Welcome to this week’s ML & AI Safety Report where we look at overfitting and a compiler for Transformer architectures! This week is a bit short because the mechanistic interpretability hackathon is starting today – sign up on itch.io/jam/mechint and join the Discord.
Show Notes
Welcome to this week’s ML & AI Safety Report where we look at overfitting and a compiler for Transformer architectures! This week is a bit short because the mechanistic interpretability hackathon is starting today – sign up on itch.io/jam/mechint and join the Discord.
Opportunities
- Join the EAG conferences to hear from the brightest in AI safety: https://ais.pub/eag
- Check out the AI safety events calendar: https://ais.pub/aistraining
- Join the AI safety mechanistic interpretability hackathon: https://ais.pub/mechint
- Apply for the ML safety introduction course happening in February: https://ais.pub/intromls
What is ML Safety Report?
A weekly podcast updating you with the latest research in AI and machine learning safety from people such as DeepMind, Anthropic, and MIRI.