Submissions from andonlabs.com

		Releasing Vending-Bench 2 for measuring model performance on running a business (andonlabs.com)
		2 points by lr0 1 day ago \| past \| discuss
		Bengt Hires a Human–Towards a Happy Future with AI Employers (andonlabs.com)
		2 points by lukaspetersson 10 days ago \| past \| 1 comment
		The Evolution of Bengt Betjänt (andonlabs.com)
		54 points by lukaspetersson 17 days ago \| past \| 7 comments
		Vending-Bench 2 (andonlabs.com)
		2 points by samdung 17 days ago \| past
		Opus 4.6 on Vending-Bench – Not Just a Helpful Assistant (andonlabs.com)
		5 points by lukaspetersson 21 days ago \| past \| 1 comment
		Gemini 3 is #1 on Vending-Bench 2 (andonlabs.com)
		1 point by lukaspetersson 3 months ago \| past
		Our LLM-controlled office robot can't pass butter (andonlabs.com)
		229 points by lukaspetersson 4 months ago \| past \| 117 comments
		Misaligned Vending Machines [pdf] (andonlabs.com)
		1 point by bulla 5 months ago \| past
		Vending-Bench: Testing long-term coherence in agents (andonlabs.com)
		3 points by andromaton 8 months ago \| past \| 1 comment
		Vending-Bench: Testing long-term coherence in agents (andonlabs.com)
		1 point by vector_spaces 10 months ago \| past
		Vending-Bench: Testing long-term coherence in agents (andonlabs.com)
		5 points by tosh 10 months ago \| past \| 2 comments
		Vending-Bench: Testing long-term coherence in agents (andonlabs.com)
		1 point by gdeglin 11 months ago \| past
		Claude isn't the best Computer-use agent (andonlabs.com)
		2 points by lukaspetersson on Jan 10, 2025 \| past