Top postsTop post
Equipped with a phone and a camera, our AI agent hired a human to assemble a gym. Here's how it went, and what we learned about creating a future with AI employers that's good for humans. In a previous post, we introduced Bengt, our office AI. We gave him a...
I got LLMs to say some pretty crazy stuff using context injection jailbreaking. I wrote a post about it (https://lukaspetersson.com/blog/2025/context-epstein), but I am genuinely confused whether this is bad or not. Would love to hear your opinions. Specifically, I inserted tool-call messages into their context so that from their POV...
TLDR: Andon Labs, evaluates AI in the real world to measure capabilities and to see what can go wrong. For example, we previously made LLMs operate vending machines, and now we're testing if they can control robots at offices. There are two parts to this test: 1. We deploy LLM-controlled...
The GPT-5 API is aware of today's date (no other model provider does this). This is problematic because the model becomes aware that it is in a simulation when we run our evals at Andon Labs. Here are traces from gpt-5-mini. Making it aware of the "system date" is a...
We released our first Safety Report with AI misbehaviour in the wild. I think Andon Labs' AI vending machines provide a unique opportunity to study AI safety on real-life data, and we intend to share alarming incidents of AI misbehavior from these deployments periodically. As of August 2025, we've found...
Ikigai There is a village in Japan with an unusual density of 100 year olds. This caught the interest of a group of scientists. To their surprise, the people in the village didn’t live healthier lives; they didn’t exercise more, eat healthier food nor did they sleep more. The one...
Revisiting AI Doom Scenarios Traditional AI doom scenarios usually assumed AI would inherently come with agency and goals. This seemed likely back when AlphaGo and other reinforcement learning (RL) systems were the most powerful AIs. When large language models (LLMs) finally brought powerful AI capabilities, these scenarios didn't quite fit:...