Latest / The AI, Privacy, and Security Weekly Update
Subliminal Learning with the AI, Security, and Privacy Weekly Update for the Week ending April 7th, 2026
Episode 286
And have we got an update for you. Focus on this:
Researchers have discovered that AI models can be secretly shaped by their training data even after every suspicious signal has been scrubbed out, which raises an uncomfortable question: do we actually know what we've built?
It turns out the most comprehensive profile LinkedIn has on you isn't the one you wrote yourself.
Samsung would like you to know that the $2,000 refrigerator you just bought comes with one small surprise: a billboard.
AI-assisted coding has pushed GitHub to a billion commits a year, which sounds like…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.