‘Reasoning’ AI is LYING to you! — or maybe it’s just hallucinating again
The chatbot is definitely trying to kill you, maybe. Send us money.
Text version: https://pivot-to-ai.com/2025/04/18/re...
Anthropic: Reasoning models don't always say what they think https://www.anthropic.com/research/re...
paper (PDF) https://assets.anthropic.com/m/71876f...
Introducing Transluce https://transluce.org/introducing-tra...
Investigating truthfulness in a pre-release o3 model https://transluce.org/investigating-o...
Transluce: "These behaviors are surprising." https://x.com/TransluceAI/status/1912...
(Ars Technica article, edited) Researchers concerned to find AI models misrepresenting their “reasoning” processes https://arstechnica.com/ai/2025/04/re...
(Ars Technica article, original) Researchers concerned to find AI models hiding their true “reasoning” processes https://web.archive.org/web/202504102...
Copyscape is nice for quickly comparing web pages https://copyscape.com
Previously:
Anthropic, Apollo astounded to find a chatbot will lie to you if you tell it to lie to you https://pivot-to-ai.com/2024/12/19/an...
How Sam Altman got fired from OpenAI in 2023: not being an AI doom crank (and lying a lot) https://pivot-to-ai.com/2025/04/06/ho...
video: • How Sam Altman got fired from OpenAI in 20...
T-shirt store now open! https://pivot-to-ai.redbubble.com
Enhance the channel: https://www.amazon.co.uk/hz/wishlist/...
Please fund my vital AI safety research! The fate of humanity is at stake!
Patreon: / davidgerard
Ko-Fi: https://ko-fi.com/A1529D5