HumanOstrich

That's a different problem and not really relevant to OpenClaw. Also, your issue is primarily a skills issue (your skills) if you're using one of the latest models on Claude Code or Codex.

Huge models? First you have to spend $5k-$10k or more on hardware. Maybe $3k for something extremely slow (<1 tok/sec) that is disk-bound. So that's not a great deal over batch API pricing for a long, long time.

Also you still wouldn't be able to run "huge" models at a decent quantization and token speed. Kimi K2.5 (1T params) with a very aggressive quantization level might run on one Mac Studio with 512GB RAM at a few tokens per second.

To run Kimi K2.5 at an acceptable quantization and speed, you'd need to spend $15k+ on 2 Mac Studios with 512GB RAM and cluster them. Then you'll maybe get 10-15 tok/sec.

How much extra power do you think you would need to run an LLM on a CPU (that will fit in RAM and be useful still)? I have a beefy CPU and if I ran it 24/7 for a month it would only cost about $30 in electricity.

No

Edit ~/.claude/settings.json and add "effortLevel": "medium". Alternatively, you can put it in .claude/settings.json in a project if you want to try it out first.

They recommend this in the announcement[1], but the way they suggest doing it is via a bogus /effort command that doesn't exist. See [2] for full details about thinking effort. It also recommends a bogus way to change effort by using the arrow keys when selecting a model, so don't use that either.

[1]: https://www.anthropic.com/news/claude-opus-4-6

[2]: https://code.claude.com/docs/en/model-config#adjust-effort-l...

If we want to make it extremely complex, wasteful, and unusable for 99% of people, then sure, put it on the blockchain. Then we can write tooling and agents in Rust with sandboxes created via Nix to have LLMs maintain the web of trust by writing Haskell and OCaml.

This is irrelevant to the article and discussions here. Weird copypasta bullet points too.

Bluesky also randomly bans new accounts saying they violated the ToS. Like right after signup before you do anything. It says you'll receive an email with details (never happens) and offers a form to appeal. The form goes nowhere and you never hear anything again. This happened to me a couple months ago so it's probably still an issue. It seems more like sloppy, careless engineering than malice, however.

You can tell it not to do that and it will show inline diffs.

I think your problem is you don't seem to be aware of history before 1967 or society outside of the US. Your local community college might offer some courses in history and sociology.

It's more like following astrology - entirely irrelevant to reality.

I tried Cerebras with GLM-4.7 (not Flash) yesterday using paid API credits ($10). They have rate limits per-minute and it counts cached tokens against it so you'll get limited in the first few seconds of every minute, then you have to wait the rest of the minute. So they're "fast" at 1000 tok/sec - but not really for practical usage. You effectively get <50 tok/sec with rate limits and being penalized for cached tokens.

They also charge full price for the same cached tokens on every request/response, so I burned through $4 for 1 relatively simple coding task - would've cost <$0.50 using GPT-5.2-Codex or any other model besides Opus and maybe Sonnet that supports caching. And it would've been much faster.

Looking at it through a religious lens is pretty narrow-minded. Secular people have values too. You're limiting your ability to understand the world around you.

As slow and buggy as Photoshop is, an incredibly fast superhuman AI couldn't get much done in 5 minutes or even 5 hours.

In general I agree with you, just not at the extreme.

Did YOU even bother to look at their site? They support more than static generation, including SSR and even API endpoints. That means Astro has a server that can run server-side (or serverless) to do more than static site generation, so it's not just a static site generator either.

And yes I can see you're posting the same lie all over the comments here.

Stop being a potty mouth.

So something like "now that we own Astro, all of you using Netlify should start migrating to Cloudflare Pages"?

Astro isn't just a static site generator either. Not sure what your point is.

Why did you expect info about deploying Astro to Cloudflare Pages? It's been supported for a long time already.

The same ways Vercel makes it harder to deploy Next.js sites to competitors or for self hosting.

We're currently discussing the cost of _storage_, and you can bet the providers already are deduplicating it. You just don't get those savings - they get increased margins.

I'm not going to quote the article or other threads here to you about why reducing storage just for the sake of cost isn't the answer.

What do you mean by "not all"? They aren't obligated to block every tool/project trying to use the private API all the way to a lone coder making their own closed-source tool. That's just not feasible. Or did you have a way to do that?

Nope, you can't just look at cost of storage and try to minimize it. There are a lot of other things that matter.

That's already pretty common, but the goal isn't storing less data for its own sake.

Yes, but Claude Cowork isn't just an LLM. It's a sophisticated harness wrapped around the LLM (Opus 4.5, for example). The harness does a ton of work to keep the number of tokens sent and received low, as well as the context preserved between calls low. This applies to other coding agents to varying extents as well.

Asking for the trace is likely to involve the LLM just telling the harness to call some tools. Such as calling the Bash tool with grep to find the line numbers in the trace file for the command. It can do this repeatedly until the LLM thinks it found the right block. Then those line numbers are passed to the Read tool (by the harness) to get the command(s), and finally the output of that read is added to the response by the harness.

The LLM doesn't get a chance to reinterpret or hallucinate until it says it is very sorry for what happened. Also, when it originally wrote (hallucinated?) the commands was when it made an oopsy.

So.. He has no backups?

Claude Code is smart enough to search its session traces and give you the real info.

You just repeated what I said in a different way. It is accessed differently, but it's still going to go through the same APIs at Anthropic. Maybe they have some differences or use different endpoints, but Anthropic didn't duplicate their entire business for CC vs official API users.

Edit: I appreciate the reply that we're probably on the same page.

You're just parroting what you've heard. The reality of continuing an abandoned project is not that simple.

That's not MIT-compatible, it's the opposite. MIT-compatible would mean that code under your license could be relicensed to MIT. Similar to how the GPL is not MIT-compatible because you cannot relicense GPL code under MIT.

How do you think Claude Code and OpenCode communicate with Anthropic? Through the API. Maybe it's accessed slightly differently for subscription users. Anthropic is saying you can't use the API via a subscription anywhere you want. Only Claude Code can use it that way.