Live data from Hacker News

Tokenmaxxing is dead, long live tokenmaxxing

12gramsofcarbon.com

221–230 of 315 posts

Re: Tokenmaxxing is dead, long live tokenmaxxing

#221
post #207

Earlier quoted context omitted.

> The logic of buying the tools then forcing the employees to use them "or else" is completely backwards in any sane world People are stubborn. A lot of productivity improvements had to be almost forced upon farmers, for example. Even when early adopters demonstrated the benefits, a decent fraction of them just didn’t want to change.

> People are stubborn. This is just a variant of the argument ”people don’t know what’s good for them”. You’re very close to the actual answer, which is that the aforementioned ”manager class” is simply convinced that they understand reality better than those below them, which is quite frankly absurd considering the fact that managers very rarely do any of the ”real work” that these tools supposedly make redundant, a…

Maybe multiple things can be true

Like when doctors insisted they didn't need to wash their hands (https://en.wikipedia.org/wiki/Ignaz_Semmelweis#Conflict_with...)

or "science advances one funeral at a time" (https://en.wikipedia.org/wiki/Planck%27s_principle)

Re: Tokenmaxxing is dead, long live tokenmaxxing

#222

The thing that most disconcerts me isn't the runtime pruning, it's the cold loading. Months ago, I added a few skills and MCPs to test them, partly in the frenzy of free shopping, but then I forgot about half of them. So after I got tired of choosing by hand, and therefore also a bit blindly, I created a small tool that runs locally and analyzes conversations to tell you which skills, MCPs, or other things are always…

[flagged]

Re: Tokenmaxxing is dead, long live tokenmaxxing

#223
post #190

Earlier quoted context omitted.

> Results are in Awesome, can you please share those results? Surely they would be all over Nature, Science, IEEE, etc.

Nature doesn't publish papers about water being wet either.

What? The basic properties of water are scientifically defined as best we can. There is mathematical proof that 1+1=2. Do you think science starts from nuclear physics or differential equations?

We couldn't build any of this stuff (rockets, LLMs, heart medicine) if the foundation was ill defined.

I think it's the second time I run into you like this, Temporal. I wish HN had a way to classify you as an "AI booster" or equivalent.

Re: Tokenmaxxing is dead, long live tokenmaxxing

#224

> Like, imagine if some serious business leader, like, idk, Mark Zuckerberg, decided to announce that Meta was going to burn money. Like ... pivoting to the "metaverse" and changing the company name to show he's serious.

It's astounding to me that they looked at Second Life and really thought that was the future.

Re: Tokenmaxxing is dead, long live tokenmaxxing

#225
post #77

Folks have been saying “things are different now, the agents are now compounding success instead of error” for at least a year now, but I just don’t see it. I was lucky enough to receive a weeklong $50k per head AI training from the people saying these things, and one of their few helpful concrete recommendations was to constantly clear context all the time, to avoid things going off the rails. However, I think findi…

50k per head training and the largest takeaway was to clear context.. that is the "hello world" of using agents, insane.

Re: Tokenmaxxing is dead, long live tokenmaxxing

#227
post #118
post #77

Folks have been saying “things are different now, the agents are now compounding success instead of error” for at least a year now, but I just don’t see it. I was lucky enough to receive a weeklong $50k per head AI training from the people saying these things, and one of their few helpful concrete recommendations was to constantly clear context all the time, to avoid things going off the rails. However, I think findi…

Even modern frontier models benefit so hugely from careful context pruning, maintenance, and rewriting to erase mistakes that it's astonishing to me that there are no tools centered around it. The one tool that used to have such a feature, Zed and its retroactively-named Text Threads, has now stripped itself of it.

this! the back-and-forth chat interface where you can edit only your own messages, and only then to get a new response, is a terrible one, but I think favored by vendors because it helps them fight in vain against prompt injection. Custom harnesses and stuff are nice but incredibly time consuming to set up when all I want to do is like, see what the agent is reading, and editing out some irelevant nonsense side quest it went on, or trim some massive log file it read which filled 90% of its context. Theres no inherent reason behind some caching gains that these things must be strictly chronological - a response it gave me previously does not have to be part of the context now

Re: Tokenmaxxing is dead, long live tokenmaxxing

#228
post #223

Earlier quoted context omitted.

Nature doesn't publish papers about water being wet either.

What? The basic properties of water are scientifically defined as best we can. There is mathematical proof that 1+1=2. Do you think science starts from nuclear physics or differential equations? We couldn't build any of this stuff (rockets, LLMs, heart medicine) if the foundation was ill defined. I think it's the second time I run into you like this, Temporal. I wish HN had a way to classify you as an "AI booster" or…

> What? The basic properties of water are scientifically defined as best we can. There is mathematical proof that 1+1=2. Do you think science starts from nuclear physics or differential equations?

Yes. There's a lot of interesting things science has to say about water, very specific claims that took a lot of effort to discover, precisely formulate, and reproduce.

We're not talking about those. The whole LLM discussion on HN, as well as in the wider industry, is still stuck at the state where a large (or vocal) group of people refuses to believe water is wet. Yes, there is a similar group that tries to sell water as miracle cure, I'm not denying it - IMO both perspectives are dumb and entirely detached from obvious observational evidence that you can collect for ~free at home in 15 minutes. Example will follow.

There exist the equivalent of foundational, detailed studies on LLMs, at every level of rigor imaginable (with a caveat, it's hard to rigorously prove anything useful in software engineering; it's still largely opinion-driven field). But they're not part of the overall "AI hypers/haters" dynamics.

> I wish HN had a way to classify you as an "AI booster" or equivalent.

You can take any of the LLMs and have it vibecode you a user script in under 5 minutes, than you then can paste into Greasemonkey/Tampermonkey, and voilà, you have me labeled as "AI booster" or filtered out.

In fact, let me help you, I'll time it. I opened chatgpt.com in incognito (to emulate being a rando free user), and put the following prompt in:

> I need a user script I can paste into Tampermonkey on my Firefox that will clearly label user named TeMPOraL with robot emoji and some silly emoji, so I never forget when reading their HackerNews comments that they're an unapologetic AI booster.

Got back this script in under 10 seconds: https://pastebin.com/akEchvHd. Tested it, works out of the box.

This is the promised empirical example. It doesn't prove everything, but it proves something, and it took, end-to-end, a total of 1 minute to perform just now. You can collect many such examples over a single day by just trying. People who keep saying AI is useless and a fad and can't do anything useful, obviously never bother with even that.

FYI: I'm not an AI booster. I like AI, and I find it useful, but I'm not going out of my way to boost it. I just enjoy this topic, but more importantly - and I remain consistent in this - I point out bullshit that doesn't agree with obvious observable reality.

EDIT: try the example yourself, and post whether it works for you too - if it does, it's technically a peer-reviewed, replicated study, but I doubt it'll convince any of the naysayers of anything.

EDIT2: I have plenty of negative things to say about LLM capabilities and how irresponsibly people use them, and I do occasionally write about this (mostly at work, these days), but most HN threads on AI are not on this level - not anymore. They used to be more reasonable back in GPT-4 days.

Re: Tokenmaxxing is dead, long live tokenmaxxing

#230
post #223

Earlier quoted context omitted.

What? The basic properties of water are scientifically defined as best we can. There is mathematical proof that 1+1=2. Do you think science starts from nuclear physics or differential equations? We couldn't build any of this stuff (rockets, LLMs, heart medicine) if the foundation was ill defined. I think it's the second time I run into you like this, Temporal. I wish HN had a way to classify you as an "AI booster" or…

> What? The basic properties of water are scientifically defined as best we can. There is mathematical proof that 1+1=2. Do you think science starts from nuclear physics or differential equations? Yes. There's a lot of interesting things science has to say about water, very specific claims that took a lot of effort to discover, precisely formulate, and reproduce. We're not talking about those. The whole LLM discussio…

LLMs are useful.

They're not "3-4 trillion dollars in investments over 5 years" useful, nor "crammed into the throat of every employee on the planet, regardless of their actual job" useful.

The way they are pushed right now will lead to a very hard crash and probably lots of suffering. Also, you need a more advanced prompt for Firefox on Android :-p

Post reply on HN