Inverse Rubric Optimization: A testbed for agent science
(news.ycombinator.com)
1.
2.
Using coding assistance tools to revive projects you never were going to finish
(news.ycombinator.com)
3.
Anonymous request-token comparisons from Opus 4.6 and Opus 4.7
(news.ycombinator.com)
4.
Epoch confirms GPT5.4 Pro solved a frontier math open problem
(news.ycombinator.com)
5.
Cross-Model Void Convergence: GPT-5.2 and Claude Opus 4.6 Deterministic Silence
(news.ycombinator.com)
6.
Common Lisp Development Tooling
(news.ycombinator.com)
7.
How I write software with LLMs
(news.ycombinator.com)
8.
1M context is now generally available for Opus 4.6 and Sonnet 4.6
(news.ycombinator.com)
9.
"Car Wash" test with 53 models
(news.ycombinator.com)