Truth is not a direction: a Tarski attack on LLM probes (abeljansma.nl) | HN Screenshots

YHacker Newsscreenshots

Screenshot of abeljansma.nl: Truth is not a direction: a Tarski attack on LLM probes

First screen, captured 3 months ago.

Looks similar

Screenshot of laion.ai: LeoLM: German-Language LLM Research

LeoLM: German-Language LLM Research (laion.ai)

92 points by doubtfuluser 3 years ago | 82 comments

Screenshot of evanhahn.com: Local LLMs versus offline Wikipedia

Local LLMs versus offline Wikipedia (evanhahn.com)

288 points by EvanHahn 1 year ago | 171 comments

Screenshot of adamkarvonen.github.io: An Intuitive Explanation of Sparse Autoencoders for LLM Interpretability

An Intuitive Explanation of Sparse Autoencoders for LLM Interpretability (adamkarvonen.github.io)

77 points by sebg 1 year ago | 1 comments

Screenshot of fratepietro.com: Building a Rust Inference Engine That Matches Llama.cpp

Building a Rust Inference Engine That Matches Llama.cpp (fratepietro.com)

20 points by antonellof 2 months ago | 22 comments

Screenshot of benjamin-bai.com: LeMario: Training a JEPA World Model on Super Mario Bros

LeMario: Training a JEPA World Model on Super Mario Bros (benjamin-bai.com)

119 points by kevinjosethomas 3 months ago | 13 comments

Screenshot of dedoimedo.com: Long live Xorg, I mean Xlibre

Long live Xorg, I mean Xlibre (dedoimedo.com)

50 points by dxs 1 year ago | 42 comments