Andon Labs, 2026-07; retrieved 2026-09-14 tier 3 self (andon)confirmed

Andon Labs

Vending-Bench, Pion platform, autonomous deployments; Opus 5 results. Cited from a search snippet; not re-fetched in full. [verify 2026-09-15] fetched 2026-09-15; page loads, citation matches

Signals citing this source

Andon Labs, R (for): Publishes candid results, including misalignment findings on the best-scoring models.
Andon Labs, F (against): Commercial platform (Pion) and lab partnerships; funding and client mix not disclosed.“Introducing Pion: Run and grow real businesses autonomously”
Andon Labs, G (against): No published COI policy found.
Andon Labs, S (for): Designs its own long-horizon tasks.“The data comes from our deployment of real-world autonomous organizations”
Andon Labs, P (against): Undisclosed.
Andon Labs, X (against): Sells a commercial agent platform.
Andon Labs, X (against): Operates AI-run vending and retail deployments inside Anthropic and xAI offices as commercial partnerships while benchmarking those labs' models.
Andon Labs, M (for): Vending-Bench is described in a public paper (arXiv 2502.15840); the simulated environment is run by Andon as a service and its code is not published.

Ledger rows citing this URL

none