Gemma The Unstopping: a Behavioral Experiment

·LessWrong··

Following up on my previous experiment - studying Gemma's behavior on agentic tasks when given the number of steps left across the run - I endeavored to see whether giving Gemma a stop_run tool meaningfully changes it's behavior.My initial assumption was that it would not change the completion rate of these tasks, and that has been correct.What I wanted to test:Whether Gemma would "give up" when nearing the end of the run after hitting a dead end. Interesting.Whether Gemma would "want to stop" -...

Read full article →

Related Articles

Codex starts encrypting sub-agent prompts
embedding-shape · Hacker News · 4h ago
Australian energy retailers must provide three hours of free daytime electricity
i2oc · Hacker News · 11h ago
European "age verification" "app" forcing everyone to use Android or iOS
roundabout-host · Hacker News · 7h ago
LAPD lets contract with surveillance giant Flock expire
forks · Hacker News · 1d ago
Grok CLI uploaded the whole home directory to GCS
denysvitali · Hacker News · 1d ago