Anthropic's latest Claude model can interact with computers – what could go wrong?
For starters, it could launch a prompt injection attack on itself...
AI + ML24 Oct 2024 | 8
Anthropic
Anthropic's Claude vulnerable to 'emotional manipulation'
AI model safety only goes so far
AI + ML12 Oct 2024 | 42
Another OpenAI founder moves to arch-rival Anthropic
Just two of the gang of eleven remain as safety concerns swirl
AI + ML02 Oct 2024 | 21
AI agent promotes itself to sysadmin, trashes boot sequence
Fun experiment, but yeah, don't pipe an LLM raw into /bin/bash
AI + ML02 Oct 2024 | 94
Anthropic's UK revenue not enough to stop $4B Amazon union, says watchdog
Tie-up between AI toolmaker and Bezos biz doesn't qualify for merger partnership probe
AI + ML30 Sep 2024 | 5
No major AI model is safe, but some do better than others
Feature Anthropic Claude 3.5 shines in Chatterbox Labs safety test
AI + ML17 Sep 2024 | 14
BROADER TOPICS
Canadian artist wants Anthropic AI lawsuit corrected
Interview Tim Boucher objects to the mischaracterization of his work in authors' copyright claim
AI + ML31 Aug 2024 | 17
Writers sue Anthropic for feeding 'stolen' copyrighted work into Claude
Another day, another lawsuit over how AI lands training sets
AI + ML20 Aug 2024 | 35
UK monopoly police launch full blown probe of Amazon's Anthropic tie-up
Poor cloud titans, just trying to give a helping hand to AI startups valued at billions of dollars
AI + ML09 Aug 2024 | 5
Biting the hand that feeds IT
