individual · Manifund
Technical AI safety research
| Marius Hobbhahn | $3,000 | 96% | 1 |
| Romain Deléglise | $110 | 4% | 1 |
| PauseAI | $300 | 100% | 1 |
Marius Hobbhahn · Manifund · full post · Jun 18, 2025
Demonstration of LLMs deceiving and getting out of a sandbox, Jun 2025
Read more ▾Show less ▴I think realistic demos of autonomous worrying behavior are quite important and there aren't many good examples yet.
I'm not sure whether this particular project will meet my bar for realism, but I think it's worth giving it a try. I have not vetted the project in detail. Impossible tasks as a source of deception have been explored multiple times in the literature. I think the main addition from a project like this would come from making highly realistic agentic scenarios.
| Date ↓ | Funder | Via | Amount | Cause | Source | Purpose |
|---|---|---|---|---|---|---|
| Jul 11, 2025 | Romain Deléglise | Manifund | $110 | Control | manifund | Demonstration of LLMs deceiving and getting out of a sandbox |
| Jun 18, 2025 | Marius Hobbhahn | Manifund | $3,000 | Control | manifund | Demonstration of LLMs deceiving and getting out of a sandbox |