b--l

Agreed--if you can catch them of course.

I need to stop using this website.

It's one of claude models.

We've seen it a lot so it' become extremely grating to us. And it's always the same speech patterns.

I really can't stand it. I don't even think it's intentional from anthropic.

Codex is one of the most infamous examples of slopware. Just having the window unhidden on my mac will cause it to use 100% of the GPU displaying the spinner message.

THE SPINNER MESSAGE CAUSES 100% GPU USAGE ON AN MBP M5!!

So any time you're waiting on the model (which is 90% of the time), your fans will be blasting (careful, don't use it on battery).

The issue is on github and close to 6 months old. Probably since the release of vibe coded junk. I would literally fix it myself but it's closed source for whatever reason.

There are many discussions about which model is better, or if vibe coding is even possible. I point you to the extent of what one of the most well funded, money flush, well staffed model making companies can do with vibe coding.

To me a screwup this bad (where the CEO has already made it clear they're now "focussing on coding") indicates that there's something truly broken in the company. No one on polymarket expects them to have a leading model any time soon for example.

It's a tragedy. The world needs competition to anthropic.

It's because they use gpt-5.5-xhigh (the money making* model) to build it.

(*for them)

I doubt it. It's a shit a model.

The constitutional right to bare LLMs.

Ooohh yeah. I forgot completely about that naked shameless bribe.

That one was even more overt than the plane.

The last Opus models were money models--as in designed to make them money.

It will be interesting to see. If you look at the GDPR fines record (well at least the last time I did) spain stands out for its frequency and size of fine.

`qwen-35b-3a` is really garbage (I know well because it's what I run locally). What quant are you running? Would people really pay $6 a month for it even if unlimited?

That said, nice looking site and wish you the best for getting it off the ground.

A huge win for china. No one is going to forget this. Every single developer will remember this weekend and be pissed off. I'm sure it's a huge wakeup call for any dev that was asleep and not bothering with open source models.

There is not a single chance this would have happened under that admin. Not one single chance.

I found it tripped in most laughable situations by mere were words that could be related in some way to hacking but are in common use in programming. I would have to go back, examine my prompt for word that could be use in another context and replace it with a synonym.

Just speculating but I "feel" 4.7 was post-trained using more synthetic techniques. The way it writes for one thing, it's "personality", is less human and more fatiguing-AI-slop like.

Thank you for the gold kind stranger.

If you assume he is being blackmailed then it makes sense. On any other level it does not.

grok-4.1-fast is the the number 2 model on this benchmark.

~~If you've used this model in real life to do any sort of programming, and have seen its output, you would know that there is something VERY wrong with your benchmark.~~

Edit: Oh sorry, I looked at the questions, I see this is also for SQL specifically. Interesting. Maybe they tuned that grok model for SQL. Cool site. I bookmarked it.

If we learned anything from the code leak is that they essentially do not know what is in the blackbox of the code for that 500k line mass. So that's plausible.

"but most of our samples are from the last 2 months."

There's your major issue. That's well within the brutal quantization window.