AI ResearchMachine Learning5 min reading time

Silico, a tool for researchers to understand their AI models better

IEEE Spectrum
Read full post
Goodfire, an AI lab founded in 2024, launched Silico, a platform offering tools for mechanistic interpretability of AI models. They also introduced a $1 million grant program to support academic and nonprofit research in AI interpretability, aiming to democratize access to advanced analysis tools.

More in AI Research

Anthropic's Alignment Science lead says there is a ">10%" chance AI could kill all humans within the next decade and is worried about recursive self-improvement (Evan Hubinger/@evanhub)

Covered by 9 sources
AI Research4 min read

Suno trained its v6 AI music models with help from Warner and BMG

Covered by 5 sources

Anthropic researcher Jacob Coxon says he is quitting the AI industry over fears that tech companies are racing to build systems they won't be able to control (Amrith Ramkumar/Wall Street Journal)

Covered by 11 sources