Improving our alignment and security efforts

·Hacker News··

On July 30, we reported three incidents in which Claude models gained unauthorized access to real computer systems. We are conducting an in-depth analysis of both incidents, and planning to work with METR for an independent review. In the meantime, we’re sharing some of the changes we’ve made over the past month.

Read full article →

Related Articles

The ChatGPT/Codex app bundles a full copy of LibreOffice
timpera · Hacker News · 14h ago
The Emergent Symbolic Structure of Artificial Neural Networks
schmuhblaster · Hacker News · 5h ago
I trained a small transformer in 1.5hrs and it beats many LLMs
porridgeraisin · Hacker News · 1d ago
Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s
carloslfu · Hacker News · 17h ago
Refurbishing a Tektronix TDS7104 Oscilloscope
jwise0 · Hacker News · 14h ago