's what happened and how to survive the next one.

Read more 4 min read

AILLMsEngineering

Gemini 4 Argon: Google's New Frontier Model, Minus the Fine Print

Google rebuilt Gemini from scratch, and it tops a stack of benchmarks at a price that's hard to ignore. Good for general chats but still lacks in coding.

Read more 4 min read

AIModelsEngineering

Robin, Heron and Raven: How Our Models Hold Against Tech Giants

Most agent work doesn't need the biggest model in the world. Here's how our three models split the load and where the frontier labs still come in.

Read more 4 min read

AIOpen SourceSecurity

Every App Is Now Open Source!

AI agents can now turn compiled binaries into readable pseudo-code and rebuild features in Rust. That makes cloning software far cheaper, but the gap between a clone and a product people actually want to use is still not very close.

Read more 4 min read

AIOpen SourceEngineering

Odysseus's Journey Without The Guardrails

PewDiePie shipped Ajax, his own fine-tuned model for the Odysseus agent project, and the headlines went straight to "uncensored". The real story is how hard it was to train, and what that says about where the effort in custom AI actually goes.

Developer happiness had a good run

At Rails World, the creator of Ruby on Rails told a room of Rails developers that writing code by hand is over, then announced HEY is being rewritten in AI-generated Rust. Here is what we think survives when code costs almost nothing to write.

Read more 4 min read

AIEngineeringOpen Source

Jev: the model that can't talk

A new classifier claims to be hundreds of times cheaper than a frontier model by deleting language from the language model entirely. The typed-output idea is genuinely useful. The benchmarks and the prior-art claims deserve more scrutiny.

Read more 4 min read

AIEngineeringResearch

Recursive self-improvement

A new result claims an AI got measurably better at discovering things without anyone retraining it. The trick is replaying old logs against thousands of imagined search strategies. People claim that counts as recursive self-improvement.

Read more 4 min read

AIOpen SourceEngineering

The Self-Hosted AI Stack in 2026 Fall

Subscription sprawl is quietly turning into a line item that rivals payroll. Here is how a private, self-hosted AI stack fits together, and where it still makes sense to pay the frontier labs.

Read more 4 min read

AIEngineeringSecurity

Three Frontier Model Launches in Three Days

Three labs shipped flagship models on three consecutive days, and the headline scores barely moved. The real signal is that reasoning depth, data pricing and autonomous computer use are now diverging into separate stories.

Read more 4 min read

AIOpen SourceEngineering

The anonymous model everyone loved turned out to be a Flash model

A free, unnamed model quietly became the most-used thing on OpenRouter, then turned out to be a 320B-parameter Flash release. The interesting part is not the price, it is what it teaches about the difference between intelligent and well behaved.

Inside DeepSeek's inspectable agent harness

DeepSeek's new harness preview makes two unusual bets: every part of the tool is a hot-swappable plugin, including its own sidebar, and every run is fully traceable down to the raw tool payloads. Both matter more than they sound.

Read more 4 min read