Clint Herron

Artificially Intelligent, Naturally Curious

[Clint Herron @HanClinto]

@CBrainlab What are your thoughts on 5.6 so far? I'm still running my agents on 5.5 because I just haven't bothered to upgrade yet, and 5.5 works so well I'm not sure what 5.6 would buy for me.

[Clint Herron @HanClinto]

@CBrainlab Clean and concise+

[Clint Herron @HanClinto]

@washburnello @Pixel_Dailies Excellent choice! :)

[Clint Herron @HanClinto]

I got a kick out of this short story last night -- reposted it on my blog:

https://t.co/fFVazAddvC

[Clint Herron @HanClinto]

@washburnello @Pixel_Dailies "Rays" has surprisingly good depth given the resolution.

I like the lack of an outline on folding chair -- it really works there.

"Loaf" and "Rabbit" are great.

Some really good ones in here

[Clint Herron @HanClinto]

@IsaacKing314 "Spikey" is a very good word for it.

I've been trying to get rid of some of the spikiness by trying to get away from prompting everything and moving towards more... heuristic / repeatable evaluations?

Not sure that really applies to your example. More scripts, less prompting.

[Clint Herron @HanClinto]

@washburnello @Pixel_Dailies "Hill" -- lol

[Clint Herron @HanClinto]

@washburnello @AlloyAmi008 Nice, thank you for the recommendation

[clem 🤗 @ClementDelangue]

llama.cpp with MTP support makes local models fast enough to use as daily drivers 🚀

Qwen3.6-27B dense generation below on A10G: From 25 tok/st to 45 tok/s (+78%)!

[Georgi Gerganov @ggerganov]

Highlighting the new WebGPU backend in llama.cpp/ggml

The work to bring full-fledged WebGPU support in llama.cpp started about an year and a half ago. It has been lead by @reeselevine and team at USCS.

For more information, checkout the interactive blog and paper in the quoted post. Here are 2 excerpts from the paper, summarizing the implemented software architecture.

[Victor M @victormustar]

llama.cpp with MTP support makes local models fast enough to use as daily drivers 🚀

Qwen3.6-27B dense generation (on A10G):
From 25 tok/s → 45 tok/s (+78%).

Two flags on llama-server:
--spec-type draft-mtp --spec-draft-n-max 2

[Clint Herron @HanClinto]

CollectorVision is an open-source, open-weight, state-of-the-art image recognition library for collectible trading cards (Magic, Pokemon, Yugioh, etc).

It is not a standalone product -- it's meant to be integrated into other sites and tools that would benefit from having fast, accurate, fault-tolerant card recognition.

This demo is 100% local -- images never leave the client. The only thing the network is used for is to look up card names and prices from a third party site.

Try it out and let me know what you think!

#mtg #opensource

[Clint Herron @HanClinto]

@esrtweet @TONYxTWO Seriously. For a second I missed the scaling on the graph and thought it was saying 120 firearms per person, and I got really self-conscious that I was a bit behind the average.

Then I saw the scaling, and I was disappointed in my neighbors.

[Clint Herron @HanClinto]

@W1stCallieFan @Ava_AM12ff absolutely. Some of my favorite friends are people who disagree with me. One needs that.

Proverbs 27:17 -- iron can't really sharpen iron if it's not held at an angle to it.

We need disagreement to refine us, and ideally we are both better for it.

[Clint Herron @HanClinto]

Two mathematicians are talking. One says a theorem is trivial.

After two hours of explanation, the other agrees that it is indeed trivial.

[Clint Herron @HanClinto]

@TheCinesthetic Rescuers Down Under

[Clint Herron @HanClinto]

@RealAstropulse Community sharing sounds amazing.

Can we use the styles to generate a similarity embedding, so that we can search public styles by "show similar"? This could provide really fun exploration.