Evidence receipt / uncertainty
Published · transcript-backedAman Sanger: uncertainty
22 Aug 2023 Latent Space Cursor.so: The AI-first Code Editor — with Aman Sanger of Anysphere
“I don't know how far you can take the agent stuff with a four level model, but I think with like a 4.”
Source trail
Everything needed to verify it.
- Speaker
- Aman Sanger
- Attribution
- Verified speaker
- Claim type
- uncertainty
- Recorded
- 22 Aug 2023
- Publisher
- Latent Space
Transcript context
…In what direction though? So I've said my piece on like 4.5 being more inference time. I don't actually know if that's true. That's just my theory. I think the direction that we'll probably see is, I mean, the language models will just get better at doing intense reasoning, right? So they'll be able to tackle harder problems. They'll probably pick up in more nuances and how like software engineering is done. They'll probably have longer context windows. And so I expect, yeah, more agentic type things will end up being more prominent in the future. I don't know how far you can take the agent stuff with a four level model, but I think with like a 4. 5 or a 5, I think agent models will work for almost any kind of coding task. At least almost any kind of reasonably well-scoped coding tasks. Agents are the future. Well, thanks so much for coming in. Thanks Aman. Of course.…
Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.