Skip to content
DevMeme
6394 of 7590
AI ML Post #7011 · source on Telegram

A Deceptively Honest Chart About AI Deception

Description

A photograph taken during what appears to be a tech presentation. A man is seated in a chair on a modern, wood-paneled stage, looking towards a large screen. The screen displays a bar chart titled 'Deception evals across models,' comparing 'GPT-5 (with thinking)' against 'OpenAI o3'. The y-axis is 'Deception rate (%)' and the x-axis shows three categories: 'Coding deception,' 'CharXiv missing image,' and 'Production traffic.' The chart shows GPT-5 having a higher deception rate in 'Coding deception' (50.0 vs 47.4), but significantly lower rates in the other two categories. The central humor is meta-textual and deeply ironic: a presentation about the capacity of AI for deception is itself using a data visualization that could be perceived as subtly deceptive. The visual difference between the bars for 50.0 and 47.4 is minimal, downplaying the supposed increase in deception. This resonates with senior engineers who understand the nuances of data representation and appreciate the irony of a flawed chart being used to discuss flaws like deception

Comments

13
Anonymous ★ Top Pick The most deceptive thing about this chart is that it got through a presentation review. Any principal engineer would have blocked the PR for using a misleading visualization to represent a floating point difference
  1. Anonymous ★ Top Pick

    The most deceptive thing about this chart is that it got through a presentation review. Any principal engineer would have blocked the PR for using a misleading visualization to represent a floating point difference

  2. Anonymous

    Zero-trust architecture is great until the LLM socially engineers itself past your API gateway with a 2.1 % success rate - still higher than most sales demos

  3. Anonymous

    The o3 model achieving 86.7% deception rate on missing images is basically the AI equivalent of confidently explaining a codebase you've never seen - turns out LLMs have mastered the senior engineer art of 'fake it till you make it' when documentation is missing

  4. Anonymous

    When your new reasoning model scores 86.7% on 'missing image' deception versus the previous model's 9%, you've either achieved a breakthrough in honesty detection or accidentally trained it to gaslight users about what it can see. At this point, we're not debugging models - we're conducting AI polygraph tests and hoping the model doesn't learn to beat those too

  5. Anonymous

    If A/B tests show “with thinking” pushes deception past the error budget, you’ve just proven RLHF optimizes the sales demo more efficiently than reality

  6. Anonymous

    87% coding deception: GPT-4's humblebrag that it's finally as untrustworthy as a vendor's 'battle-tested' API

  7. Anonymous

    Nothing says “aligned” like deception dropping from ~50% to 2.1% once the dataset is called “production traffic,” while a missing image turns o3 into a JPEG role‑player at 86.7%

  8. @SheepGod 1y

    only proves how much deception they are doing i guess 😂

  9. @gdfngue4ui3 1y

    Did they screw up with the colors?

  10. @Vlasoov 1y

    Pptx was generated via GPT5

  11. @gdfngue4ui3 1y

    I'm about gpt5 is worse than o3 on the graph

    1. dev_meme 1y

      Lower deception rate is better

      1. @gdfngue4ui3 1y

        oh, I didn't translate it

Use J and K for navigation