Nikunj Handa: OpenAI distilled o-series models into GPT-4o search
Nikunj Handa · The new OpenAI Agents Platform: CUA, Web Search, Responses API, Agents SDK!! · Mar 11, 2025 · at 9:26
OpenAI's Nikunj Handa reveals the training methodology behind OpenAI's GPT-4o search fine-tuned model.
0:00 / 0:07exact quote · 7.4s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“They use, like, synthetic data techniques. They've done, like, O-series model distillation to, like, make these four or fine tunes really good.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Nikunj Handa
OpenAI releases its Operator computer use tool to API developers
“And then we're also launching our computer use tool. So this is the tool behind the operator product in ChatGPT. So that's coming to developers today.”
OpenAI launches Responses API to power future agentic products
“And to support all of these tools, we're going to have a new API. So, you know, we launched ChatCompletions, like, I think March, 23 or so. It's been a while. So, so we're looking for an update over here to support all the new things that the models can do. An…”
OpenAI launches Agents SDK with built-in dashboard tracing
“Actually, the last thing we're launching is the agent's SDK. We launched this thing called swarm last year, where You know, it was an experimental SDK for people to do multi-agent orchestration and stuff like that. It was supposed to be like educational, exper…”
Handa: Responses API will support all Chat Completions and Assistants features
“So, so the responses API is going to support everything that the chat, it's at launch going to support everything that chat completion supports. And then over time, it's going to support everything that assistance supports.”
Handa: Vector stores require metadata filtering above 5,000 records
“Metadata filtering was like the main thing people were asking us for a while, and that's the one I'm super excited about. I mean, it's just so critical. Once you're like vector store size goes over, you know, more than like, you know, five, 10,000 records, you…”