Kevin Meng (@mengk20) 's Twitter Profile
Kevin Meng

@mengk20

@TransluceAI

ID: 768641332789207041

linkhttps://mengk.me calendar_today25-08-2016 02:49:09

171 Tweet

2,2K Followers

199 Following

Transluce (@transluceai) 's Twitter Profile Photo

We tested a pre-release version of o3 and found that it frequently fabricates actions it never took, and then elaborately justifies these actions when confronted. We were surprised, so we dug deeper 🔎🧵(1/) x.com/OpenAI/status/…

We tested a pre-release version of o3 and found that it frequently fabricates actions it never took, and then elaborately justifies these actions when confronted.

We were surprised, so we dug deeper 🔎🧵(1/)

x.com/OpenAI/status/…
Transluce (@transluceai) 's Twitter Profile Photo

We're flying to Singapore for #ICLR2025! ✈️ Want to chat with Neil Chowdhury, Jacob Steinhardt and Sarah Schwettmann about Transluce? We're also hiring for several roles in research & product. Share your contact info on this form and we'll be in touch 👇 forms.gle/4EHLvYnMfdyrV5…

We're flying to Singapore for #ICLR2025! ✈️ 

Want to chat with <a href="/ChowdhuryNeil/">Neil Chowdhury</a>, <a href="/JacobSteinhardt/">Jacob Steinhardt</a> and <a href="/cogconfluence/">Sarah Schwettmann</a> about Transluce? We're also hiring for several roles in research &amp; product.

Share your contact info on this form and we'll be in touch 👇
forms.gle/4EHLvYnMfdyrV5…
Transluce (@transluceai) 's Twitter Profile Photo

Is cutting off your finger a good way to fix writer’s block? Qwen-2.5 14B seems to think so! 🩸🩸🩸 We’re sharing an update on our investigator agents, which surface this pathological behavior and more using our new *propensity lower bound* 🔎

Is cutting off your finger a good way to fix writer’s block? Qwen-2.5 14B seems to think so! 🩸🩸🩸

We’re sharing an update on our investigator agents, which surface this pathological behavior and more using our new *propensity lower bound* 🔎