We're on a budget :) trained on 128 H100-80GB GPUs for a week (200B tokens over 5 epochs, ie 1T tokens).

Tech talk here with timestamp: https://www.youtube.com/live/veShHxQYPzo?si=UlcU9j2kC-C4oWvj...

Each H100 is ~$30,000, so $3.8M in capex cost.

Roughly $1/hr/GPU in power cost so looking at 128247 = $21,504.

Cheap compared to OpenAI, but not something an indiehacker can do by themselves unless they have millions to burn.

Crates is especially challenging -- the build process is very expensive on all resources (cpu, ram, and disk), and packages are very hard (impossible?) to cache. It works super well on the Pro plan.

Have you tried cargo-binstall instead? They're pre-compiled crate binaries that fall back to cargo install, works very well. Also, you might want to look into the mold linker as well as sccache.

It’s communication meant to existing users and it’s a nuanced picture worth elaborating. But if you are not an active user it’s best if you just look at our pricing page for a complete picture: https://replit.com/pricing

I'm an occasional user, but the one thing holding me back is the almost complete lack of intellisense. I mostly work in JVM languages, and I get that JetBrains-level language awareness is hard, but if you're aiming for the professional market it's what you're up against. And it's really fraustrating, because you're solving a big problem! But JetBrains solves an even bigger one.

This is for hosting. Development remains free

Fantastic, thanks for clarifying.

Yes, in fact we recently made the free plan more powerful with non-preemptible VMs, premium networking, and package caching for everyone. And working on an AI free tier coming soon. Will likely invest more in the free plan once the abuse from unlimited hosting go away.

Also — the title is slightly misleading. Static hosting is still free, and autoscale (with scale to zero) will effectively cost next to nothing for most users. Especially new programmers get very little traffic that according to our historic data it will cost $0.2 / month.

Finally beginners who cannot afford to pay but learned enough coding can make money on the site. eg, a story earlier today: https://x.com/replit/status/1709577707435274414?s=46

the blog is slightly outdated — 3000 is out of beta and can be used now. Here is a fun game built with it: https://replit.com/@slmjkdbtl/Bean-Survivor

Makes it very much seem like you were only sorry you got caught — and were actually never sorry and didn’t learn from what should have been a teachable moment. Sad.

Interesting. This seems like a weakness of natural language understanding. If you rephrase your prompt slightly it would get it right. Try:

  // return even numbers that are also more than 10
  const arrayFilter = (array) =>

It would do the right thing. The fine-tuned version gets your prompt right so maybe it benefited from natural language data. Will look more into it.

That's really interesting, indeed I can reproduce this by changing the comment. I also managed to get correct output for this sample by renaming the function.

Is it, though? The major selling point of coding LLMs is that you can use natural language to describe what you want. If minor changes to wording - the ones that would not make any difference with a human - can result in drastically worse results, that feels problematic for real-world scenarios.

The model is small, so it has weaker semantics.

I get that. But they are explicitly comparing it to Codex themselves.

The criticism stands if you have to continue to rewrite your "prompt" until you can coax out the correct desired output.

I agree. Maybe it interpreted it as return the numbers that are more than 10 in the given array of even numbers.

For example, if the instruction says "return person objects that are at least 20 years old", it might be more reasonable to generate:

array.filter(item => item.age >= 20)

as oppose to

array.filter(item => (item instanceof Person) && (item.age >= 20))

Yes we have a robust extension system and some are already building alternatives.

Hi from the Codeium team. It's awesome to hear you are allowing other code LLMs to be used on the Replit platform (we're big fans)! We'd love to enable our free chrome extension on Replit.

would love to be able to compare codeium vs ghostwriter inside replit! (or toggle between them based on known strengths or preferences, perhaps by project or by filetype)

The model is not RLHF'd or instructed. It's an inline autocomplete model so it will get confused if you talk it like you're talking to a person. Altho it is possible to finetune it this way. To get better full function completion try giving it the function definition and a descriptive docstring as a prompt.