fine-tuning

Further training an existing model on your own examples to shift its behaviour. Powerful, and usually the wrong first move — better prompts and better context are far cheaper.

ai 1 video 1 mention

Where it comes up

Training Composer 2

May 14, 2026first said at 4:471 mention

“We're then going to run a long context extension phase to provide more data at 256,000 tokens. And then we end with a final supervised fine-tuning phase, which looks more like the kind of agent data that you might use in practice. On the le…”