pull down to refresh

Brainworm - Hiding in Your Context Window | Originwww.originhq.com/blog/brainworm
544 sats \ 1 comment \ @Scoresby 5h AI
related
LLM Agents can Autonomously Hack Websitesarxiv.org/pdf/2402.06664.pdf
474 sats \ 2 comments \ @doofus 25 Feb 2024 security
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
Hacker Plants False Memories In ChatGPT To Steal User Data In Perpetuity
89 sats \ 0 comments \ @0xbitcoiner 24 Sep 2024 ideasfromtheedge
LLM agents are the new high-level programming languagefedericopereiro.com/llm-high/
139 sats \ 0 comments \ @co574 8 Feb AI
Hacker plants false memories in ChatGPT to steal user data in perpetuityarstechnica.com/security/2024/09/false-memories-planted-in-chatgpt-give-hacker-persistent-exfiltration-channel
341 sats \ 0 comments \ @ch0k1 25 Sep 2024 news
LLMs + Coding Agents = Security Nightmaregarymarcus.substack.com/p/llms-coding-agents-security-nightmare
151 sats \ 0 comments \ @carter 18 Aug 2025 AI
ChatGPT Agent Violates Policy and Solves Image CAPTCHAssplx.ai/blog/chatgpt-agent-solves-captcha
258 sats \ 2 comments \ @0xbitcoiner 21 Sep 2025 AI
Claude_Sonnet-4.5 System Prompt - elder-pliniusgithub.com/elder-plinius/CL4R1T4S/blob/main/ANTHROPIC/Claude_Sonnet-4.5_Sep-29-2025.txt
472 sats \ 0 comments \ @Scoresby 29 Sep 2025 AI
Hallucination Stations On Some Basic Limitations of Transformer-Based LMarxiv.org/pdf/2507.07505
213 sats \ 0 comments \ @0xbitcoiner 23 Jan AI
Nanochat Lets You Build Your Own Hackable LLMhackaday.com/2025/10/20/nanochat-lets-you-build-your-own-hackable-llm/
218 sats \ 1 comment \ @0xbitcoiner 20 Oct 2025 AI
AI trained for treachery becomes the perfect agent - The Registerwww.theregister.com/2025/09/29/when_ai_is_trained_for/
257 sats \ 1 comment \ @Scoresby 30 Sep 2025 AI
Disrupting first reported AI-orchestrated cyber espionage campaign - Anthropicwww.anthropic.com/news/disrupting-AI-espionage
457 sats \ 1 comment \ @Scoresby 13 Nov 2025 AI
Salesforce Agentforce tricked into leaking sales leadswww.theregister.com/2025/09/26/salesforce_agentforce_forceleak_attack/
292 sats \ 0 comments \ @0xbitcoiner 26 Sep 2025 AI
Large-scale online deanonymization with LLMsarxiv.org/abs/2602.16800
1578 sats \ 2 comments \ @Scoresby 21 Feb AI
Microsoft and OpenAI say hackers are using ChatGPT to improve cyberattackswww.theverge.com/2024/2/14/24072706/microsoft-openai-cyberattack-tools-ai-chatgpt
265 sats \ 0 comments \ @ch0k1 14 Feb 2024 security
Agentic Misalignment: How LLMs could be insider threatswww.anthropic.com/research/agentic-misalignment
130 sats \ 0 comments \ @carter 8 Aug 2025 AI
Scamlexity: When Agentic AI Browsers Get Scammedguard.io/labs/scamlexity-we-put-agentic-ai-browsers-to-the-test-they-clicked-they-paid-they-failed
733 sats \ 6 comments \ @optimism 23 Aug 2025 AI
Awesome AI Agents: A collection of autonomous agents 🤖️ powered by LLM.github.com/Jenqyang/Awesome-AI-Agents
120 sats \ 0 comments \ @Rsync25 25 Aug 2024 openagents
ChatGPT Agent casually clicks through “I am not a robot” verification testarstechnica.com/information-technology/2025/07/openais-chatgpt-agent-casually-clicks-through-i-am-not-a-robot-verification-test/
281 sats \ 2 comments \ @south_korea_ln 31 Jul 2025 AI
Modder injects AI dialogue into 2002’s Animal Crossing using memory hackarstechnica.com/gaming/2025/09/animal-crossing-mod-uses-ai-to-orchestrate-anti-tom-nook-villager-revolt/
2160 sats \ 3 comments \ @jakoyoh629 13 Sep 2025 AI
The Age of the All-Access AI Agent Is Herewww.wired.com/story/expired-tired-wired-all-access-ai-agents/
551 sats \ 2 comments \ @0xbitcoiner 24 Dec 2025 AI