Extending swe-2 reward function for Pareto frontier steering | Hacker News - But Better

Extending swe-2 reward function for Pareto frontier steering anishlk.com

Experiments extending the reward function in Cognition’s SWE-2 model release.

1 points•anishlk•about 9 hours ago•0 comments•

#reward #function #extending #swe #reward function #steering #pareto #frontier

0 comments

No comments yet.

Related stories

Show HN: swe-mux – A terminal multiplexer for coding agents optimized for mobilegithub.com
Hacker News · 1 points · 5 days ago
Choosing a Model on the Pareto Frontier with Jevphilippdubach.com
Hacker News · 1 points · 11 days ago
Devin Fusion: the first multi-model coding agent on the Pareto frontiertwitter.com
Hacker News · 1 points · 11 days ago
Step 5 Preview: Advancing the Pareto Frontierstepfun.com
Hacker News · 121 points · 13 days ago
Show HN: Reliopt – Pareto-frontier, contract-gated optimization for LLM programsgithub.com
Hacker News · 1 points · 7 days ago
MiMo-v2.6-Flash: on intelligence/price Pareto frontierartificialanalysis.ai
Hacker News · 2 points · 5 days ago