HumanOstrich

> Forcing it to be concise doesn't work because it wasn't trained on token strings that short.

This is a 2023-era comment and is incorrect.

> things start to get weird

> just look at research papers

You didn't add anything other than vibes either.

So you think the answer is replacing a requirement for a 6-digit 2FA code that can be typed into the npm publishing CLI with a requirement for a device that has a camera that can scan a QR code and then... what? What does the QR code do on the device? How does the npm CLI present the QR code?

None of your solutions seem useful in this case, especially a $150 hold. Site-wide rate limiting for payment processing? Too complicated, high-maintenance, and easy to mess up.

You can't block 100% of these attempts, but you can block a large class of them by checking basic info for the attempted card changes like they all have different names and zip codes. Combine that with other (useful) mitigations. Maybe getting an alert that in the past few hours or days even, 90% of card change attempts have failed for a cluster of users.

Stop posting AI slop, especially slop pull requests like the one you made to OpenClaw. Learn the first thing about a project you want to monetize and make fake contributions to. For example, OpenClaw is overwhelmed with slop PRs and the author has talked about this a lot.

Calm down. That kind of mania is for Twitter.

Where's the RSS feed? I'm not signing up for email newsletters.

Yea, it's pretty clear you're loudmouthed and an aggressively arrogant know-it-all (at least you think). You keep moving the goalposts too. First you're acting like they can't run models that don't fit in 44GB or 4x44GB. Then you say they can "only" run a larger model at 500 tps but that wouldn't be profitable.. Lol

Cerebras CURRENTLY serves GLM-4.7. I've used it through their API. Look up how big it is. 1,000-1,700 tps. https://www.cerebras.ai/blog/glm-4-7

Not interested in further conversation, so have a nice day! You can go ahead and get in the last word though.

How do you objectively measure if an LLM is training on something if you don't have access to its training data?

Trying to set up a prompt injection attack for someone accessing a repo with a coding agent is juvenile and pointless. And it doesn't deal with the training part.

Uh, the combined offering (smaller model + ~800 tps on cerebras) is nothing like the previous mini offerings, and you're hallucinating details about their process of creating it.

Read more about how Cerebras hardware handles clustering. The limit is not 44 GB or 500GB. Each CS-3 has 1,200 TB of MemoryX, supporting up to ~24T parameter models. And up to 2,048 can be clustered.

Not if you're suggesting that "(served by Cerebras)" should be part of the name. They're partnering with Cerebras and providing a layer of value. Also, OpenAI is "serving" you the model.

We don't know how they integrate with Cerebras hardware, but typically you'd pay a few million dollars to get the hardware in your own datacenter. So no, "served by Cerebras" is confusing and misleading.

Also "mini" is confusing because it's not analagous to gpt-5.1-codex vs gpt-5.1-codex-mini. Gpt-5.3-codex-spark is a unique, _experimental_ offering that doesn't fit the existing naming suffixes.

I don't understand what's wrong with "spark". It's friendly and evokes a sense of something novel, which is perfect.

If you want to know more about the model, read the first paragraph of the article. That information doesn't need to be hardcoded into the model name indefinitely. I don't see any "gpt-5.3-codex-nvidia" models.

Ouch, at least it fesses up. I ran into problems with it first refusing to use git "because of system-level rules in the session". Then later it randomly amended a commit and force pushed it because it made a dumb mistake. I guess it was embarassed.

I don't think everyone should assume that AI is the answer to all questions. I was asking the person I replied to, thanks.

It's been around for almost 15 years and stable enough for several providers to roll it out in production the past 10 years (GCP and Azure in 2017).

AWS is just late to the game because they've rolled so much of their own stack instead of adapting open source solutions and contributing back to them.

> Firecracker and microVMs are good use-case.

Good use-case for what?

Not sure what you mean. It IS the same model, just a smaller version of it. And gpt-5.3-codex is a smaller version of gpt-5.3 trained more on code and agentic tasks.

Their naming has been pretty consistent since gpt-5. For example, gpt-5.1-codex-max > gpt-5.1-codex > gpt-5.1-codex-mini.

Yea it's been butchering relatively easy to moderate tasks for me even with reasoning set to high. I am hoping it's just tuning that needs to be done since they've had to port it to a novel architecture.

If instead the model is performing worse due to how much they had to shrink it just so it will fit on Cerebras hardware, then we might be in for a long wait for the next gen of ginormous chips.

Give Pi[1] a try. Comes pretty barebones out of the box, yet still provides a decent default experience. Extension points are all TypeScript if you want. There are a lot of examples[2] and some 3rd party extensions[3].

I'll point out that if you want permission prompts for certain behavior, you have to add that yourself. There's at least one example.

Edit: Just noticed the article's author is using a fork of Pi.

[1]: https://shittycodingagent.ai/

[2]: https://github.com/badlogic/pi-mono/tree/main/packages/codin...

[3]: https://github.com/nicobailon

Well that's the best reply I've seen to someone being cranky on the Internet. I'm not even mad.

Take care.

Why did you quote yourself at the end of this comment?

Claude Code CLI 2.1.39 released a few hours ago fixes the problem. They didn't note it in the changelog though. Seems like a significant bug fix. ¯\_(ツ)_/¯

I think re-indexing all my drives every time it runs is even worse.

I used this for a while. What I don't like is that it updates its database by creating an entirely new copy and then deleting/renaming. For me that meant a several-hundred-MB file was being unnecessarily rewritten on a regular basis. It's a rather excessive waste of resources and not a polite thing to do when a lot of people have SSDs now.

I uninstalled it for that reason.

I'm on v2.1.37 and I have it set to auto-update, which it does. I also tend to run `claude update` when I see a new release thread on Twitter, and usually it has already updated itself.

Also if they bundled the documentation for the version you're running it would have fewer problems due to version differences (like stable vs latest).

Good to know it works for some people! I think it's another issue where they focus too much on MacOS and neglect Windows and Linux releases. I use WSL for Claude Code since the Windows release is far worse and currently unusable do to several neglected issues.

Hoping to see several missing features land in the Linux release soon.

I'm also feeling weak and the pull of getting a Mac is stronger. But I also really don't like the neglect around being cross-platform. It's "cross-platform" except a bunch of crap doesn't work outside MacOS. This applies to Claude Code, Claude Desktop (MacOS and Windows only - no Linux or WSL support), Claude Cowork (MacOS only). OpenAI does the same crap - the new Codex desktop app is MacOS only. And now I'm ranting.

Yep, and their documentation AI assistant will egregiously hallucinate whatever it thinks you want to hear, then repeat itself in a loop when you tell it that it's wrong.

That's not a thing, at least not in my installation of Claude Code.

I beg to differ, and so do a lot of other people. But if you're locked into this mindset, I can't help you.

Also, Codex isn't a model, so you don't even understand the basics.

And you spent "several hours" on it? I wish I could pick up useful skills by flailing around for a few hours. You'll need to put more effort into learning how to use CLI agents effectively.

Start with understanding what Codex is, what models it has available, and which one is the most recent and most capable for your usage.