wujerry2000
- Karma
- 0
- Created
- ()
- Submissions
- 0
- Sims with verifiable rewards for web agent benchmarking and RL (halluminate.ai)
-
Hi everyone, Jerry and Wyatt here from Halluminate (https://halluminate.ai/). We help AI labs train computer use agents with high quality data and RL environments. Training AI agents to use computers, browsers, and…
- Most liked comment is AI (drive.google.com)
- FrontierMath was funded by OpenAI (lesswrong.com)
-
Companies with LLM-based products (specifically Retrieval-Augmented Generation)deployed in production - how are you monitoring outputs for hallucinations? What's your process?