Viewing profile — westoncb

Location: Tucson, Arizona, USA Remote: Yes Willing to relocate: Yes Technologies: TypeScript, Rust, React, three.js, HTML/CSS, Java Résumé/CV: https://symbolflux.com/resume.html Em…

That's fine as a point but it's not what the headline describes. The question of total/real effect on accuracy is also something one could ask about. Both are valid.

I've been building this "general problem solver" (will likely focus on math problems first) that uses a special kind of orchestrator to direct/structure the problem solving approac…

Taking on a 'slow' software project with the kind of attention to quality (inside and out) that I had pre-AI. It's a tool I'll use myself, LLM-related, but not any kind of radical …

>but you could give me two black boxes that act the same externally, one written as a single line , single character variables, etc. etc. etc. and another written to be readable, a…

He also remade quake a couple weeks ago (on three.js as well I believe).

It wouldn’t work for other models if it’s encoded in a latent representation of their own models.

I would guess you can if you're using their Responses api for inference within your agent.

Interesting that compaction is done using an encrypted message that "preserves the model's latent understanding of the original conversation": > Since then, the Responses API has e…

https://symbolflux.com

That depends on the content of the SVGs.. Of course you can write a script to do a very literally kind of conversion of regardless, but in practice a lot of interpretation would be…

That's about how it came across for me as well: ignoring my actual content and joking about generalizations related to key words. Project is cool overall, love the xkcd-like comic …

It sounds more like you just made an overly simplistic interpretation of their statement, "everything works like I think it should," since it's clear from their post that they reco…

I've been on a break from coding for about a month but was last working on a new kind of "uncertainty reducing" hierarchical agent management system. I have a writeup of the projec…

Ah interesting, I missed that possibility. Digging a little more though my understanding is that what's universal is a shared basis in weight space, and particular models of same a…

> So, they found an underlying commonality among the post-training structures in 50 LLaMA3-8B models, 177 GPT-2 models, and 8 Flan-T5 models; and, they demonstrated that the common…

I think the idea is like: it took extra work 'cause Rust makes you be so explicit about allocations and types, but it's also probably faster/more reliable because that work was don…

Doing math is not the same as calculating. LLMs can be very useful in doing math; for calculating they are the wrong tool (and even there they can be very useful, but you ask them …

lol no problem. In reality though there's kind of a funny story behind it because I suspect the way I ended up using them so much is similar to how ChatGPT did. When I got into wri…

I actually tweeted like a month ago that I was the reason LLMs use em dashes so much lol: https://x.com/Westoncb/status/1961802304698671407

The difference is the incentive to improve, and actual present rate of improvement, for models like this is far higher than it is for jetpacks. (That and certain intrinsic features…

Yep, it's surreal.

lol yep, fully get that. And I mean I'm sure o4 will be great but the '-mini' variant is weaker. Some of it will come down to taste and what kind of thing you're working on too but…

I've seen that specific kind of role-playing glitch here and there with the o[X] models from openai. The models do kinda seem to just think of themselves as being developers with t…

Gotcha. Yeah, give o3 a try. If you don't want to get a sub, you can use it over the api for pennies. They do have you do this biometric registration thing that's kind of annoying …