671–678 of 678 posts
Earlier quoted context omitted.
I don’t remember that and I was there! The idea that the performance delta between Apache and nginx for any normal workload is anything like 20,000% is absurd.
Absurd indeed. Apache httpd server got MPM support two years before nginx was released.
Earlier quoted context omitted.
I was afraid my description sounded like agents, and it kind of is, but not like most implementations. Most use a “boss bot” to craft a prompt/system message and launch the model, and sometimes they redo it every time it launches the agent. It’s a low effort attempt that’s immediately flawed because it uses LLM output for LLM input. It can look like it’s working for some time, but the perplexity guarantees it’s a rol…
>Run the same exact prompt 100x in a single step test (one prompt, one response), hash the full responses, and you’ll see 10-50+ unique responses. The higher the unique the worse your prompt; focus on the system. A highly tuned system prompt will result in one response, even at a temperature of 1.0. Really. Once that’s done that’s the only thing it does and it’s the only one that does it and it never changes. Other L…
Couple tips:
A first pass is to blank out the system prompt, add only one tool, and work to reduce the thinking length for a direct function call prompt. “Read archive.log” should result in roughly 0 length thinking. If it’s thinking about anything, especially if it mentions {readfile tool}, rename the tool and minimize the description. Depending on the model it might always output thinking, so run it until you get a consistent outlier that’s far lower thinking length than the others. It’ll be obvious when you find it. Repeat the prompt dozens of times, modify it slightly, and focus on the lowest max length, not average.
You should really use a Claude with Python (or similar preferred) to make API calls to the LLM and have it iterate through hundreds of names/descriptions and return only len(thinking). Have it build a batch testing harness to run a dozen tests at a time, that helps keep it from ‘cheating’ to finish. laziness = count(messages), but frame it as an academic research project studying the effects of minimalist tool descriptions on thinking length. Don’t set the goal as minimal thinking length, Claude will short circuit it.
Remove all other tools until {readfile} is perfected, then add/test the next tool. Btw: you don’t need to describe readfile() when it’s named right.
The built-in tools[] makes that hard because it tacks a really dumb system prompt on at the server and requires some length of description, which is why I built my own function calling, but that’s still a good first pass. Focus almost entirely on the function name itself; readfile, readFile, read_file, readlines, file_get_contents, etc., and make the description just “Operational” or similar. Field description, if required by API, is literal “filepath”, same as field itself. Lowercase, nothing else said. Minimize your contribution to perplexity, use standard naming conventions.
When you add a second tool you need to still include the first tool prompt in the second tool testing. Adding {writefile} can absolutely break {readfile}. Have Claude run the tests and build it out into permanent testing module with file_read=[prompts], file_write=[prompts], making it easy to extend, and full_test() that runs them all to see if a new addition broke it.
Add your system prompt back in and probably watch the tests go to shit. Start with nothing and slowly work up. Focus on positive action framing, not negating: “Your responses are always..” and not “Do not…”
It sounds like a pain, but building the systems to automate the tests IS the infrastructure, everything you have it do afterwards is just the tasks.
That was longer than I planned, but I guess this’ll be a comment for future generations to find.
Earlier quoted context omitted.
> but way, way better at creative writing than Qwen and even better than Gemma 4 26 and 31b. I suspect this is the only use-case I would consider...and I don't really have a use-case for "creative writing" that I would delegate to an LLM. I suppose for dialogue generation in games? But yes, hard agree. Why on Earth would you ever want to write code with a model that is supposedly "jailbroken"? So it can put great bac…
> I suppose for dialogue generation in games? I use it to write short sci-fi stories. Life is not only about being an SDE. > Why on Earth would you ever want to write code with a model that is supposedly "jailbroken"? I need a model which decent enough at coding to write boilerplate for me, yet I do not need to unload in case I want to write an article or enguage in my writing hobby.Exactly why Gemma 4 are so popular…
What you do in the privacy of your own home is none of my business, but I would hope you don't inflict those stories on others.
Earlier quoted context omitted.
> America is becoming increasingly oligarchic and corrupt with decades of experience of companies profiting off harming people and lying through their teeth and Meta is like one of the worst offenders. Isn't China a single-party state that is run by a corrupt autocrat, has literally enslaved people to build products, and disappears people for saying the wrong things? If America is becoming more like China, shouldn't…
I say China is not starting any wars, you gesture at some vague "not behaving nicely" as if this is equivalent to a war or some damning proof that they will start a war - these are nowhere near the same thing. China has killed maybe 50 people outside it's borders since 2000. The US has killed 100,000-250,000 in that time period. There is no amount of rationalization that can reverse the deaths of those people or the…
Well I just pointed out that just because they haven't started any new wars, and obviously they haven't been in a position to start anything new in recent memory doesn't mean they can't or won't, and we also shouldn't excuse their belligerence toward their neighbors in the South China Sea. Nobody is forcing them to ram their boats into Filipino fishing vessels, for example.
> The US has killed 100,000-250,000 in that time period. There is no amount of rationalization that can reverse the deaths of those people or the cities turned to rubble.
Well if you want to play this kind of numbers game China in the last 100 years has killed tens of millions so really they're the bad guys. You just have a recency bias.
But to engage with your point in a different way, China also has not been a factor on the world stage until recently (I mean over the last couple of hundred years or so) and they, like other nations, rely on the United States to maintain peace and order to the extent the US is able to. In other words, stop criticizing the man in the arena.
> Same thing with literally kidnapping the president of another country.
Well he's a criminal, drug trafficker, and his actions and the actions of his predecessor resulted in 1/3rd of Venezuelans fleeing the country, a drastic reduction in economic growth, and more. Also just because you're the president of some country doesn't mean you get immunity. Otherwise, nobody can go arrest Vladimir Putin can they?
Second - the world doesn't exist in isolation. Just because some country isn't outright attacking you doesn't mean their policies can't cause you to take your own actions and at the end of the day, countries get to decide what they want to do because they are sovereign and then they live with the repercussions. Venezuelans aren't exactly upset about us removing their commie dictator guy either.
> I can tell you the prevalence of sports gambling and betting is exploding in Canada
Ok? Go ban the platforms. What does this have to do with anything?
> in that scenario, it's really just saying "yes we suck, but they suck more!" and that doesn't solve anything..
Ok stop criticizing the United States and just say we suck all the time. It doesn't solve anything. Frankly the only real reason my post had anything to do with China is because they're the only other country that currently matters in the AI race - and I specifically have a problem with folks and their arguments about who is "doing better" or "winning" that race. I was criticizing the strategy and criticism of that strategy which seems to only apply to the United States when in fact it does not. In other words they can release open weight models and so can we. They can take the lead and we can just release open weight models like they supposedly do to us.
Earlier quoted context omitted.
If I understand correctly, you're saying people are compute-poor but not necessarily GPU-poor because there's a lot of GPUs out there but nowhere to plug them into? If so, I'm not sure that distinction matters to the GP's point that there is too much demand to call this an oversupply. I also doubt we can estimate the level of demand based on a single deal between Anthropic and SpaceX (despite which, note, Claude stil…
> If I understand correctly, you're saying people are compute-poor but not necessarily GPU-poor because there's a lot of GPUs out there but nowhere to plug them into? If so, I'm not sure that distinction matters to the GP's point that there is too much demand to call this an oversupply. It's a distinction without a difference if your issue is getting hold of a GPU. But there's a significance to it if you are trying t…
Oh I think I recall this. However Satya said that more a year and a half ago, eons in AI time, and maybe he even believed it at the time. But since then Microsoft's annual CapEx spend has gone from $65B to $116B. Not the actions of somebody concerned about an overbuild.
> But there's a significance to it if you are trying to use demand for a GPU as a proxy for demand for AI. That is where the industry is making serious mistakes.
Ah I see what you're saying. The AI industry is certainly not looking at just GPU demand as a proxy for AI demand, primarily because they themselves are creating the GPU demand -- but that is in response to other signals they are getting. Actually that's what I hoped to illustrate with the rest of my analysis; rather than a hypothesis of what AI might be able to do, it was more a hypothesis of the signals the industry is looking at (including various economic data sources) that drive its current spending frenzy.
Earlier quoted context omitted.
Would be nice if there were a hn feature, userscript, or plugin to just filter comments from new accounts. Bonus if there was some sentiment analysis or llm-based analysis to filter out unsubstantiated inflammatory comments too.
The account we're discussing is from 2014. How much earlier do you want?
Earlier quoted context omitted.
I find Claude doing a lot of pointless confirmation at night when it will ask me about things that it would normally just do during the day. Frustrating to be like “do X overnight, don’t ask me for input” and come down to find it having worked for a few minutes and then stopped.
Doesn't setting the question auto-continue timeout before you go to bed fix that? https://code.claude.com/docs/en/tools-reference#question-aut...