241
The cult of vibe coding is dogfooding run amok
Bad software is a choice you make
242
ML promises to be profoundly weird
This is a long article, so I've broken it up into a series of posts, listed below. You can also read the full work as a PDF or EPUB .
243
LLM Voice
The uncanny valley of LLMs' prose
244
Ex-GitHub CEO launches a new developer platform for AI agents
Announcing Entire with $60 million seed round and shipping our first product, called Checkpoints.
245
What Claude Code chooses
Benchmarking and Ground Control for developer tool providers. Understand agent choices and test what helps them succeed.
246
Advancing the price-performance frontier with GPT‑5.6
Explore lower GPT‑5.6 pricing for Luna and Terra—and how OpenAI’s more efficient models help enterprises deploy AI workflows at scale.
247
How to stop Claude from saying load-bearing
Hack the text output of Claude Code to make life a little bit sillier.
248
Grok 4.7
SpaceXSI's most powerful model for coding and knowledge work. Twice as fast, at half the price of comparable models.
249
Claude Code uses Bun written in Rust now
In Rewriting Bun in Rust Jarred Sumner made the following claim: Claude Code v2.1.181 (released June 17th) and later use the Rust port of Bun. Startup got 10% faster on …
250
AlphaGenome Atlas: a high-resolution map of human DNA
We’re introducing AlphaGenome Atlas, a database predicting the effects of every possible single nucleotide variant in the human genome.
251
Nano Banana 2: Google's latest AI image generation model
Our latest image generation model offers advanced world knowledge, production-ready specs, subject consistency and more, all at Flash speed.
252
4TB of voice samples just stolen from 40k AI contractors at Mercor
Lapsus$ posted Mercor on its leak site. Voice biometrics plus ID documents in one bundle is a deepfake-ready kit. Here is what to do.
253
A Jev that can ask Opus for help gives Opus accuracy at 4x lower cost
We tested Jev and GPT-6 Luna as judges for identity resolution. A hybrid of Jev and Claude Opus matched frontier accuracy at over 4x lower cost.
254
Qwen3.6-Plus: Towards real world agents
Qwen offers comprehensive functionality spanning chatbot, image and video understanding, image generation, document processing, web search integration, tool utilization, and artifacts.
255
Plan mode is dead
Earlier this year, I believed planning was going to become the most important part of building software with AI.
256
Mistral X Mozilla: Private, Multilingual AI Browsing
Open, private and multilingual AI is coming to your web browser. Mistral and Mozilla team up to put powerful, trustworthy AI where you already browse.
257
Agents need control flow, not more prompts
Thesis: reliable agents tackling complex tasks need deterministic control flow encoded in software, not increasingly elaborate prompt chains If you’ve eve...
258
Astra for Law
OpenAI for Law brings frontier intelligence for law, custom firm workflows, connected legal data sources, and legal-grade controls for confidential client work.
259
Ember-1
Ember-1 is a new specialized model from Fireworks Research that delivers Kimi K3’s quality with 40% fewer tokens.
260
Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint
Ternary Bonsai 2 27B retains 98.2% of Qwen3.8 27B benchmark performance in a 5.9GB footprint, with multimodal and agentic capabilities.
261
Exploiting the most prominent AI agent benchmarks
Every week, a new AI model climbs to the top of a benchmark leaderboard. Companies cite these numbers in press releases. Investors use them to justify valuations. Engineers use them to pick which model to deploy. The implicit promise is simple: a higher score means a more capable system.
262
OpenAI’s accidental attack against Hugging Face is science fiction that happened
This story is wild. The short version: OpenAI were running a cybersecurity test against an unreleased model, with the model’s guardrail features turned off. Rather than solve the test, the …
263
The bottleneck was never the code
The other month I finally ran an experiment we had been postponing for over a year at .txt.
264
LLM Architecture Gallery
A gallery that collects architecture figures from The Big LLM Architecture Comparison and related articles, with fact sheets and links back to the original sections.
265
Google fixed more Chrome bugs in June than over the past two years, thanks to AI
Chrome uses Gemini AI to automate vulnerability discovery, triage, and patching, accelerating updates to match modern security risks.
266
267
268
Claude's new constitution
A new approach to a foundational document that expresses and shapes who Claude is
269
Running local models on an M4 with 24GB memory
Experiments with getting usable outputs out of local models on a standard Macbook
270
