pull down to refresh

Hail to the Thief: Exploring Attacks and Defenses in Decentralised GRPOarxiv.org/abs/2511.09780
335 sats \ 0 comments \ @optimism 16 Nov 2025 AI
related
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
Distillation, Experimentation, and Integration of AI for Adversarial Usecloud.google.com/blog/topics/threat-intelligence/distillation-experimentation-integration-ai-adversarial-use
335 sats \ 0 comments \ @0xbitcoiner 13 Feb AI
Agentic Reinforced Policy Optimizationarxiv.org/abs/2507.19849
171 sats \ 0 comments \ @optimism 29 Jul 2025 AI
Should you use "you" in your LLM prompts?x.com/BrianRoemmele/status/1998068828295877011
827 sats \ 10 comments \ @Scoresby 9 Dec 2025 AI
The week in AI, September 15-21, 2025
1687 sats \ 5 comments \ @optimism 22 Sep 2025 AI
The week in AI, October 6-12, 2025
991 sats \ 2 comments \ @optimism 13 Oct 2025 AI
To Share Weights from Neural Network Training Is Dangerousbrownstone.org/articles/to-share-weights-from-neural-network-training-is-dangerous/
165 sats \ 7 comments \ @Rothbardian_fanatic 17 Aug 2025 AI
Researchers poison stolen data to make AI results wrongwww.theregister.com/2026/01/06/ai_data_pollution_defense/
266 sats \ 1 comment \ @0xbitcoiner 6 Jan AI
Language Models are Injective and Hence Invertible - GLADIA Researcharxiv.org/html/2510.15511v3
281 sats \ 0 comments \ @Scoresby 28 Oct 2025 AI
Bitcoin Filters Work By Default, and That's a Good Thing!
28.8k sats \ 37 comments \ @BITC0IN 23 Jan 2024 bitcoin freebie
Zero-Click AI Vulnerability Exposed Microsoft 365 Copilot Datathehackernews.com/2025/06/zero-click-ai-vulnerability-exposes.html
1040 sats \ 0 comments \ @k00b 12 Jun 2025 security
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
The week in AI, August 4-10, 2025
2353 sats \ 12 comments \ @optimism 11 Aug 2025 AI
LLMs Can Get Brain Rotllm-brain-rot.github.io/
287 sats \ 0 comments \ @Scoresby 21 Oct 2025 AI
Tongyi-DeepResearch
301 sats \ 0 comments \ @optimism 29 Oct 2025 AI
How zero knowledge proofs can be an attack on Bitcoingroups.google.com/g/bitcoindev/c/sn3-Uc1yPx4/m/Vuc6WnRNAwAJ
15.8k sats \ 5 comments \ @Scoresby 12 Dec 2025 bitcoin
Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMsarxiv.org/abs/2512.09742
401 sats \ 2 comments \ @Scoresby 14 Dec 2025 AI
Open Source and America's AI Action Plan
10.5k sats \ 13 comments \ @optimism 27 Jul 2025 AI
Open Source AI Spam: Further Commentary
1570 sats \ 6 comments \ @halleck 10 May 2024 devs freebie
OpenAI Secretly Funded Benchmarking Dataset Linked To o3 Modelwww.searchenginejournal.com/openai-secretly-funded-frontiermath-benchmarking-dataset/537760/
441 sats \ 0 comments \ @frostdragon 21 Jan 2025 tech
Why language models hallucinate - OpenAIopenai.com/index/why-language-models-hallucinate/
438 sats \ 4 comments \ @Scoresby 6 Sep 2025 AI