News for hackers. Stuff that matters.

A comment on OpenAI Charges by the Minute, So Make the Minutes Shorter. Parent comment

Re:OpenAI Charges by the Minute, So Make the Minutes Shorter by swyx on Wednesday June 25, 2025 @04:07PM (#44381352)
> I didn't look at all at the quality of the transcription by feeding it the shorter version.

guys how hard is it to toss both versions into like diffchecker or something haha youre just comparing text

[ Parent | on HN ]
Re:OpenAI Charges by the Minute, So Make the Minutes Shorter by TimorousBestie on Wednesday June 25, 2025 @05:41PM (#44382070)
Why use diffchecker when there’s a perfectly good LLM you could ask right there? lol
[ Parent | on HN ]
Re:OpenAI Charges by the Minute, So Make the Minutes Shorter by serf on Wednesday June 25, 2025 @07:28PM (#44382758)
because a lot of LLMs will just eat tokens to call a diffchecker.

really it becomes a question of whether or not the friction of invoking the command or the cost of tokens is greater.

as I get older and more rsi'd the tokens seem cheaper.

[ Parent | on HN ]
Re:OpenAI Charges by the Minute, So Make the Minutes Shorter by trashchomper on Wednesday June 25, 2025 @08:54PM (#44383232)
Assuming sarcasm but if not, because deterministic vs. nondeterministic output?
[ Parent | on HN ]
Re:OpenAI Charges by the Minute, So Make the Minutes Shorter by TimorousBestie on Wednesday June 25, 2025 @10:57PM (#44383836)
Not sarcasm, just a little joke. I thought the emote at the end would prevent it from being taken seriously. . .
[ Parent | on HN ]
Re:OpenAI Charges by the Minute, So Make the Minutes Shorter by Der_Einzige on Thursday June 26, 2025 @11:20AM (#44388267)
Make it semi deterministic with structured/constrained generation!
[ Parent | on HN ]