I'm a guy with vague knowledge on KVM - having only tinkered with it and briefly had a GPU pass-through setup 2 years ago.

I suggest putting the 'multiple guests at near-native speed' use-case in the opening paragraphs of the README.

Thank you for the feedback... i will do that

I would agree with the argument of Jensen that laws and regulation already exists for liability if he, as the parent company of HuggingFace, were to sue OpenAI for breaking the law.

Who and when better to fight it out and set a precedent then Nvidia and OpenAI right now?

6 months from now we'll be discussing if model training is assmaxxing.

I'm not sure the tokens can be compared like that between OpenAI/Anthropic.

When i swapped between a 200k Fable context into an Astra model (i was out of fable) the token usage in that context dropped to 150k or something.

Either there was a bug somewhere, or the same text got cut up very differently between providers.

That 50k was almost certainly accumulated encrypted reasoning tokens that would have been unreadable by astra.

Ah that makes sense.

Its vastly more likely these contain SSH keys of the VM - generated when the user first starts the machine, for just that machine.

It's not even running an SSH server unless you ask it to install one. It does seem to come with an SSH client by default and can of course generate its own keypair for that.

In what way?

Not sure whats the norm nowadays, but it used to be MCP descriptions were loaded in from the start.

In any case, to be cheaper the `cli --help` command needs to more noisy than the json description.

Finally, and the really big one: cli can be composed with `grep`, `jq` , etc.

I think the result is fine. The benchmark is silly to the point of being useless nowadays.

It used to be a mess in various interesting ways. Now, almost every big release can draw something perfectly functional.

So the question - without a correct answer - given the prompt "Generate an SVG of a pelican riding a bicycle":

Does the user want the least lines of code to make it functional, or the best looking version?

The user at the very least expects the bike to have bike geometry; Grok seems to struggle with that

exactly, the benchmark just needs to be downvoted into oblivion each times it's posted. The outcome is not deterministic and the model needs to determine what level of detail is appropriate for an svg. There is no wrong answer to this unless it's obviously un-Pelican-like.

Its indicative of a pattern of behavior where they want to upsell you into their ecosystem and keep you there.

They don't even allow alternative harnesses on their subscription model. (But they do allow a agent-sdk that can pretend to be a generic compatible endpoint the alternative harnesses can use).

If you like your stuff overengineered, gated, and over-priced then by all means.

Its not even wrong from Anthropic because it's the path to most profit.

I'll take the opinion of people who have strong opinions about mild inconveniences.

Between my goals and Anthropic's bottom line, i want my goal to win out without needless inconveniences.

These arguments have nothing to do with Claude supporting or not supporting AGENTS.md.

> Its indicative of a pattern of behavior

If you think I'm wrong, and these arguments have nothing to do with it, just tell us what explains Claude not supporting AGENTS.md.

Was it such a grand engineering challenge? Too many 'legacy' projects relying on both AGENTS.md/CLAUDE.md and that has recently changed?

I've made clear my belief on the reason behind it - branding decisions outweighing utility.

Add something to the thread by sharing your version of a 'more likely' decision process that led to the choice to only now support it.

not that i agree, but this is what an anthropic engineer said about this:

> Our reasoning for this was that we don't think that model families are interchangeable and the system prompt can have a big impact on performance.

https://x.com/trq212/status/2092302273099796842

Bad take. You should feel bad.

This kind of comment doesn't belong on hacker news.

But you do seem to get to host a https version of your app in case you need features locked behind secure context.

This is just wrong.

The overwhelming amount of expenses is for domestic products; lumber, food, services, rent, etc. Cheaper foreign shit isn't going to be meaningfully felt by the majority.

The part where the rich come in, is that the rich will disproportionally feel the upside of selling the fuel. The people on below average wage are just going to see prices rise and meager savings dilute, long before their wages grow.

Thats not to say the US isn't going to be well of as history's largest energy producer ever, but the reshuffling is going to be extremely painful for a majority of Americans.