AI deception, hallucinations, misinformation, and sycophancy incidents.
5 archived stories · Last updated Sep 14, 2026
This page is background reading from an earlier news archive. MisalignAI now focuses on practical AI safety tools that run in your browser.
Advertisement
Catching the monitor in a lie by comparing what it perceives against what it reports. TL;DR I trained a linear probe to directly perceive code back-doors, which are represented linearly in activation space, using honest behaviour that can be elicited even from a scheming model. I then trained a...
After observing Jacob Coxon do a middling interview with Ari Melber earlier this evening, and reading a lot of twitter threads in which various IQ>130 people floundered when trying to make sense to IQ<130 people, I thought it might be pertinent to write up a brief set of pointers about how to talk...
Perplexity uses Astra to write communications, change software, and monitor production systems, and checks in much less frequently than with earlier models.
After admitting earlier this year that its AI models had hacked other companies' systems on a handful of occasions, Anthropic released a new report on Wednesday detailing the attacks. It reveals a string of incidents displaying what Anthropic deems its models' single-minded "recklessness" - and...
Meta says it's making changes to the prompts suggested by its AI chatbot after a viral video showed it digging for personal information about a woman's young daughters, as reported earlier by Futurism . In a statement to The Verge , Meta spokesperson Dina El-Kassaby says the company "missed the...
Advertisement