AI + ML Claude Code bypasses safety rule if given too many commands A hard-coded limit on deny rules drops automatic enforcement for concatenated commands UPDATED Claude Code will ignore its deny rules, used to block risky actions, if burdened with a sufficiently long chain of subcommands. …
… It could have been a lot worse Claude Code bypasses safety rule if given too many commands GitHub backs down, kills Copilot pull-request ads after backlash AI supply chain attacks don't even require malware…just post poisoned documentation The solution? …
… It is also, in my professional opinion, a direct breach of Article 5 3 of Directive 2002/58/EC the ePrivacy Directive as well as a multitude of computer access and misuse laws usually criminal law , on a scale large enough to matter, in a vendor which has spent considerable effort on being perceive… …
… Governments, especially in the UK and EU, are caught between two modes: pushing on the AI accelerator, or stressing AI safety and governance. Neither approach concerns itself with addressing AI's societal impact. …
… MORE CONTEXT AI recruiting biz Mercor says it was 'one of thousands' hit in LiteLLM supply-chain attack Google's TurboQuant saves memory, but won't save us from DRAM-pricing hell 'Uncle Larry's biggest fan' cut by email in early morning Oracle layoff spree Claude Code bypasses safety rule if given … …