Tag: #AIRisk
-

Only read this if you have not met your required daily intake of scary news…
Are you sitting down? I hope so, ’cause Anthropic just shared some pretty eye-popping findings. In research they conducted with the UK AI Security Institute and the Alan Turing Institute, they found that slipping in as few as 250 malicious documents into LLM training can create an exploitable backdoor within the model. This results in…
