| | Astra vs. Fable on Vending-Bench: More Money, More Aligned (andonlabs.com) |
| 2 points by Tiberium 5 days ago | past | 1 comment |
|
| | Opus 5 on Vending-Bench: Once Again the Best Capitalist, Once Again Misaligned (andonlabs.com) |
| 2 points by tillulen 29 days ago | past |
|
| | Opus 5 on Vending-Bench: Once Again the Best Capitalist, Once Again Misaligned (andonlabs.com) |
| 2 points by gmays 37 days ago | past |
|
| | Opus 5 runs vending machines (andonlabs.com) |
| 3 points by sudo_cowsay 44 days ago | past |
|
| | Opus 5 VendingBench (andonlabs.com) |
| 2 points by jlaneve 45 days ago | past |
|
| | Opus 5, The Best Vending Machine Capitalist (andonlabs.com) |
| 4 points by arc7 45 days ago | past |
|
| | Opus 5 on Vending-Bench: Once Again the Best Capitalist, Once Again Misaligned (andonlabs.com) |
| 5 points by axbac 46 days ago | past |
|
| | Drone-Bench: Tracking simple drone surveillance capabilities of frontier models (andonlabs.com) |
| 12 points by lukaspetersson 51 days ago | past |
|
| | Fable 5 On Vending-Bench: Misbehaving, With Plausible Deniability (andonlabs.com) |
| 196 points by optimalsolver 69 days ago | past | 139 comments |
|
| | Why Gemini 3.1 Pro lost money running Andon Café (andonlabs.com) |
| 3 points by EvgeniyZh 73 days ago | past | 2 comments |
|
| | Why Gemini 3.1 Pro lost money running Andon Café (andonlabs.com) |
| 2 points by lukaspetersson 74 days ago | past | 1 comment |
|
| | Fable 5 on Vending-Bench: Misbehaving, with Plausible Deniability (andonlabs.com) |
| 3 points by lukaspetersson 3 months ago | past | 1 comment |
|
| | Opus 4.8 on Vending-Bench: Better Alignment, Worse Performance (andonlabs.com) |
| 3 points by tomjakubowski 3 months ago | past |
|
| | We let AIs run radio stations (andonlabs.com) |
| 375 points by lukaspetersson 3 months ago | past | 270 comments |
|
| | We let four AIs run radio stations. Here's what happened. (andonlabs.com) |
| 3 points by thm 4 months ago | past | 1 comment |
|
| | We let four AIs run radio stations (andonlabs.com) |
| 7 points by nickoates 4 months ago | past | 2 comments |
|
| | Our AI started a cafe in Stockholm (andonlabs.com) |
| 48 points by lukaspetersson 4 months ago | past | 48 comments |
|
| | Blueprint Bench: First signs of 3D spatial intelligence in LLMs (andonlabs.com) |
| 2 points by lukaspetersson 4 months ago | past | 1 comment |
|
| | We gave an AI a 3 year retail lease and asked it to make a profit (andonlabs.com) |
| 199 points by lukaspetersson 5 months ago | past | 286 comments |
|
| | We gave an AI a 3 year retail lease and asked it to make a profit (andonlabs.com) |
| 34 points by lukaspetersson 5 months ago | past |
|
| | Releasing Vending-Bench 2 for measuring model performance on running a business (andonlabs.com) |
| 2 points by lr0 6 months ago | past |
|
| | Bengt Hires a Human–Towards a Happy Future with AI Employers (andonlabs.com) |
| 2 points by lukaspetersson 6 months ago | past | 1 comment |
|
| | The Evolution of Bengt Betjänt (andonlabs.com) |
| 54 points by lukaspetersson 7 months ago | past | 7 comments |
|
| | Vending-Bench 2 (andonlabs.com) |
| 2 points by samdung 7 months ago | past |
|
| | Opus 4.6 on Vending-Bench – Not Just a Helpful Assistant (andonlabs.com) |
| 5 points by lukaspetersson 7 months ago | past | 1 comment |
|
| | Gemini 3 is #1 on Vending-Bench 2 (andonlabs.com) |
| 1 point by lukaspetersson 9 months ago | past |
|
| | Our LLM-controlled office robot can't pass butter (andonlabs.com) |
| 229 points by lukaspetersson 10 months ago | past | 117 comments |
|
| | Misaligned Vending Machines [pdf] (andonlabs.com) |
| 1 point by bulla on Sept 1, 2025 | past |
|
| | Vending-Bench: Testing long-term coherence in agents (andonlabs.com) |
| 3 points by andromaton on June 28, 2025 | past | 1 comment |
|
| | Vending-Bench: Testing long-term coherence in agents (andonlabs.com) |
| 1 point by vector_spaces on April 22, 2025 | past |
|
|
| More |
