Everything you care about in one place
Follow feeds: blogs, news, RSS and more. An effortless way to read and digest content of your choice.
Get Feederlesswrong.com
Less Wrong
Get the latest updates from Less Wrong directly as they happen.
Follow now 82 followers
Latest posts
Last updated 9 minutes ago
On today's panel with Bernie Sanders
22 minutes ago
It’s sort of easy to forget how close Bernie Sanders was to...
Scaffolding vs Reinforcement Finetuning for AI Forecasting
about 3 hours ago
Epistemic status: low-medium confidence in results, this is work I did last...
What Do You Mean by a Two-Year AGI Timeline?
about 3 hours ago
Until recently, I was a bit confused about what people meant when...
No Strong Orthogonality From Selection Pressure
about 3 hours ago
TL;DRIf everything goes according to plan, by the end of this post...
Computation in Superposition: Two Handcrafted Models
about 4 hours ago
Many interpretability researchers (ourselves included) believe that neural networks store knowledge in...
Research Sabotage in ML Codebases
about 5 hours ago
One of the main hopes for AI safety is using AIs to...
The fall of the theorem economy (David Bessis)
about 10 hours ago
I found this post from mathematician David Bessis very interesting. It explains...
Probe-Based Data Attribution: Surfacing and Mitigating Undesirable Behaviors in LLM Post-Training
about 10 hours ago
IntroductionResearch by Frank Xiao (SPAR mentee) and Santiago Aranguri (Goodfire).Post-training can introduce...
Probe-Based Data Attribution: Surfacing and Mitigating Undesirable Behaviors in LLM Post-Training
about 10 hours ago
IntroductionResearch by Frank Xiao (SPAR mentee) and Santiago Aranguri (Goodfire).Post-training can introduce...
Book review: The Infinity Machine
about 10 hours ago
Book review: The Infinity Machine: Demis Hassabis, DeepMind, and the Quest for...
Poisoning Fine-tuning Datasets of Constitutional Classifiers
about 12 hours ago
The primary contributors to this work are Chase Bowers, Faizan Ali, John...