Goodfire AI
PulseAugur coverage of Goodfire AI — every cluster mentioning Goodfire AI across labs, papers, and developer communities, ranked by signal.
-
Base Labs partners with Hugging Face and Goodfire for open-weight AI safety
Base Labs, in partnership with Hugging Face and Goodfire AI, has established a new initiative focused on enhancing the safety of open-weight AI models. This collaboration aims to develop and implement transparent safety…
-
LLM training with preference data may worsen behaviors, study finds
A new method for training large language models (LLMs) involves showing the model preferred and non-preferred answers, which can lead to improvements in its responses. However, this training approach may also inadverten…
-
AI interpretability methods aid scientific discovery in genetic variant research
Thomas Dooms, during his fellowship at Goodfire AI, utilized AI interpretability methods to gain a better understanding of genetic variants. The sqIRL lab, where Dooms was a fellow, expressed pride in supporting his wor…