GPT-4 can't reason (preprints.org)

Screenshot of preprints.org: GPT-4 can't reason

First screen, captured 3 years ago.

Looks similar

Screenshot of gwern.net: GPT-3 Creative Fiction (2020)

GPT-3 Creative Fiction (2020)(gwern.net)

77 points by ijidak 3 years ago | 31 comments

Screenshot of arxiv.org: LLMs cannot find reasoning errors, but can correct them

LLMs cannot find reasoning errors, but can correct them (arxiv.org)

222 points by koie 2 years ago | 112 comments

Screenshot of arxiv.org: Probabilistic Artificial Intelligence

Probabilistic Artificial Intelligence (arxiv.org)

335 points by pavanto 1 year ago | 83 comments

arXiv listing for "Probabilistic Artificial Intelligence" by Andreas Krause and Jonas Hübotter, a manuscript on probabilistic ML, uncertainty, and decision-making.

probabilistic-machine-learning uncertainty-quantification reinforcement-learning bayesian-inference

Screenshot of arxiv.org: Comparing humans, GPT-4, and GPT-4V on abstraction and reasoning tasks

Comparing humans, GPT-4, and GPT-4V on abstraction and reasoning tasks (arxiv.org)

202 points by mpweiher 2 years ago | 156 comments

Screenshot of arxiv.org: Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4

Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4 (arxiv.org)

28 points by saurabh20n 3 years ago | 39 comments

Screenshot of kenschutte.com: Gzip beats BERT? Part 2: dataset issues, improved speed, and results

Gzip beats BERT? Part 2: dataset issues, improved speed, and results (kenschutte.com)

225 points by JoeyBananas 3 years ago | 46 comments

Looks similar

GPT-3 Creative Fiction (2020)(gwern.net)

LLMs cannot find reasoning errors, but can correct them(arxiv.org)

Probabilistic Artificial Intelligence(arxiv.org)

Comparing humans, GPT-4, and GPT-4V on abstraction and reasoning tasks(arxiv.org)

Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4(arxiv.org)

Gzip beats BERT? Part 2: dataset issues, improved speed, and results(kenschutte.com)

LLMs cannot find reasoning errors, but can correct them (arxiv.org)

Probabilistic Artificial Intelligence (arxiv.org)

Comparing humans, GPT-4, and GPT-4V on abstraction and reasoning tasks (arxiv.org)

Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4 (arxiv.org)

Gzip beats BERT? Part 2: dataset issues, improved speed, and results (kenschutte.com)