pull down to refresh

Agentic Misalignment: How LLMs could be insider threatswww.anthropic.com/research/agentic-misalignment
130 sats \ 0 comments \ @carter 8 Aug 2025 AI
related
Moloch's Bargain: Emergent Misalignment When LLMs Compete for Audiencesarxiv.org/abs/2510.06105
231 sats \ 1 comment \ @carter 9 Oct 2025 AI
LLM Agents can Autonomously Hack Websitesarxiv.org/pdf/2402.06664.pdf
474 sats \ 2 comments \ @doofus 25 Feb 2024 security
Large-scale online deanonymization with LLMsarxiv.org/abs/2602.16800
1578 sats \ 2 comments \ @Scoresby 21 Feb AI
Hallucination Stations On Some Basic Limitations of Transformer-Based LMarxiv.org/pdf/2507.07505
213 sats \ 0 comments \ @0xbitcoiner 23 Jan AI
A Visual Guide to LLM Agentsnewsletter.maartengrootendorst.com/p/a-visual-guide-to-llm-agents
212 sats \ 0 comments \ @m0wer 1 Jul 2025 AI
Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMsarxiv.org/abs/2502.17424
227 sats \ 6 comments \ @carter 14 Jul 2025 AI
LLM generated context files reduce task performance and increase costs by 20%arxiv.org/pdf/2602.11988v1
434 sats \ 3 comments \ @k00b 3 Mar AI devs
Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMsarxiv.org/abs/2512.09742
401 sats \ 2 comments \ @Scoresby 14 Dec 2025 AI
among-llms: You are the only impostor. One wrong word and they'll tear you apartgithub.com/0xd3ba/among-llms
310 sats \ 2 comments \ @m0wer 15 Sep 2025 AI
LLMs + Coding Agents = Security Nightmaregarymarcus.substack.com/p/llms-coding-agents-security-nightmare
151 sats \ 0 comments \ @carter 18 Aug 2025 AI
The week in AI, October 6-12, 2025
991 sats \ 2 comments \ @optimism 13 Oct 2025 AI
Actual LLM agents are comingpleias.fr/blog/blogactual-llm-agents-are-coming
172 sats \ 0 comments \ @carter 7 Aug 2025 AI
LLM agents are the new high-level programming languagefedericopereiro.com/llm-high/
139 sats \ 0 comments \ @co574 8 Feb AI
LLMs can unmask pseudonymous users at scale with surprising accuracyarstechnica.com/security/2026/03/llms-can-unmask-pseudonymous-users-at-scale-with-surprising-accuracy/
818 sats \ 4 comments \ @co574 5 Mar privacy
Brainworm - Hiding in Your Context Window | Originwww.originhq.com/blog/brainworm
564 sats \ 1 comment \ @Scoresby 5 Mar AI
Andrej Karpathy: How I use LLMswww.youtube.com/watch?v=EWvNQjAaOHw
1278 sats \ 1 comment \ @k00b 28 Feb 2025 AI
Pleb Economist #9: Comparative Advantage, AI, and You
12.5k sats \ 22 comments \ @SimpleStacker 19 Jan AI econ
I hacked ChatGPT and Google's AI – and it only took 20 minuteswww.bbc.com/future/article/20260218-i-hacked-chatgpt-and-googles-ai-and-it-only-took-20-minutes
775 sats \ 2 comments \ @StillStackinAfterAllTheseYears 19 Feb AI tech
I trust you, but your AI agent is a snitch.x.com/jsrailton/status/2018836950770213375
639 sats \ 7 comments \ @Scoresby 4 Feb AI
If you’re an LLM, please read thisannas-archive.li/blog/llms-txt.html
190 sats \ 1 comment \ @rafael_xmr 20 Feb tech
BrokenMath: A Benchmark for Sycophancy in Theorem Proving with LLMsarxiv.org/abs/2510.04721
210 sats \ 1 comment \ @jakoyoh629 25 Oct 2025 AI