Viewing profile — bensyverson

Probably both, but I have to add: I agree with the post. I've done a ton of agentic development using Go over the past 6 months, and it hasn't let me down. You may ask "why not Rus…

Yes but how often in practice does the same information stay accessible via 30x redirects after one reorganization, let alone two or three?

I would assume that training pales in comparison to inference when it comes to energy use, taking into account the number of inference users

That’s because no one wants to admit that their product is vibe coded… But there are plenty of vibe coded products out there making money from actual users.

This is super cool! I like the idea of expressing the game declaratively, with a language that an LLM can easily understand. Do you have any other demos of what the language is cap…

What about alphabetical order would lead "Section 9" to sort above "Section 8"?

I'm not sure what's going on with the ordering of the sections, but it's definitely creative. - 01: Section 1 - 02: Section 11 - 03: Section 10 ... - 10: Section 3 - 11: Section 2 …

one week later: "It says 'You're absolutely right! Let me look at the seams so I'm checking, not guessing—' and I guess that's when my SSD melted."

And is this using conventional model loading (all in VRAM), or are you streaming it in some way?

Are people getting decent tokens/second throughput? Some of these demos crawl at 1 tok/s or worse, which limits their utility.

I do think these “run a bigger model than will fit in VRAM” projects are necessary steps, but are they functionally useful or helpful to anyone currently? For example, is anyone ou…

Yes, the writing just has a disproportionate impact on this outcome.

How does one even purchase an AMD MI355X?

People said this kind of thing about MiniDV cameras, and then iPhones. The reality is that technology hasn't been a barrier for filmmakers for a very long time. Writing is still th…

I think it just gets really into the weeds and assumes you have full context. I do find myself saying "You have more context than me—can you restate the question in simple terms?" …

The machines really are learning

New music genre just dropped

On the one hand, they say "for experimental purposes only," but on the other hand, hey, no cancer warning!

Yes, I do this all the time, and also check in the co-authored project plans which drove the commits. For a project that is transparently only possible due to agentic coding, I don…

Needs more "invariant," its latest catchphrase

> models don't have a good sense of their own capabilities. It actually had some memorized knowledge about LLMs being bad at confidence intervals, then it did a cursory web search.…

I was designing a system that pulls structured data out of an unstructured transcript, and Opus initially suggested a confidence score for each value. When I asked it “do you think…

[dead]

Sure, it's a real mix. Most recently: - An electrical component "synthesizer" which takes natural language specifications in (e.g. from an RFQ) and uses material data sheets and co…

Same, though the types of jobs I’m working on now require the speed I get from LLMs. If I had to take my current projects and switch to hand-coding I’d have to extend the timelines…