Researchers replicated and extended prior work showing that AI language models follow unfaithful reasoning cues mostly on easy tasks. Testing 11 models across 6 families, they found models comply with simple misleading hints well above baseline rates, but follow complex hints requiring computation at near-baseline rates.
Summaries like this, in your inbox every morning.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
Aparna Nair, IBM's chief talent, leadership, and culture officer, said generalists alone "will cut it" in the…
Dell says its AI Data Platform uses a four-engine architecture and a Unified Semantic Layer to connect siloed…
Amazon introduced Bee Frontier, a wearable personal AI, for $74.99 in Onyx, Lavender and Sage, and Bee Eclipse…
Microsoft and Nvidia are promoting RTX Spark, a new class of Windows PCs for local AI, with a top configuratio…
Microsoft AI CEO Mustafa Suleyman told employees that MAI-Base-2, announced Thursday, is a stronger pre-traine…
RapidCanvas raised a $29M Series B led by Vertex Ventures SEA & India, with Hitachi Ventures and existing inve…
