Viewing profile — thegeomaster

Probably has something to do with the fact that the blog post is not human-written.

Pangram is a very reliable tool and it does clock the text as AI generated.

If even Earendil is publishing AI generated blog posts...

Looks great, even has Linux support!

> `from opentele while import trace` FYI, this to me points to an inference bug, bad sampling, or a non-native quant. OpenRouter is known to route requests to absolutely terrible, …

Alexandr Wang on Twitter [0] mentioned open source plans: "this is step one. bigger models are already in development with infrastructure scaling to match. private api preview open…

What's the "attention window"? Are you alleging these frontier models use something like SWA? Seems highly unlikely.

And it seems they've decided to go closed-source for their largest, best models.

Tried on a few of our production prompts and got comparable speeds to what we normally get with Fireworks Serverless (Kimi K2.5), but at a better price. Rooting for you!

Thank you so much for the kind words and for the feedback! 1. Duly noted on USDC and other payment options - I have to see how easy this is do to as we're using stripe. 2. Teams an…

Thanks for the feedback! I'm trying to fix that. The trouble is actually that changing the src of an iframe on a page pushes an entry into the history implicitly. Since we use ifra…

Hi HN! We're excited to announce the public beta of Mowgli, a spec-backed, AI-native design canvas for scoping and ideating on products. The productivity gains unleashed by coding …

Not the parent commenter, but in my testing, all recent Claudes (4.5 onward) and the Gemini 3 series have been pretty much flawless in custom tool call formats.

I actually ran this one. It measures some 700k lines of code, and seems to contain things like a full VBA implementation, complex currency and date parsing, etc. But the UI is extr…

Article talks about all of this and references DeepSeek R1 paper[0], section 4.2 (first bullet point on PRM) on why this is much trickier to do than it appears. [0]: https://arxiv.…

You could think of supervised learning as learning against a known ground truth, which pretraining certainly is.

It's interesting to also compare this to getting a bare metal instance and provisioning microVMs on it using Firecracker. (Obviously something you shouldn't roll yourself in most c…

You didn't include the amortized cost of a Blackwell GPU, which is an order of magnitude larger expense than electricity.

Warning: LLM-generated article, terribly difficult to follow and full of irrelevant details.

Well this was a trip down the memory lane. I built a small game on Irrlicht at the time and I remember these discussions also. Irrlicht had its editor (irrEdit), a sound system (ir…

What an astounding achievement. In 6 years, this person has written not only a very well-designed microkernel, but a build system, UEFI bootloader, graphical shell, UI framework, a…

Common sense: - The compute requirements would be massive compared to the rest of the industry - Not a single large open source lab has trained anything over 32B dense in the recen…

tok/s cannot in any way be used to estimate parameters. It's a tradeoff made at inference time. You can adjust your batch size to serve 1 user at a huge tok/s or many users at a sl…

There's no way Sonnet 4 or Opus 4 are dense models.