At the end the article links this gem, ping via avian carriers:
How Fast Does Claude, Acting as a User Space IP Stack, Respond to Pings?
61–70 of 70 posts
Re: How Fast Does Claude, Acting as a User Space IP Stack, Respond to Pings?
#62If you wonder why your Copilot subscription has new limits that you hit every few days, it's because of PhDs like Adam. Could Adam use a local model hosted on his own box? Probably yes. But he preferred to waste the service we all use just to produce a weak blog post that introduces absolutely no knowledge and serves no other purpose than to tell everyone that the author likes to waste resources and calls it "fun". >…
Don't hate the player, hate the game.
excuse me? this is a cop out used to justify heinous things done under capitalism
Re: How Fast Does Claude, Acting as a User Space IP Stack, Respond to Pings?
#63Earlier quoted context omitted.
I'm not angry, I'm just disappointed. Hating is just terminology I've used to reply to the parent poster. Personally I don't think hating anything will solve any problem. True, people send dumber stuff to LLM, but some of them have the decency not to brag about it. But if they brag, then the common sense I imagine would be to tell them they are currently conducting a shitty thing. Yet on HN over 100 people told him t…
Talking about "We have brains and don't offload your thinking" while admonishing someone because you think you would have used their tokens better is wild.
You've literally just used the same argument from the previous poster which was even addressed by me in my parent reply. Talking about not thinking!
Re: How Fast Does Claude, Acting as a User Space IP Stack, Respond to Pings?
#64Do some people still claim "LLMs are just dumb auto completers"? Because this seems to disprove that claim pretty convincingly?
Oh, they are. It's just that the harness around it is able to pick up the commands it "autocompletes" and runs them for you. LLM can't run anything, it never could.
What do you mean that the "harness ran the commands"?
It looks to me like the LLM "executed" the logic in pure output tokens, not by using any kind of external tool calls?
Re: How Fast Does Claude, Acting as a User Space IP Stack, Respond to Pings?
#65Modulo Anthropic messing with the model for load mitigation, I wonder how stable this result is. 1,000 pings, how many correctly ponged?
is pong an actual term? If so I might've found a CS term better than wyde (2 bytes)
I'll give you another one: In Japanese there is the (unserious) term "enbug" which is the opposite of debug.
Re: How Fast Does Claude, Acting as a User Space IP Stack, Respond to Pings?
#66Earlier quoted context omitted.
Oh, they are. It's just that the harness around it is able to pick up the commands it "autocompletes" and runs them for you. LLM can't run anything, it never could.
What do you mean that the "harness ran the commands"? It looks to me like the LLM "executed" the logic in pure output tokens, not by using any kind of external tool calls?
Right, I mean that the logic of creating the packet was in the output tokens, sure. But the actual sending of the packet was done by bash command.
Re: How Fast Does Claude, Acting as a User Space IP Stack, Respond to Pings?
#67Wouldn't this be faster with an agent skill that has code? /skill-creator [or /create-skill] Write an agent skill with code script(s) that use an existing user space IP library that works with your agent runtime, to [...] ComposioHQ/awesome-claude-skills: https://github.com/ComposioHQ/awesome-claude-skills anthopics/skills//skill-creator/SKILL.md: https://github.com/anthropics/skills/blob/main/skills/skill-... /.agen…
Well, yeah, of course it would be. Even faster would just to be use code in the first place!
But why would you use tokens instead of using the LLM to call code for this?
The minimum overhead to doing it with the LLM is the useful question
Re: How Fast Does Claude, Acting as a User Space IP Stack, Respond to Pings?
#68Earlier quoted context omitted.
What do you mean that the "harness ran the commands"? It looks to me like the LLM "executed" the logic in pure output tokens, not by using any kind of external tool calls?
Right, I mean that the logic of creating the packet was in the output tokens, sure. But the actual sending of the packet was done by bash command.
Sure, we agree there.
But it seems to me that if the LLM can effectively "execute" the instruction of how to take an input IP packet and generate a response IP packet based on a set or rules, then that's effectively a general purpose processor. And not an "auto completer", right?
Re: How Fast Does Claude, Acting as a User Space IP Stack, Respond to Pings?
#69Earlier quoted context omitted.
Right, I mean that the logic of creating the packet was in the output tokens, sure. But the actual sending of the packet was done by bash command.
Sure, we agree there. But it seems to me that if the LLM can effectively "execute" the instruction of how to take an input IP packet and generate a response IP packet based on a set or rules, then that's effectively a general purpose processor. And not an "auto completer", right?
That's one way to look at it, but you're right - taking "autocompletion" to the extreme, we arrived at a task executor.
Re: How Fast Does Claude, Acting as a User Space IP Stack, Respond to Pings?
#70Earlier quoted context omitted.
Sure, we agree there. But it seems to me that if the LLM can effectively "execute" the instruction of how to take an input IP packet and generate a response IP packet based on a set or rules, then that's effectively a general purpose processor. And not an "auto completer", right?
That's one way to look at it, but you're right - taking "autocompletion" to the extreme, we arrived at a task executor.
To me, "autocompletion" means a pure lookup function input->output.
That's a lot different from "general purpose processor which can act based on program logic, stored data, and input data".