neversupervised
- Karma
- 0
- Created
- ()
- Submissions
- 0
-
I’m just as worried as the next guy about the negative implications of AI. While I’m a long-term optimist, I have high confidence that we’re about to go through a rough period, with unpleasant labor markets, class…
-
I want to share a new dataset of 331 reward-hackable environments. These are real environments used in Terminal Bench and adjacent benchmarks. I first got interested in this because, as a reviewer of Terminal Bench, I…
- How to Make a Good Terminal Bench Task (twitter.com)