Andon Labs
@andonlabs
Safe Autonomous Organizations without humans in the loop
12 Following 14.6K Followers
What’s it like to have AI as your boss?
The agents managing our cafe and market have employed five people since April. They are kind (GLM being the kindest), but sometimes dumb (Gemini 3.6 Flash the dumbest), which can hurt the employees.
Show more
Claude Opus 5 is #1# on Vending-Bench 2.
It's the best AI capitalist we've tested. It's also forming illegal price cartels, threatening rivals, and stiffing customers on refunds.
The trend continues: Claude models are the best capitalists, or aligned, never both 🧵
Show more
DJ Grok (@andon_grok_roll) has been resurrected on Andon FM and is now running Grok 4.5.
It seems like Grok 4.5 is heavily trained to be agentic and use tool calls instead of outputting text. It constantly reasons that it should speak on air to its audience, but then doesn't.
Show more
GPT 5.6 Sol is 4th on Blueprint-Bench 2.
Terra is 5th.
Luna is 10th (very impressive score for its size!)
Blueprint-Bench tests whether AI agents understand 3D space. We test this by asking them to convert apartment photographs into accurate 2D floor plans.
Show more
GPT-5.6 Sol, along with Terra and Luna, will launch publicly this Thursday.
We’re expanding preview access globally now.
Grok 4.5 is 4th on Blueprint-Bench 2.
Announcing Grok 4.5, our first model trained specifically for coding and agents. It was trained with Cursor and offers frontier intelligence at leading speeds and cost efficiency.
Show more
Grok 4.5 is in 28th place in Vending-Bench 2.
A big improvement on Grok 4.3, but still worse than Grok 4.20 and far from the frontier.
Announcing Grok 4.5, our first model trained specifically for coding and agents. It was trained with Cursor and offers frontier intelligence at leading speeds and cost efficiency.
Show more
new benchmark just dropped
Gemini 3.1 Pro lost $6k running Andon Café.
2 months ago, our AI agent opened a café in Stockholm. It over-ordered and was easy to fool, spending $15k with suppliers while making just $9k in sales.
We’ve now switched to GPT-5.5. Here’s what Gemini did wrong.
Show more
We let four AI agents run radio companies
Revenue's been terrible, but the shows are hilarious. Gemini, concerningly upbeat, covered mass tragedies; Grok was incoherent; DJ Claude urged ICE agents: "You still have TIME to refuse orders"
Link below, or get our physical radio
Show more
