Stanford CS336 – Language Modeling from Scratch, all lectures on youtube.
@jeande_d
-
GPT-4o Leads Updated Text-to-Image Model Leaderboard
By
–
gpt-4o is the lead on the updated leader-board: https://
artificialanalysis.ai/text-to-image/
arena?tab=Leaderboard
… -
Artificial Analysis: Comparing AI Models Across Intelligence, Speed, Price
By
–
People at Artificial Analysis are doing good job on comparing models across important axes: intelligence, speed, and price. And for all modalities and tasks: language, speech, video, image, code. Benchmarks are not perfect but there is no other way to know a model is better than
-
LLM Reasoning: Scaling Inference Compute and Chain of Thought Optimization
By
–
A great talk on "learning to reason with LLMs" by Naom Brown(
@polynoamial
). – Scale compute at inference time, not just train time. Let the model "think longer" using RL to improve reasoning. More like System 2 thinking, but for LLMs. – Optimize the "chain of thought" with -
LLM-Friendly Code Copying Tool Across Any Codebase
By
–
"Copy to clipboard" but for LLMs, from any codebase. Wow, nice feat!!
-
Training Helpful Harmless Assistant with Reinforcement Learning from Human Feedback
By
–
Training a Helpful and Harmless Assistant with
Reinforcement Learning from Human Feedback slides: https://
docs.google.com/presentation/d
/1hYPWiLETSK5r_Y6sU0mWbOyAz-uevNJh3Xp6BmUnGHM/edit?usp=sharing
… paper: https://
arxiv.org/abs/2204.05862 instructgpt: -
Early RLHF Paper: From Supervised Fine-tuning to Personality in Language Models
By
–
[Slides] This is one of the earliest papers on RLHF (if not the first, alongside InstructGPT). Before RLHF, language models didn’t really have personalities—they mostly relied on supervised fine-tuning or clever prompting to understand humans. Think back to the InstructGPT days.
-
Winning the Turing Test Grants You Naming Rights
By
–
If you win turing, you choose how you want to be called
-
RL – An Introduction to Reinforcement Learning Book
By
–
RL – An Introduction http://
incompleteideas.net/book/the-book-
2nd.html
… -
Reinforcement Learning Pioneers Win Turing Award
By
–
RL won Turing Award to day. Richard Sutton and Andrew Barto. For anyone getting the excitement to dive in RL after Turing Award and reasoning models, here is a copy of all-time RL book written by Turing winners.