back
OpenAI prompts AI models to ‘confess’ when they cheat
Get SIGNAL/NOISE in your inbox daily
The idea is to make LLMs turn themselves in when they don’t follow instructions, potentially reducing errors in enterprise deployments.
Recent Stories
Jan 13, 2026
CEOs of NVIDIA and Lilly Share ‘Blueprint for What Is Possible’ in AI and Drug Discovery
Dave Ricks, chair and CEO of Lilly, sat down with NVIDIA founder and CEO Jensen Huang at the J.P. Morgan Healthcare Conference to discuss a new, first-of-its-kind AI co-innovation lab — and the future of biopharma.
Jan 13, 2026Microsoft vows to cover full power costs for energy-hungry AI data centers
Company responds to community concerns over electricity bills and water use.
Jan 13, 2026The AI Ad Network: What a next‑gen DSP looks like when the interface is a conversation
The last decade of ad tech was built for pages, feeds, and apps. You scroll. You click. You land. The ad is some rectangle, and the business model is: show enough of them to subsidize whatever the user is doing. And whatever the user is doing happens to be an awful lot. Advertising is the…