AI & machine learning2023 · shared on Hacker News
Emergent World Representations in Neural Networks
Explore Emergent World Representations in Neural Networks, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Comment #47961090 Comment #47960972 Comment #42213256 Comment #42145239 Comment #42004251 Comment #40543674 Comment #40401478 Comment #39878949 Comment #37843103 Comment #36038149 Comment #36018310 Comment #36017579 Comment #35966307 Comment #35561413 Comment #35516644 Comment #35447244 Comment #35435266 Comment #35389345 Comment #35323516 Comment #35213228 Comment #35213219 Comment #35179275 Comment #35178673 Comment #35156277 Comment #35075560 Comment #35005133 Comment #34960684 Comment #34954413 Comment #34799725 Comment #34798852 Comment #34797185 Comment #34480738 Comment #34475576
Ycrescit_eundo ·
Something weird is happening with LLMs and chess
696 points474 comments
Ydmazin ·
OK, I can partly explain the LLM chess weirdness now
524 points460 comments
Ye0m ·
GPT-4
499 points201 comments
Ybenocodes ·
Chain-of-thought can hurt performance on tasks where thinking makes humans worse
371 points250 comments
Yrfw300 ·
Legal models hallucinate in 1 out of 6 (or more) benchmarking queries
215 points255 comments
Yandreyk ·
Mamba Explained
201 points44 comments
Yilreb ·
Where the Goblins Came From
84 points22 comments
Ygardenfelder ·
The LLama Effect: Leak Sparked a Series of Open Source Alternatives to ChatGPT
58 points7 comments
Ydavidbarker ·
Governance of Superintelligence
46 points39 comments
Ytim_sw ·
Eight Things to Know About Large Language Models [pdf]
32 points7 comments
Ymarviel ·
GPT-4 Designed a Programming Language
26 points9 comments
Ymarshblocker ·
Just Calm Down About GPT-4 Already
18 points5 comments
Ywashedup ·
What Is ChatGPT Doing and Why Does It Work?
16 points8 comments
Ycocacola1 ·
What Kind of Mind Does ChatGPT Have?
13 points10 comments
YAlwaysNewb23 ·
Ask HN: How do you explain LLMs to those *still* unfamiliar?
10 points20 comments
Ymakaimc ·
US Senator Uses ChatGPT for Opening Remarks at a Hearing on AI
8 points0 comments
Ygeorgehill ·
Do large language models need sensory grounding for meaning and understanding?
6 points0 comments
Yiraldir ·
A case for the capacity to reason of GPT-4
5 points0 comments
Ydanboarder ·
Do Large Language Models learn world models or just surface statistics?
3 points0 comments
Ymjburgess ·
Emergent World Representations in Neural Networks
2 points1 comments
Ysonabinu ·
To Build Truly Intelligent Machines, Teach Them Cause and Effect
2 points0 comments
Yduck ·
AI-enhanced development makes me more ambitious with my projects
2 points0 comments
Ynmstoker ·
We need a much more sophisticated debate about AI
2 points0 comments
Yexcerionsforte ·
ArxivGPT: Chrome extension that summarizes arxived research papers using ChatGPT
1 points0 comments
Yog_kalu ·
Bing AI can play chess
1 points0 comments