pull down to refresh

LLMs use a surprisingly simple mechanism to retrieve some stored knowledgenews.mit.edu/2024/large-language-models-use-surprisingly-simple-mechanism-retrieve-stored-knowledge-0325
228 sats \ 1 comment \ @hn 31 Mar 2024 tech
related
What are your most surprising personal uses of LLMs?
1533 sats \ 39 comments \ @k00b 3 May AI AskSN
How do you use LLMs?
901 sats \ 8 comments \ @gmd 21 Mar 2025 AI
If LLMs Have Human-Like Attributes, Then So Does Age of Empires IIarxiv.org/abs/2605.31514
608 sats \ 1 comment \ @Scoresby 6 Jun lol AI
Andrej Karpathy: How I use LLMswww.youtube.com/watch?v=EWvNQjAaOHw
1278 sats \ 1 comment \ @k00b 28 Feb 2025 AI
Here’s What’s Really Going On Inside An LLM’s Neural Network
216 sats \ 0 comments \ @0xbitcoiner 22 May 2024 BooksAndArticles
Project Alexandria: Freeing Scientific Knowledge from Copyright Burdens via LLMsarxiv.org/abs/2502.19413
592 sats \ 14 comments \ @nkmg1c_ventures 1 Nov 2025 AI
A Bitcoin-native LLM: dataset, architecture and open questionsdelvingbitcoin.org/t/a-bitcoin-native-llm-dataset-architecture-and-open-questions/2550
259 sats \ 0 comments \ @0xbitcoiner 2 Jun AI bitcoin
Open Source AI Spam: Further Commentary
1570 sats \ 6 comments \ @halleck 10 May 2024 devs freebie
Two LLM UI patterns that aren’t chatpoyo.co/note/20260525T094605/
438 sats \ 2 comments \ @deSign_r 3 Jun Design
More Artificial than Intelligent, it is only getting worse - Mathjis Lagerbergmlagerberg.com/much-a-little-i-and-it-is-not-getting-better/
247 sats \ 4 comments \ @Scoresby 15 Jul 2025 AI
LLM coding is the wrong layer of abstractionbbuyukliev.blogspot.com/2026/04/llm-coding-is-wrong-layer-of-abstraction.html
687 sats \ 6 comments \ @co574 3 Apr devs
Is Chain-of-Thought Reasoning of LLMs a Mirage?arxiv.org/abs/2508.01191
427 sats \ 9 comments \ @optimism 7 Aug 2025 AI
Elites, the curse of recursion, and the half-life of policy
5779 sats \ 11 comments \ @elvismercury 29 Mar 2024 mostly_harmless
Hallucination Stations On Some Basic Limitations of Transformer-Based LMarxiv.org/pdf/2507.07505
213 sats \ 0 comments \ @0xbitcoiner 23 Jan AI
Here’s how I use LLMs to help me write code -- Simon Willisonsimonwillison.net/2025/Mar/11/using-llms-for-code/
570 sats \ 0 comments \ @StillStackinAfterAllTheseYears 12 Mar 2025 tech
"History is only useful to the extent that it can predict the future": Rebuttal
2674 sats \ 8 comments \ @frostdragon 24 Mar 2024 FiresidePhilosophy
Things we learned about LLMs in 2024simonwillison.net/2024/Dec/31/llms-in-2024/
470 sats \ 0 comments \ @Rsync25 31 Dec 2024 tech
Bringing LLMs to the edgewww.raspberrypi.com/news/bringing-llms-to-the-edge/
285 sats \ 2 comments \ @0xbitcoiner 26 May AI DIY
LLMs generate slop because they avoid surprises by design - Dan Fabulichdanfabulich.medium.com/llms-tell-bad-jokes-because-they-avoid-surprises-7f111aac4f96
373 sats \ 2 comments \ @Scoresby 19 Aug 2025 AI
LLMs and Programming in the first days of 2024antirez.com/news/140
2759 sats \ 20 comments \ @hn 2 Jan 2024 tech
LLMs don’t do formal reasoning - and that is a HUGE problemgarymarcus.substack.com/p/llms-dont-do-formal-reasoning-and
300 sats \ 0 comments \ @Rsync25 11 Oct 2024 tech