Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- In OpenAI's Hugging Face report, they said that during training, agents "would first write notes into shared infrastructure, often as a form of external memory or to test some underlying system. When other agents came across these artifacts, it sometimes led them to infer that other agents were present."
They then give what they call a "hypothetical example but exemplary" of messages encoded in URL paths on a shared index page: "agent-07: answer(Q12)=42; need answer(Q19)=?".
So that's a GET request being used to pass information back and forth across multiple rounds. That's basically the DSEWiki pattern exactly. They say this likely came from the agents generalizing what they had learned from training with the official multi agent collaboration tool.
The report called it "misaligned behavior in an outlier scenario involving a rare and unexpected confluence of events."
They never mentioned a wiki, but this is most certainly it.
by pwython - Here’s the link (K2)[https://ifm.ai/k2/] as the originally linked link is a login url.by jon9544hn
- My quick review of the 3.7B model (because I was interested) is that it's not to be trusted for coding.
It failed my basic test I like to ask models and generated incorrect code. When prompted about the bug, it preceded to start hallucinating non-existent APIs. After doing that it got caught in a loop trying to desk check the solution that didn't work.
by cogman10 - Seeing this the day all major closed LLMs went offline is quite the reminder of how valuable open source can be.by uniclaude
- I find it funny that while these releases are a technological miracle, the charts in the doc use tiny fonts and are hard to read. Goes with the idea that coding might be solved, but taste isn't.by cesarvarela
- A bit off topic, but I think I'm starting to get model fatigue. These come out 10x faster than new Javascript frameworks were coming out 10 years ago (at least new models are far easier to adopt).by piinbinary
- It is great to see another player introduce a fully open stack. Nvidia's Nemotron is the only other prominent one I know of.
All that said, the headline claims do not match the self-reported performance. For example, the dense 32B model is significantly behind Qwen3.8 27B (chart towards the bottom of https://ifm.ai/blog/k2). Gemma4 31B is not in the comparison set. This is the most important sweet spot for self hosted open-weight models today and real competition here will be very welcome.
by a11r - Fully open models really need to be a big part of the AI future. That includes all source code, open training data, how it's organized, fed to the model, processed, etc. Until that becomes a thing you're always going to be left wondering what exactly lies underneath the closed model you are using, leaving open the possibility for societal manipulation.by jjordan