Introducing System One Models and Jev

Post by tylermarques » Wed, Sep 16, 2026, 6:19 PM UTC

kevmo314 wrote: post #365

tylermarques wrote: post #125

We had early access and found it to be pretty useful. Having a second form of verification, where you can ask multiple questions (in the form of Nouls) raised our confidence in the outputs of other models. [0] IMHO This type of model works incredibly well in concert with LLMs, not as a replacement. [0] https://goodstartlabs.com/research/verification-is-the-bottl...

Don't your numbers suggest DeepSeek V4.1 Flash, for $100 more, gets you to slightly better agreement?

Post by satvikpendem » Wed, Sep 16, 2026, 6:41 PM UTC

vintermann wrote: post #404

> Structured outputs slot into ordinary software as fuzzy decision rules: classify, route, score, extract, or branch where hand-written logic is too brittle. Oh, I have one of those use cases, matching people in genealogy trees. You can ask all sorts of questions: do the names match? Do they match within some edit distance? Do they match according to soundex/ metaphone rules (which are themselves a ginormous set of r…

Post by haarts » Wed, Sep 16, 2026, 7:24 PM UTC

xixixao wrote: post #351

lubujackson wrote: post #339

Earlier quoted context omitted.

Not confidential, but not super relevant, as this is something I have learned the hard way over the past year across various projects. A lot of people have become prompt maximalists, asking for complex multi-part solutions or dynamic workflows in a single prompt. You can get this to work sort of reliably with frontier models, but without much confidence or clarity where things might break in practice. My goal is to s…

Example I have worked: Personal delivery app, that tracks packages from various senders using incoming emails. I am using the single prompt approach with GPT5.4, which is free, but it’s not reliable. Using Jev I’d decompose the prompt into a bunch of smaller questions, then I’d combine the answers in software. I’m super excited to try Jev out.

Post by DavCreator » Wed, Sep 16, 2026, 8:24 PM UTC

smusamashah wrote: post #456

rana3g wrote: post #366

Earlier quoted context omitted.

you don't say - https://huggingface.co/harshatheg/Qwen-2.5-1B-RLCD

https://x.com/harshagundal/status/2100044305536889015 tweet by the author

Post by baq » Wed, Sep 16, 2026, 9:28 PM UTC

stpedgwdgfhgdd wrote: post #444

baq wrote: post #364

Earlier quoted context omitted.

A quantum calculator answers in distributions.

In one universe that is true, in another one not.