AI & ML
OpenAI and Anthropic share findings from a joint safety evaluation
OpenAI Blog0 views
OpenAI and Anthropic share findings from a first-of-its-kind joint safety evaluation, testing each other’s models for misalignment, instruction following, hallucinations, jailbreaking, and more—highlighting progress, challenges, and the value of cross-lab collaboration.
Source:https://openai.com/index/openai-anthropic-safety-evaluationPreviousCollective alignment: public input on our Model SpecNextHelping people when they need it most
Related posts
![Best Buy brings back 4K Blu-ray discs with an expanding collection, in-store availability [U]](https://9to5google.com/wp-content/uploads/sites/4/2020/03/Best-Buy-Store-Front.jpg?quality=82&strip=all&w=1600)
Best Buy brings back 4K Blu-ray discs with an expanding collection, in-store availability [U]
09to5Google
Hebbia sees improvements in financial research with GPT-6 Astra
0OpenAI Blog

How Cloudflare WAF protects against ruby2shell (CVE-2026-132825)
0Cloudflare Blog
Experts warn: nearly everyone in AI is susceptible to a honey trap scheme right now
0TechCrunch
Relics now play video, show PDFs and present slides
0dev.to

aster - personal AI from scratch
0dev.to