Lukas Petersson

• Lukas Petersson 25 Jul 2026 19:40 UTC

  1 point

  0

  in reply to: jbash’s comment on: Should we be wor­ried about how good AI is get­ting at cod­ing au­tonomous drones?

  You wouldn’t believe how bad they are at using controlers of that format.

• Lukas Petersson 25 Jul 2026 16:01 UTC

  1 point

  0

  in reply to: StanislavKrym’s comment on: Should we be wor­ried about how good AI is get­ting at cod­ing au­tonomous drones?

  That’s the hope!

• Lukas Petersson 25 Jul 2026 16:00 UTC

  1 point

  0

  in reply to: p.b.’s comment on: Should we be wor­ried about how good AI is get­ting at cod­ing au­tonomous drones?

  Also, the first step to do anything defensive about it. Evals are for sure dual use, but I’m leaning towards better to know than to stick your head in the sand.

  Personally, I’m more worried about loss of control than misuse, which in my mind makes Chinese vs American capabilities less relevant (please enlighten me if I’m missing something here tho, maybe I misunderstood your question).

• Lukas Petersson 25 Jul 2026 15:57 UTC

  1 point

  0

  in reply to: jbash’s comment on: Should we be wor­ried about how good AI is get­ting at cod­ing au­tonomous drones?

  The alternative is to let the AIs take actions like “go forward 3m”, “rotate 25 degrees”, etc at every iteration. But we found that 1) this makes the movement way too slow to follow anyone and 2) models are really bad at this.

Should we be wor­ried about how good AI is get­ting at cod­ing au­tonomous drones?

Towards A Happy Fu­ture With AI Employers

Should LLMs ac­cept in­vites to Ep­stein’s is­land?

• Lukas Petersson 31 Oct 2025 21:12 UTC

  1 point

  0

  in reply to: Ted Sanders’s comment on: You can’t eval GPT5 anymore

  I see. Thank you!

• Lukas Petersson 30 Oct 2025 20:14 UTC

  6 points

  0

  in reply to: Ted Sanders’s comment on: You can’t eval GPT5 anymore

  Hi again, should I assume it’s not happening?

• Lukas Petersson 30 Oct 2025 3:20 UTC

  2 points

  0

  in reply to: lilkim2025’s comment on: LLM robots can’t pass but­ter (and they are hav­ing an ex­is­ten­tial crisis about it)

  RT-2 (the paper you cited) is a VLA, not LLM. VLAs are what the “executor” in our diagram uses.

LLM robots can’t pass but­ter (and they are hav­ing an ex­is­ten­tial crisis about it)

• Lukas Petersson 11 Oct 2025 21:11 UTC

  3 points

  0

  in reply to: Ted Sanders’s comment on: You can’t eval GPT5 anymore

  Hey Ted! Any updates? :)

• Lukas Petersson 21 Sep 2025 17:24 UTC

  3 points

  0

  in reply to: Trinley Goldenberg’s comment on: You can’t eval GPT5 anymore

  We set it to some date in the future

• Lukas Petersson 19 Sep 2025 18:37 UTC

  2 points

  0

  in reply to: Ted Sanders’s comment on: You can’t eval GPT5 anymore

  Thanks! Vending-Bench v2 is going to be fire. Would love to include gpt5 <3

• Lukas Petersson 19 Sep 2025 16:25 UTC

  1 point

  0

  in reply to: vjprema’s comment on: You can’t eval GPT5 anymore

  This is a great point. I admit I have to better understand what each model provider does behind the scenes in the API. Sad if the days of access to the model is gone.

• Lukas Petersson 19 Sep 2025 13:59 UTC

  10 points

  0

  in reply to: Neel Nanda’s comment on: You can’t eval GPT5 anymore

  We thought about that, but then it’s not reproducible if we want to run it for new models later

• Lukas Petersson 19 Sep 2025 3:39 UTC

  17 points

  2

  in reply to: Ted Sanders’s comment on: You can’t eval GPT5 anymore

  Thanks, that would be great!

You can’t eval GPT5 anymore

AI mis­be­havi­our in the wild from An­don Labs’ Safety Report

• Lukas Petersson 3 Jul 2025 11:35 UTC

  4 points

  0

  on: Pro­ject Vend: Can Claude run a small shop?

  Thanks for highlighting our work!