Tag: Sim
-
Slashdot: LLM Attacks Take Just 42 Seconds On Average, 20% of Jailbreaks Succeed
Source URL: https://it.slashdot.org/story/24/10/12/213247/llm-attacks-take-just-42-seconds-on-average-20-of-jailbreaks-succeed?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: LLM Attacks Take Just 42 Seconds On Average, 20% of Jailbreaks Succeed Feedly Summary: AI Summary and Description: Yes Summary: The article discusses alarming findings from Pillar Security’s report on attacks against large language models (LLMs), revealing that such attacks are not only alarmingly quick but also frequently result…
-
Simon Willison’s Weblog: Quoting Michael Wooldridge
Source URL: https://simonwillison.net/2024/Oct/12/michael-wooldridge/#atom-everything Source: Simon Willison’s Weblog Title: Quoting Michael Wooldridge Feedly Summary: Carl Hewitt recently remarked that the question what is an agent? is embarrassing for the agent-based computing community in just the same way that the question what is intelligence? is embarrassing for the mainstream AI community. The problem is that although the…
-
The Register: Anthropic’s Claude vulnerable to ’emotional manipulation’
Source URL: https://www.theregister.com/2024/10/12/anthropics_claude_vulnerable_to_emotional/ Source: The Register Title: Anthropic’s Claude vulnerable to ’emotional manipulation’ Feedly Summary: AI model safety only goes so far Anthropic’s Claude 3.5 Sonnet, despite its reputation as one of the better behaved generative AI models, can still be convinced to emit racist hate speech and malware.… AI Summary and Description: Yes Summary:…
-
Hacker News: Bug, $50K+ in bounties: how Zendesk left a backdoor in companies
Source URL: https://gist.github.com/hackermondev/68ec8ed145fcee49d2f5e2b9d2cf2e52 Source: Hacker News Title: Bug, $50K+ in bounties: how Zendesk left a backdoor in companies Feedly Summary: Comments AI Summary and Description: Yes Summary: The text narrates the journey of a young programmer discovering a significant security vulnerability in Zendesk, which could potentially expose sensitive customer support tickets for multiple Fortune 500…
-
The Register: INC ransomware rebrands to Lynx – same code, new name, still up to no good
Source URL: https://www.theregister.com/2024/10/11/inc_ransomware_lynx/ Source: The Register Title: INC ransomware rebrands to Lynx – same code, new name, still up to no good Feedly Summary: Researchers point to evidence that scumbags visited the strategy boutique Researchers at Palo Alto’s Unit 42 believe the INC ransomware crew is no more and recently rebranded itself as Lynx over…
-
Hacker News: Machines of Loving Grace: How AI Could Transform the World for the Better
Source URL: https://darioamodei.com/machines-of-loving-grace Source: Hacker News Title: Machines of Loving Grace: How AI Could Transform the World for the Better Feedly Summary: Comments AI Summary and Description: Yes **Summary:** The text presents an ambitious and optimistic vision of how powerful AI could lead to profound advancements across multiple domains, particularly in health, neuroscience, economic development,…
-
Simon Willison’s Weblog: lm.rs: run inference on Language Models locally on the CPU with Rust
Source URL: https://simonwillison.net/2024/Oct/11/lmrs/ Source: Simon Willison’s Weblog Title: lm.rs: run inference on Language Models locally on the CPU with Rust Feedly Summary: lm.rs: run inference on Language Models locally on the CPU with Rust Impressive new LLM inference implementation in Rust by Samuel Vitorino. I tried it just now on an M2 Mac with 64GB…
-
Hacker News: LLMs don’t do formal reasoning – and that is a HUGE problem
Source URL: https://garymarcus.substack.com/p/llms-dont-do-formal-reasoning-and Source: Hacker News Title: LLMs don’t do formal reasoning – and that is a HUGE problem Feedly Summary: Comments AI Summary and Description: Yes Summary: The text discusses insights from a new article on large language models (LLMs) authored by researchers at Apple, which critically examines the limitations in reasoning capabilities of…