You have to apply (and they presumably need to approve).

It's probably indicative of a less predatory model, but CF got a ton of mindshare by offering their free tier. I do basically nothing in the frontend space, but I default to CF because I'm used to using it due to using the free tier for personal projects.

Is there any open model that can emulate the agentic experience you get with Opus 4.7?

GLM 5.1 gets close to 4.6. It can happily run for hours and achieve a result. It given it bugs like a race condition that lead to a count being out by 1 after millions of operations, somewhere in a hundred thousand lines of C code littered with locks and atomic swaps, and it found (as did Opus). Most other models can't.

I'm using Fable now and GLM 5.1 doesn't really compare. But it's literally 1/20 the price. I can't use Fable for coding - it's too expensive. So now we have three levels of models - lightweight ones you dispatch en masse to find things, ones capable of agentic coding tasks that can run for hours like Opus, and GLM (and possibly open source ones - I've only tried a few), and now Fable, which is a truly helpful "architecture buddy". Fable still makes many, many, mistakes, so you have to review every word it writes.

Not yet that I've tried, and I'm pretty systematic about test driving them.

I keep https://sql-benchmark.nicklothian.com/#all-data up-to-date with latest releases and try out most that score 24+.

GPT 5.5+ or Opus 4.6+ are the only things I find useful like this. Notably Gemini isn't useful in this way.

I'm not in HFT, but I assume this is also an interesting applicable domain?

The author actually works at Jane Street.

Yes, definitely: this type of work is applicable in domains where software run on general-purpose processors cannot meet latency or power requirements.

On topic of hidden files: wherefrom is the pattern of treating configuration files as hidden? I'm referring to the pattern of `.configfile` -- I mean, for code projects, a local config file is a first-level construct. This leads to hidden files being not being a viable construct, as there is no longer any consensus on what should be hidden.

I don't know the answer to this, but I have to wonder if, for source files specifiically, .git is the culprit here... It's not part of your project, it's part of your repo. Which maybe makes sense if people ever divorced their source code from the repo but that's not a thing anymore. Others probably just copied it.

Is this poor man's Nix/direnv, or does it do anything else?

I'm wondering who's paying for this. Is it becoming a part of the iCloud subscription? A separate billed product?

Why was this posted to HN? What an utter waste of time. Someone's slopwriter writes a slop article about which slopper slops the most slopulicious slop. Comments agree it's a bogus "study". We need some gate on AI-written articles. It's so weird that AI-written comments are not permitted, while the front page can be occupied by stuff like this.

That's precisely the issue, the power dynamic needs to flip. The state of USA and more worryingly the direction it is in is horrifying.

What? What LLM were you using a decade ago? Am I misreading you?

You might not be aware of it but GenAI predates OpenAI which was founded more than 10 years ago anyway.

Of course I am aware, but how is this relevant today? How does that prove that the science is irrelevant and wasted?

Did I say that the science is irrelevant and wasted?

No. GenAI means LLMs right now. I agree it didnt in the past, but definitions change.

There's a favourite button for comments if you click the timestamp.