Keren Gu πŸŒ±πŸ‘©πŸ»β€πŸ’» (@KerenGu) header
Keren Gu πŸŒ±πŸ‘©πŸ»β€πŸ’» (@KerenGu) profile picture

Safety Research @ OpenAI

San Francisco, CA
Joined November 2012
Photo by Keren Gu πŸŒ±πŸ‘©πŸ»β€πŸ’» (@KerenGu)Photo by Keren Gu πŸŒ±πŸ‘©πŸ»β€πŸ’» (@KerenGu)Photo by Keren Gu πŸŒ±πŸ‘©πŸ»β€πŸ’» (@KerenGu)Photo by Keren Gu πŸŒ±πŸ‘©πŸ»β€πŸ’» (@KerenGu)Photo by Keren Gu πŸŒ±πŸ‘©πŸ»β€πŸ’» (@KerenGu)Photo by Keren Gu πŸŒ±πŸ‘©πŸ»β€πŸ’» (@KerenGu)Photo by Keren Gu πŸŒ±πŸ‘©πŸ»β€πŸ’» (@KerenGu)Photo by Keren Gu πŸŒ±πŸ‘©πŸ»β€πŸ’» (@KerenGu)Photo by Keren Gu πŸŒ±πŸ‘©πŸ»β€πŸ’» (@KerenGu)Photo by Keren Gu πŸŒ±πŸ‘©πŸ»β€πŸ’» (@KerenGu)
Months and months of safety preparations
1 / Today we launched gpt-5, finishing a huge week for OpenAI. We’ve 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/1945908…
We’ve activated our strongest safeguards for ChatGPT Agent. It’s the first model we’ve classified as High capability in biology & chemistry under our Preparedness Framework. Here’s why that matters–and what we’re doing to keep it safe. 🧡
1
3
29
4,856
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/…
2
1
475
We take the risk of bio-misuse very seriously but also deeply care about advancing frontier biology research with our models. Will continue to iterate on both ends!
1
2
311
Feeling grateful this morning to be pushing the frontier. πŸ₯°
1
14
737
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 πŸŒ±πŸ‘©πŸ»β€πŸ’» retweeted
1/N I’m excited to share that our latest @OpenAI experimental reasoning LLM has achieved a longstanding grand challenge in AI: gold medal-level performance on the world’s most prestigious math competitionβ€”the International Math Olympiad (IMO).
390
1,275
796
7,213
5,741,006
Keren Gu πŸŒ±πŸ‘©πŸ»β€πŸ’» retweeted
tip for chatgpt agent slides: first ask it to do the research only, then ask it to make the slides!
39
31
9
480
55,019
We’ve activated our strongest safeguards for ChatGPT Agent. It’s the first model we’ve classified as High capability in biology & chemistry under our Preparedness Framework. Here’s why that matters–and what we’re doing to keep it safe. 🧡
Replying to @OpenAI
We’ve 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-f…
83
121
49
1,132
551,341
Because keeping models safe is an always-on process, we’re launching a bio bug bounty to identify jailbreaks so that we can address them quickly. openai.com/bio-bug-bounty/
6
5
2
63
8,928
Securing AI bio capabilities extends beyond any one lab. We’ll continue researching, collaborating, and sharing what we learn. Read the full details in our detailed system card. openai.com/index/chatgpt-age…
2
40
5,461
Keren Gu πŸŒ±πŸ‘©πŸ»β€πŸ’» retweeted
1/ Our models are becoming more capable in biology and we expect upcoming models to reach β€˜High’ capability levels as defined by our Preparedness Framework. 🧡
168
168
16
1,283
548,859