Months and months of safety preparations
1 / Today we launched gpt-5, finishing a huge week for OpenAI.
Weβve raised the bar for safety in both open and closed models. With gpt-oss and gpt-5, we introduced meaningful capability advancements with rigorous, industry-leading safeguards and safety testing.
1
19
3,083
GPT-5 with thinking is another model we are treating as High capability under the preparedness framework. We've activated biorisk safeguards in ChatGPT, like the ones in ChatGPT agent, and some new ones in the API.
nitter.gq/KerenGu/status/1945908β¦
We've updated our safeguards to be both more robust and precise, but you may still see that highly detailed dual use biology requests are being blocked. That's why we've introduced our Life Science Special Access program to Enterprise accounts. help.openai.com/en/articles/β¦
2
1
475
what a banger of a week over here
To summarize this week:
- we released general purpose computer using agent
- got beaten by a single human in atcoder heuristics competition
- solved 5/6 new IMO problems with natural language proofs
All of those are based on the same single reinforcement learning system
1
23
4,141
Keren Gu π±π©π»βπ» retweeted
1/N Iβm excited to share that our latest @OpenAI experimental reasoning LLM has achieved a longstanding grand challenge in AI: gold medal-level performance on the worldβs most prestigious math competitionβthe International Math Olympiad (IMO).
Keren Gu π±π©π»βπ» retweeted
tip for chatgpt agent slides:
first ask it to do the research only, then ask it to make the slides!
Weβve activated our strongest safeguards for ChatGPT Agent.
Itβs the first model weβve classified as High capability in biology & chemistry under our Preparedness Framework. Hereβs why that mattersβand what weβre doing to keep it safe. π§΅
Replying to @OpenAI
Weβve decided to treat this launch as High Capability in the Biological and Chemical domain under our Preparedness Framework, and activated the associated safeguards. This is a precautionary approach, and we detail our safeguards in the system card.
We outlined our approach on preparing for future AI capabilities in biology through a blog post earlier this month. openai.com/index/preparing-fβ¦
Because keeping models safe is an always-on process, weβre launching a bio bug bounty to identify jailbreaks so that we can address them quickly. openai.com/bio-bug-bounty/
Securing AI bio capabilities extends beyond any one lab. Weβll continue researching, collaborating, and sharing what we learn.
Read the full details in our detailed system card.
openai.com/index/chatgpt-ageβ¦
2
40
5,461








