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

I burned all my tokens researching how to save tokens

quesma.com

Post reply on HN
Print view View original

151–160 of 237 posts

Re: I burned all my tokens researching how to save tokens

#151

Post by aytigra »

dominotw wrote: post #39
stavros wrote: post #33

Earlier quoted context omitted.

Whenever I've answered this question, the reply was always "this is shit", so I don't bother now. Bad faith questions just shouldn't be answered.

shipped = paying real users ( or a non profit with users) doesnt matter what subjective opinions are. shipped is not pushing something on github.

Many very well made software written without any AI was never "shipped" because there were no people who wanted to pay for it, many very poorly made software was shipped because demand and marketing did the job.

So evaluating software by "shipped or not" is just useless.

Re: I burned all my tokens researching how to save tokens

#153

Post by Schiendelman »

dominotw wrote: post #30
resonious wrote: post #20

Earlier quoted context omitted.

Trust me there are plenty of us using cloud AI to actually ship stuff. We just aren't writing blog posts about it.

what did you ship?

I've shipped (to TestFlight) a fairly fun video game that's tricking my friends into working out: https://reverdure.yourstrategy.co

Re: I burned all my tokens researching how to save tokens

#154

Post by spike021 »

camgunz wrote: post #54

TFA says "no hallucinations" but you can't fix hallucinations with rules or other models. I know I'm screaming into the void but whatever.

I can't remember who it was I spoke to recently, but it was some startup for doing code reviews. So I asked how they're handling larger diffs and especially when a code change is related to something requiring knowing a lot of context. Will it hallucinate things that make the review low-quality, etc. I was told "no it's been given guardrails to prevent hallucinations. it doesn't hallucinate." but I was thinking, that's not really how LLMs do or do not hallucinate, is it? (I'm not an AI person so I really don't know).

Re: I burned all my tokens researching how to save tokens

#155

Post by fc417fc802 »

inigyou wrote: post #127
nojito wrote: post #124

Earlier quoted context omitted.

Correct. We were chronically understaffed and now we are able to actually breathe and can argue that we are finally right sized.

So far you have provided no evidence of achieving more results with less effort. You've only said that you can write more lines of code (effectively) and that your coworkers are happier

I have to wonder what sort of evidence you would accept? Because it seems to me that the original question was answered clearly enough and now the goalposts have shifted to demanding evidence that the answer wasn't falsified.

Re: I burned all my tokens researching how to save tokens

#156

Post by zombot »

xyzsparetimexyz wrote: post #11
bob1029 wrote: post #7

Simply starting in the right part of the search space is the biggest predictor of success. The best way to save tokens is to start out the deep research pass with cheap models and then funnel the findings through increasingly powerful models. I've got a pipeline right now that uses all 3 of the gpt-5.6 model variants to address each stage of the process. If you are using models like sol or terra to generate hypotheti…

Couldn't someone build an adaptive system, where the llm is frequently judging the difficulty of a task and switching to a more/less powerful model?

And while you're at it, solve the halting problem.

Re: I burned all my tokens researching how to save tokens

#157

Post by zombot »

bob1029 wrote: post #7

Simply starting in the right part of the search space is the biggest predictor of success. The best way to save tokens is to start out the deep research pass with cheap models and then funnel the findings through increasingly powerful models. I've got a pipeline right now that uses all 3 of the gpt-5.6 model variants to address each stage of the process. If you are using models like sol or terra to generate hypotheti…

So did you find out how to save tokens yet, or are you still spending tokens on the search for the answer?

Re: I burned all my tokens researching how to save tokens

#158

Post by seanmcdirmid »

dofm wrote: post #12

It sometimes feels to me that cloud AI providers have convinced people that cloud AI is worth it because of all the ways people have been able to use cloud AI to write blog posts about using cloud AI to make cloud AI more efficient for something that they haven't shipped yet and aren't really ready to talk about.

People busy building shippable things are generally too busy to blog about it. It is selection bias in its most classical meaning.

Re: I burned all my tokens researching how to save tokens

#159

Post by seanmcdirmid »

camgunz wrote: post #54

TFA says "no hallucinations" but you can't fix hallucinations with rules or other models. I know I'm screaming into the void but whatever.

You can reduce hallucinations with appropriate grounding checks. You can’t really get rid of them though, so feedback loops with verification are essential.
Post reply on HN