Hacker Newsnew | past | comments | ask | show | jobs | submit | fromlogin
Intentionally Designing the Future of AI (goodfire.ai)
1 point by jal278 14 days ago | past
Using Interpretability to Identify a Novel Class of Alzheimer's Biomarkers (goodfire.ai)
2 points by keeda 16 days ago | past | 1 comment
Replicating Circuit Tracing for a Simple Known Mechanism (goodfire.ai)
2 points by tzury 8 months ago | past
Under the Hood of a Reasoning Model (goodfire.ai)
1 point by vinhnx 10 months ago | past
Show HN: Write Stories by Steering a LLM (goodfire.ai)
2 points by trq_ 11 months ago | past
Show HN: Llama 3.3 70B Sparse Autoencoders with API access (goodfire.ai)
201 points by trq_ on Dec 23, 2024 | past | 51 comments
What if you could look inside your AI? Understanding and steering Llama 3 (goodfire.ai)
21 points by danielbalsam on Sept 27, 2024 | past
Look Inside Your AI (goodfire.ai)
1 point by tMcGrath on Sept 25, 2024 | past

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: