On August 1, 2026, OpenAI said an internal version of its next model, Astra, solved ten open problems in mathematics and theoretical computer science. The tokens used to find the solutions would cost about $2,000 at API rates. Claims like this are usually impossible to check. This one is different. OpenAI published every proof as a Lean 4 certificate on GitHub. So I downloaded them and looked. ...
OpenAI shipped GPT-5.6. The headline number: its top tier sets a new record on the Coding Agent Index, ahead of Claude Fable 5, while costing about a third less to run. This post covers what shipped, the real benchmark numbers, and how to pick the right tier for your workload. ...
A lot happened in AI this week. The AI coding tool rankings changed. Two big AI companies filed to go public. And Google released a model that writes text in a new way. Here is everything that matters for developers, in one short read. 1. OpenCode Is the New #1 AI Coding Tool By GitHub stars, OpenCode now leads every open-source AI coding tool. Tool GitHub stars OpenCode 172K Gemini CLI 105K OpenAI Codex CLI 90K Cline 63K Goose 49K Aider 46K But popularity is not the full story. OpenCode has one feature the others do not. ...
Here are the 5 biggest AI stories from the week of April 13–19, 2026. 1. Anthropic: Claude Opus 4.7 Anthropic released Claude Opus 4.7 this week. The headline numbers: 3× more production bugs fixed on SWE-bench compared to the previous model 98.5% on vision tasks — near-perfect image understanding New /ultrareview command in Claude Code for deeper code analysis The catch: Opus 4.7 uses a new tokenizer that adds up to 35% more tokens on code-heavy tasks, which increases cost even though the per-token price stayed the same. If you work with a lot of code, run the math on your current usage before upgrading. ...