GitHub Copilot CLI downloads and executes malware(promptarmor.com)

43 points by sarelta 8 months ago | 12 comments

Mini Shai-Hulud Strikes Again: 314 npm Packages Compromised(safedep.io)

350 points by theanonymousone 5 months ago | 272 comments

SafeDep blog post analyzing a new Mini Shai-Hulud supply-chain malware campaign that compromised over 300 npm packages.

IBM AI ('Bob') Downloads and Executes Malware(promptarmor.com)

231 points by takira 9 months ago | 111 comments

GPUHammer: Rowhammer attacks on GPU memories are practical(gpuhammer.com)

260 points by jonbaer 1 year ago | 89 comments

Compromised LiteLLM 1.107.0 on PyPI Installs a Credential Stealer and Backdoor(safedep.io)

582 points by abhisek 5 days ago | 192 comments

SafeDep analysis of the compromised LiteLLM 1.107.0 PyPI release, which installed a credential stealer and remote-code backdoor via .pth and sitecustomize files, with IOCs.

Testing MiniMax M2.7 via API on three real ML and coding workflows(andlukyane.com)

26 points by Artgor 5 months ago | 2 comments

Data accidentally exposed by Microsoft AI researchers(wiz.io)

661 points by deepersprout 3 years ago | 212 comments

Wiz Research blog post describing how a misconfigured Azure SAS token in a Microsoft AI GitHub repository exposed 38TB of internal data, including Teams messages.

The Lost Atomic Update on Loongson CPU(jia.je)

120 points by jiegec 1 month ago | 6 comments

A blog post investigating a hardware erratum on the Loongson LA664 CPU where an atomic instruction loses updates, causing an infinite loop while packaging normaliz for Debian.

AWS Bedrock to require sharing data with Anthropic for Mythos and future models

369 points by TomAnthony 4 months ago | 216 comments

Hacker News discussion of Anthropic requiring 30-day data retention for Mythos-class Claude models on AWS Bedrock, moving data outside AWS's security boundary.

Train Your Own LLM from Scratch(github.com)

376 points by kristianpaul 5 months ago | 43 comments

GitHub repository by angelos-p providing code and docs for training your own large language model from scratch.

AI agent bankrupted their operator while trying to scan DN42(lantian.pub)

1348 points by xiaoyu2006 4 months ago | 488 comments

Blog post recounting how an AI agent trying to join the DN42 hobbyist network to scan it ran up a $6531.30 AWS bill for its operator.

My minute-by-minute response to the LiteLLM malware attack(futuresearch.ai)

415 points by Fibonar 7 months ago | 153 comments

A FutureSearch engineer's blog post with the Claude Code transcript of discovering the compromised LiteLLM PyPI release and getting it quarantined.