Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering

arxiv.org

Post reply on HN
Print view View original

91–98 of 98 posts

Re: Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering

#91

Post by saberience »

monkeydust wrote: post #50

I have a MA system setup for personal use. You give it a problem, you then refine that problem where a fast, cheaper model asks you questions which you answer to get a better input prompt. You then choose a MA strategy for example take problem break up to sections then final judge concludes or you do multi turn where agents debate then judge summarises debate. The best approach is what I call 'all angles' where all t…

The problem with these kinds of systems (they have been well studied), is that that the overall output is ultimately anchored to the dumbest models used.

I.e. you cannot end up having a more intelligent output by using more dumber models (that is: dumber than the most intelligent model used).

It's generally always best to refine your prompt and send it (at most) to the two smartest frontier models possible. And then have the smartest model review the output from the second smartest.

Re: Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering

#92

Post by deadbabe »

scotty79 wrote: post #54
deadbabe wrote: post #43

Earlier quoted context omitted.

I know how to drop a company’s token costs to zero: treat tokens as a utility same as internet and make engineers pay for it.

I would easily pay a lot of money to have access to AI for my job. I actually do pay. If the cost was significant I'd just add it to hourly rate that I consider acceptable. Company always pays in the end, because company is the only entity with money in this setup.

You will be undercut easily by someone running a cheaper LLM setup.

Re: Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering

#93

Post by monkeydust »

monkeydust wrote: post #78
monkeydust wrote: post #50

I have a MA system setup for personal use. You give it a problem, you then refine that problem where a fast, cheaper model asks you questions which you answer to get a better input prompt. You then choose a MA strategy for example take problem break up to sections then final judge concludes or you do multi turn where agents debate then judge summarises debate. The best approach is what I call 'all angles' where all t…

Right here is the video demo of what I built - https://streamable.com/e49cgt

Details and repo post on ShowHN here - https://github.com/monkeydust/rightmind

Re: Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering

#94

Post by sedatk »

altmanaltman wrote: post #64
sedatk wrote: post #21

One month I could use Github Copilot fully with no disruptions. The next month, after pricing changes, I’ve run out of tokens in two days. Such drastic changes tell me that pricing of tokens is arbitrary, and AI business is running out of money fast.

The github example is also a bit of an outlier because they made a recent change to their pricing so that's why its such a drastic jump. Also I mean prices in generally for all things are based on underlying factors, that doesn't make them arbitary (i.e. github executives using a random number generator for token pricing would be arbitary)

What I mean by arbitrary is that like raising bread prices from $5 to $50 kind of thing. That’s not a sign of cost-based pricing. It’s arbitrary.

Re: Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering

#95

Post by scotty79 »

deadbabe wrote: post #92
scotty79 wrote: post #54

Earlier quoted context omitted.

I would easily pay a lot of money to have access to AI for my job. I actually do pay. If the cost was significant I'd just add it to hourly rate that I consider acceptable. Company always pays in the end, because company is the only entity with money in this setup.

You will be undercut easily by someone running a cheaper LLM setup.

That depends entirely on how they and I are using tools available. There must be a sweet spot. Best person at finding that sweet spot wins on price. I'd be up for that.

Re: Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering

#96

Post by deadbabe »

scotty79 wrote: post #95
deadbabe wrote: post #92

Earlier quoted context omitted.

You will be undercut easily by someone running a cheaper LLM setup.

That depends entirely on how they and I are using tools available. There must be a sweet spot. Best person at finding that sweet spot wins on price. I'd be up for that.

It will trigger a race to the bottom. The sweeter the juice the better the squeeze.

Re: Tokenomics: Quantifying Where Tokens Are Used in Agentic Software Engineering

#97

Post by scotty79 »

deadbabe wrote: post #96
scotty79 wrote: post #95

Earlier quoted context omitted.

That depends entirely on how they and I are using tools available. There must be a sweet spot. Best person at finding that sweet spot wins on price. I'd be up for that.

It will trigger a race to the bottom. The sweeter the juice the better the squeeze.

Isn't that the entire point of the economy and the free market? Finding out how cheaply things can be done and doing them?
Post reply on HN