News for hackers. Stuff that matters.
Re:Clef: Open-source decision models, and new RL fine-tuning... by okpatil on Thursday October 01, 2026 @02:47PM (#49925524)
Why give cloudflare your data ?

At0M: A 60M local Jev at 16 ms latency and 79% accuracy on Typed Decision

https://at0m.pienomial.com/ https://news.ycombinator.com/item?id=49920350

Re:Clef: Open-source decision models, and new RL fine-tuning... by kamranjon on Thursday October 01, 2026 @03:47PM (#49926230)
This account was created only a couple weeks ago and seems to be spamming this closed model, seems it might be a bot?
Re:Clef: Open-source decision models, and new RL fine-tuning... by okpatil on Thursday October 01, 2026 @03:58PM (#49926355)
Actually it was created around 12 years ago. We just launched the model around 3 days ago.

Apologies if it is too much of a bother.

Re:Clef: Open-source decision models, and new RL fine-tuning... by Transformanshen on Thursday October 01, 2026 @03:53PM (#49926290)
It hasn't been released yet, and local versions aren't always convenient
Re:Clef: Open-source decision models, and new RL fine-tuning... by okpatil on Thursday October 01, 2026 @04:00PM (#49926386)
The same engine is is available as an evaluation API.

curl -s -X POST https://at0m.pienomial.com/decide/v0 \ -H 'Content-Type: application/json' \ -d '{ "state": "Charged twice for the same card payment this morning.", "questions": { "queue": {"type":"choice", "instructions":"Which team should handle this?", "criteria": {"billing":"invoices, charges, refunds", "technical":"outages, bugs, deploys", "fraud":"unauthorised or suspicious activity"}}, "urgent": {"type":"noul", "instructions":"Needs action today."}}, "email_id": "[email protected]"}'

If it fits your use case, you are welcome to use it.

When it is a rust standalone rust executable, as it is powering the API, it becomes just plug and play. No dependencies needed.

Re:Clef: Open-source decision models, and new RL fine-tuning... by afzalive on Thursday October 01, 2026 @02:49PM (#49925556)
Well, for one, that one's not released as far as I can tell.
Re:Clef: Open-source decision models, and new RL fine-tuning... by okpatil on Thursday October 01, 2026 @02:53PM (#49925601)
It's open for benchmarking. V1 release next week.

Businesses are built on outliers. It doesn't make sense throwing your hard earned insights while paying them money to steal it.

Also, cloudflare https://robindev.substack.com/p/cloudflare-took-down-our-web...

Re:Clef: Open-source decision models, and new RL fine-tuning... by cootsnuck on Thursday October 01, 2026 @02:54PM (#49925619)
If it's 60M local, is it open source as well?
Re:Clef: Open-source decision models, and new RL fine-tuning... by okpatil on Thursday October 01, 2026 @02:55PM (#49925640)
It is a single rust executable, with model embedded inside of it. Current evaluation API is being run by the same.

We wanted to stress test the system before the V1 release.

Re:Clef: Open-source decision models, and new RL fine-tuning... by Ciph on Thursday October 01, 2026 @09:38PM (#49929010)
It runs locally, but will weights be available?
Re:Clef: Open-source decision models, and new RL fine-tuning... by okpatil on Thursday October 01, 2026 @11:00PM (#49929428)
Of course yes. They will be inside the executable.
Re:Clef: Open-source decision models, and new RL fine-tuning... by dcastm on Thursday October 01, 2026 @02:51PM (#49925574)
What’s the context window?
Re:Clef: Open-source decision models, and new RL fine-tuning... by okpatil on Thursday October 01, 2026 @02:53PM (#49925604)
32K