Viewing profile — dkersten

At what cost though? “Beating” isn’t enough if it costs 100x or even 10x the amount.

You still have to remember what sizes or whatever to use for what to make it consistent, it’s just they get packed into the “class” attribute. It’s not uncommon to see very long cl…

Yep, it’s also availability on Together.ai for your sale price. Fireworks and Together were the first places I checked!

Oh, absolutely.

Because it lets you constrain the parts that the compiler can’t check and has to trust you on. The alternative is either a langue that can’t do necessary things, or a language that…

Finally, we can replace daylight saving time by just making more daylight instead

I love Mantine. It’s easy to use, full featured with lots of components and helpers, and yet if you need to, you can use it headless and customise it too (I’ve never bothered thoug…

Many vendors and service providers have SLA’s and contracts, at least for the critical services.

Sure but that adds a lot of complexity and cost to your business. It’s much simpler and safer to just work with more reliable vendors to begin with. Why build on quicksand when the…

altmanaltman is correct, I was talking about vendors. If you rely on a vendors service for your own business, you want it to be consistent. How can you plan around and rely on some…

I honestly find it crazy how many people trust them for their business needs. For a business, you want consistency and no surprises. With them you get exactly the opposite.

I like to start out by creating the overall structure of my application: the module structure, high level components, feature boundaries. That way these decisions are already made …

And AI tried telling me that Uber for Dogs (dogs are the drivers) was a terrible idea…

Its on other providers, like Together.ai

> This is not scientific at all, just vibes, YMMV. This is the problem. I would love to have a product sheet showing what each models strengths an weaknesses are, so that I can hav…

Is that true though? From Cherno’s videos it sounded like it was basically the hazel engine, repurposed. So unless he rewrote hazel, purposely for robotics, it’s still not actually…

Haven’t Unreal engine and Unity been used for robotics for over a decade? Hasn’t the Bullet physics engine been used for robotics for over a decade? I don’t understand this “first …

They did, I had something like $50 in FTX and I got it back. I don’t remember when, I think it was about a year ago.

Why am I not surprised that its a YC startup? Lately, being a YC startup seems to have become a negative signal for me, far too many grifters are getting funded by YC, it seems.

> That presumes models are only useful if they are one-shot models That’s not at all what I’m saying. I’m saying that in my experience across multiple models, the follow up prompts…

I haven’t used Fable/Mythos yet, but my experience with recent version of Opus, GPT 5.5 and recent Chinese models is that promoting again isn’t guaranteed to fix the underlying iss…

That’s the one. The speed is incredible and fun to see, but the model is rather weak to the point where I’m not sure it’s particularly useful for most people.

> You've gone too fast, too much is vague, nothing is clear. Contrast to when Clojure was released: Rich Hickey had spent years thinking about, researching, and refining the concep…

I’ve been playing around with groq and GPT OSS which they run at 1000 TPS (20B) or 800 TPS (120B) and the speed feels quite magical. I haven’t tried cerebras’ 3000 TPS yet but I di…