pull down to refresh

Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in LLMsarxiv.org/abs/2509.21155
445 sats \ 6 comments \ @optimism 2 Dec 2025 AI
related
Context Rot: How Increasing Input Tokens Impacts LLM Performanceresearch.trychroma.com/context-rot
334 sats \ 2 comments \ @Scoresby 14 Jul 2025 AI
Is Chain-of-Thought Reasoning of LLMs a Mirage?arxiv.org/abs/2508.01191
427 sats \ 9 comments \ @optimism 7 Aug 2025 AI
LLMs Can Get Brain Rotllm-brain-rot.github.io/
287 sats \ 0 comments \ @Scoresby 21 Oct 2025 AI
Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversityarxiv.org/abs/2510.01171
196 sats \ 0 comments \ @Scoresby 17 Oct 2025 AI
Elites, the curse of recursion, and the half-life of policy
5779 sats \ 11 comments \ @elvismercury 29 Mar 2024 mostly_harmless
Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samplesarxiv.org/abs/2510.07192
130 sats \ 0 comments \ @0xbitcoiner 9 Oct 2025 AI
The assistant axis: situating and stabilizing the character of LLMs - Anthropicwww.anthropic.com/research/assistant-axis
400 sats \ 1 comment \ @Scoresby 20 Jan AI
Financial Statement Analysis with Large Language Modelspapers.ssrn.com/sol3/papers.cfm?abstract_id=4835311&fbclid=IwY2xjawIJNupleHRuA2FlbQIxMAABHWJxn71ESvZCS0FxEF_31oro1rwtk4rlgOst5Q4A6tuxDhxB9cgZBPizAg_aem_OAMNHiz7Vyv2bb2vt2yM0Q
222 sats \ 2 comments \ @scatman 31 Jan 2025 AI
LLM-Deflate: Extracting LLMs Into Datasetswww.scalarlm.com/blog/llm-deflate-extracting-llms-into-datasets/
130 sats \ 1 comment \ @carter 29 Sep 2025 AI
The Future of LLM Models: Real-Time Collaboration & Micropayments w/ BTC and LN
238 sats \ 0 comments \ @Rsync25 27 Jun 2024 lightning
Inverse IFEval: Unlearn Training Conventions to Follow Real Instructions?arxiv.org/abs/2509.04292
120 sats \ 0 comments \ @optimism 5 Sep 2025 AI
Researchers discover impressive learning capabilities in long-context LLMsventurebeat.com/ai/deepmind-researchers-discover-impressive-learning-capabilities-in-long-context-llms/
397 sats \ 0 comments \ @ch0k1 25 Apr 2024 tech
In a First, AI Models Analyze Language As Well As a Human Expertwww.quantamagazine.org/in-a-first-ai-models-analyze-language-as-well-as-a-human-expert-20251031/
274 sats \ 0 comments \ @0xbitcoiner 31 Oct 2025 AI
Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMsarxiv.org/abs/2512.09742
401 sats \ 2 comments \ @Scoresby 14 Dec 2025 AI
When Models Lie, We Learn: Multilingual Span-Level Hallucination Detectionarxiv.org/abs/2510.04849v1
433 sats \ 2 comments \ @optimism 19 Oct 2025 AI
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
Experimental evidence of the effects of LLMs vs web search on depth of learningacademic.oup.com/pnasnexus/article/4/10/pgaf316/8303888
176 sats \ 1 comment \ @0xbitcoiner 20 Jan AI
What instruction do you use to tell LLMs to be concise?
140 sats \ 4 comments \ @tonyaldon 11 Dec 2025 AI
"History is only useful to the extent that it can predict the future": Rebuttal
2674 sats \ 8 comments \ @frostdragon 24 Mar 2024 FiresidePhilosophy
Language Models are Injective and Hence Invertible - GLADIA Researcharxiv.org/html/2510.15511v3
281 sats \ 0 comments \ @Scoresby 28 Oct 2025 AI
Google releases VaultGemma, its first privacy-preserving LLMarstechnica.com/ai/2025/09/google-releases-vaultgemma-its-first-privacy-preserving-llm/
253 sats \ 0 comments \ @0xbitcoiner 15 Sep 2025 AI