redox99

This is orders of magnitude cheaper and faster than paying for a song to be created from scratch by a human.

Yeah I tried GPT first because that's what I always use, it refused and I didn't even bother trying to trick it, just went straight to Grok.

Can you use Lean to... prove "Lean-fast" is equivalent to Lean?

Btw grok found out in less than ten seconds what place you refer to and likely what software within that company.

Things that wouldn't be worth your time before are trivial these days with LLMs.

You can argue all day whether cars are good or bad. That's not my point. My point is that pretending public transport is equivalent to cars if you have good enough infrastructure is silly. They are different experiences, each with their own tradeoffs. And those tradeoffs matter differently to different people.

Unnecessary is a very strong word. It's also unnecessary to have your own private house, sharing it with other people would be more efficient.

Public transport is not the same as cars. It's silly when people pretend like they are interchangeable and it's just a matter of having "better infrastructure".

With the miles you can establish a confidence interval of the true fatality rate.

Astra is definitely weird. It is more capable than Sol, no doubt about that. There are things sol could simply not solve that Astra breezes through.

However for typical low to medium difficulty code, it will often either overengineer stuff, create massive functions instead of organized code, and just write very hard to read code. It literally looks like minified code. Clearly they trained it to reduce the number of output tokens and in turn the code is often atrocious. I'll keep trying Astra but I might actually go back to 5.6 sol for many tasks if I keep getting these results.

Just use opencode/pi/etc with an open weight model?

Thanks for the reply. I'd suggest you improve your workflow with better tooling like Codex or Claude code, and if you have some kind of weird constraint they'll easily follow an AGENTS.md with that.

Those are really nice numbers. With that t/s, no network latency or queueing it must feel much snappier than cloud models.

Do you... code by copy pasting chatgpt web???

Why not? It makes less mistakes and with subscriptions it's very cheap

Stuff along the lines of implement controller service and tests for the following endpoints:

- list of many endpoints with the JSON they receive and return and description of what they need to achieve

Stuff you could probably do in a single work day if you lock in and enter flow state, but in a typical job takes like half a week. And the vast majority of times the AI one shots it with no bugs, where I would have copy paste errors or dumb stuff I'd need to fix before it's shippable.

Your prompts are probably very underspecified then. Frontier models one shot the majority of my prompts. UI is kind of the exception, there I do have to ask for a lot of tweaks.

I think pi handles it better

Anything you do right now? A typical 10 minute prompt "simply" becomes about 7 hours long. (40t/s vs 1t/s).

I hate so much how every food menu is now AI slop. I wish that was outlawed under false advertising.

At 1t/s it's still faster than humans for a lot of tasks, basically doing overnight what could take humans half a week. Plus you can always parallelize.

The amount of goalpost moving is insane. "Yeah it can solve Millenium problems, but can it do it with nothing more than a one sentence prompt?"

Also there are proofs where the only human steering was "keep going".

Fields that allow verification, like math, will far surpass human level because they don't need human data for training. It's exactly the same as with Chess

The stochastic parrots have done it again!

Mistral models are way worse than Chinese models in the real world. It's not benchmarks.

Yes and no. It means the system is pushed away from a macroscopic theory into one where molecular effects matter. So it's not that you'd get infinite velocities in the real world, but you might get significant real world behavior that is not described by the macroscopic theory.

Kinda surprised they didn't get a single sale for some of those. I think it probably looked too much like AI slop so customers refrained.

I use the $100 which currently doesn't have the 5h limit.

The 5h limit hurts the most on the $20 plan because the limit is already very small (5h is ~15% of your weekly).

5h limits are awful. It means it is literally unable to complete a large task.

A better approach if they want to balance the load is having higher usage or lower usage consumption at different times of day.

It is (uses way less tokens)

The problem is not photorealism. The SVG is outright dumb, its on the wrong side of the table, the table has fucked up geometry (its tilted) and many more minor flaws.