AI-Implanted False Memories (media.mit.edu)

Screenshot of media.mit.edu: AI-Implanted False Memories

First screen, captured 2 years ago.

Looks similar

Screenshot of gregorygundersen.com: A History of Large Language Models

A History of Large Language Models (gregorygundersen.com)

244 points by alexmolas 1 year ago | 17 comments

Screenshot of news.mit.edu: LLMs use a surprisingly simple mechanism to retrieve some stored knowledge

LLMs use a surprisingly simple mechanism to retrieve some stored knowledge (news.mit.edu)

336 points by CharlesW 2 years ago | 121 comments

MIT News article on research showing LLMs often retrieve stored facts via simple linear functions, and a technique to probe what a model knows about subjects.

large-language-models interpretability knowledge-retrieval mit

Screenshot of assemblyai.com: The Full Story of Large Language Models and RLHF

The Full Story of Large Language Models and RLHF (assemblyai.com)

84 points by pk3 3 years ago | 16 comments

Screenshot of hao-ai-lab.github.io: Consistency LLM: converting LLMs to parallel decoders accelerates inference 3.5x

Consistency LLM: converting LLMs to parallel decoders accelerates inference 3.5x (hao-ai-lab.github.io)

447 points by zhisbug 2 years ago | 94 comments

Hao AI Lab blog post introducing Consistency LLMs, a method that fine-tunes LLMs into parallel Jacobi decoders to speed up inference about 3.5x.

consistency-llm llm-inference parallel-decoding jacobi-decoding

Screenshot of openai.com: Due to concerns about malicious applications, GPT2 will not be released (2019)

Due to concerns about malicious applications, GPT2 will not be released (2019)(openai.com)

47 points by Jimmc414 1 month ago | 19 comments

Screenshot of xyzlabs.substack.com: Large Language Models Show Concerning Tendency to Flatter Users

Large Language Models Show Concerning Tendency to Flatter Users (xyzlabs.substack.com)

41 points by terryjiao 1 year ago | 34 comments

Looks similar

A History of Large Language Models(gregorygundersen.com)

LLMs use a surprisingly simple mechanism to retrieve some stored knowledge(news.mit.edu)

The Full Story of Large Language Models and RLHF(assemblyai.com)

Consistency LLM: converting LLMs to parallel decoders accelerates inference 3.5x(hao-ai-lab.github.io)