logoalt Hacker News

gruezyesterday at 5:05 PM5 repliesview on HN

Cognition, the same company that a few years ago demoed a coding bot purporting to be able to autonomously complete upwork tasks, but upon closer inspection was going off the rails and not even completing what was asked?

https://www.youtube.com/watch?v=tNmgmwEtoWE

As others have mentioned this is post trained from Kimi k3, which is already quite capable, so it can't be that bad, but any claimed improvements in performance should be taken with a grain of salt.


Replies

fishtoasteryesterday at 6:07 PM

A friend recently pushed me to try out their coding platform, Devin, after I decided to move away from Cursor. I had the same reaction: "What, the con artists from like 2024?" But after some cajoling, I gave it a shot and was pleasantly surprised. I guess they learned their lessons, grew up, and are doing good work now, maybe?

show 7 replies
deetyesterday at 11:30 PM

As others have mentioned, it's really matured a lot and at this point is one of the best cloud-hosted, team-managed coding agents, when factoring overall UX, testing and QA lifecycle via its sandboxes, and its ability to be controlled with an API. We use it quite heavily.

It's coming from a different starting place than Claude Code or Codex are as individually controlled single-developer tools. Devin has been more persistent in pursuing the direction of something that operates more autonomously at the team level, as a peer. And while it might be slightly behind in raw harness ability (maybe?) it's probably ahead on the team-focus.

show 1 reply
sterlindyesterday at 7:47 PM

I'm surprised they can post-train a closed model off of K3. Is that the norm for open-weight licenses?

show 1 reply
notfromhereyesterday at 5:11 PM

Well the models did get better but yeah their early product was godawful

esafakyesterday at 6:32 PM

Previous versions were based on Kimi too. I'd consider if it I could access the model outside Devin. No lock in for me, thank you very much.