Viewing profile — dnhkng

Totally! This with DwarfStar delivers usable local AI (I hope!)

I think the commenter means the Flash vs Terra benchmarks.

It will be fair if they release the harness though. I think now the future will be paired model-harness releases, not just weight dumps. The performance changes are so big with the…

DeepSeek V4 Flash (Preview → 2026-07-31) • Terminal Bench: 56.9 → 82.7 (+25.8) • Toolathlon: 51.8 → 70.3 (+18.5) Compared to GPT-5.6 Terra: • Terminal Bench: Flash 82.7 vs Terra 78…

Maybe instead of proofs, we should encourage the publishing of prompts and reasoning traces?

Maybe instead of proofs, we should encourage the publishing of prompts and reasoning traces?

Author here: Yeah, the encoder and decoder stuff is explicit, but the internal structure in generated during training. I don't think the big labs were doing this back when I did th…

Too bad they also don't give anything back to individual researchers. Oh well, wasn't expecting much.

I have added an endpoint for CLI-dwellers: curl -X POST https://quantumlever.stream/api/magic-8-ball \ -H "Content-Type: application/json" \ -d '{"question":"Will my sampler touch …

Gday, author here! I've wanted to hack together a "real" quantum random number generator for another upcoming project, and I got carried away a bit, and went down the 'over-enginee…

Yes, dammit. Author here. I drafted it before I left for holiday, at it's not ready to publish. It wasn't supposed to be officially posted yet, but I ran out of time before my flig…

Thanks! I have pushed basic code to GitHub ( https://github.com/dnhkng/RYS ) Some interesting areas to explore might be a combination of deleting some layers and duplicating others…

Author here: The code is up on GitHub. The probes I used seem to help identify good configurations, but are quite noisey. A small probe set was initially used to make the scan trac…

Author here: That was done in this blog post, in the beam search. I started with the best re-layer configs, and iteratively added more blocks, including the same multiple times, du…

There was some work done on this a while back, during the FrankenMerge craze of 23' I am working with TurboDerp to integrate this into the Exllama v3 format.

Author here. Another thing I want to highlight: the language-agnostic "thinking space" finding came from Evan Maunder, who read Part 1 and ran an elegant experiment — same sentence…

Author here. The result that surprised me most: after evaluating 3,024 beam search candidates, training a surrogate model on ~4,600 measurements, and scoring 2 million configuratio…

[dead]