OpenAI o-series, every mention
6 scenes · ← back to OpenAI o-series
tap a year for its mentions
every year anyone Spooks (Swyx) 3Shawn Wang 2Pratik Bhavsar 1Nikunj Handa 1
Verbatim, from the transcripts: the passages where OpenAI o-series comes up
⚡️Ranking Agentic LLMs — Pratik Bhavsar, Galileo
- ▶ 9:08 Pratik Bhavsar Inherent characteristic of specifically O series model, uh, we did not find them well to be performing on this kind of data set.
Scaling Test Time Compute to Multi-Agent Civilizations — Noam Brown, OpenAI
- ▶ 4:51 Spooks (Swyx) I guess the last diplomacy-related questions that we might have is, have you updated or tested, like, O-series models on diplomacy?
- ▶ 5:25 Spooks (Swyx) Well, we're going to go a little bit into O series now. 2 times in the scene
⚡️Multi-Turn RL for Multi-Hour Agents — with Will Brown, Prime Intellect
- ▶ 3:03 Shawn Wang Do we have any, this is like already veering off from Claude directly into speculation, but do we have any idea, um, if there are any material differences between how Claude extended thinking works versus like the old series models?
The new OpenAI Agents Platform: CUA, Web Search, Responses API, Agents SDK!!
- ▶ 3:44 Shawn Wang So it's kind of like how GPT and the old series models are also unifying.
- ▶ 9:28 Nikunj Handa They've done, like, O-series model distillation to, like, make these four or fine tunes really good.