Apart Research

Home
Apart Newsletter
Hackathons
Product development
Organization news
🌐 Versión en español
Large language models might always be slightly misaligned
Apart Newsletter #28
 • 
Apart Research
New
Top
Apart Newsletter #27
ML safety research in interpretability and model sharing, game-playing language models, and critiques of AGI risk research
 • 
Apart Research
Identifying semantic neurons, mechanistic circuits & interpretability web apps
Results from the 4th Alignment Jam
 • 
CC
Ethics or Reward?
This week we take a look at LLMs that need therapists, governance of machine learning hardware, and benchmarks for dangerous behaviour. Read to the end…
 • 
CC
Governing AI & Evaluating Danger
We might need to shut it all down, AI governance seems more important than ever and technical research is challenged. Welcome to this week's update…
What a Week! GPT-4 & Japanese Alignment
What a week. There was already a lot to cover Monday when I came in for work and I was going to do a special feature on the Japan Alignment Conference…
Perspectives on AI Safety
This week, we take a look at interpretability used on a Go-playing neural network, glitchy tokens and the opinions and actions of top AI labs and…
Bing Wants to Kill Humanity W07
Welcome to this week’s ML & AI safety update where we look at Bing going bananas, see that certification mechanisms can be exploited and that scaling…
Apart Research
Apart Research
We share updates about the progress of ML safety, run the Apart Lab along with exciting ML safety hackathons.

Apart Research

AboutArchiveSitemap
© 2023 Apart Research
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great writing