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

Migrating a production AI agent to GPT-5.6: 2.2x faster, 27% cheaper

ploy.ai

Post reply on HN
Print view View original

51–60 of 144 posts

Re: Migrating a production AI agent to GPT-5.6: 2.2x faster, 27% cheaper

#51

Post by rsalus »

w4yai wrote: post #10
kristianp wrote: post #6

> Numbers like that buy a model a real migration effort. Such a silly choice of words. I wish the human directing the LLM writing the article put some effort into rewriting the worst examples of LLM style. > But it did extremely well, and the promise was immediate and specific: builds finishing in less than half the wall-clock time, at 27% lower cost, scoring at or above our incumbent on completed work. The way the L…

Can we get over the detective work about if the text was written by LLM or not in 2026 already ? This is a lost cause, and we could instead focus on substance over syntax.

the frustration is largely because the overall substance is quite poor since it is typically imprecise by nature.

Re: Migrating a production AI agent to GPT-5.6: 2.2x faster, 27% cheaper

#52

Post by bel8 »

gunapologist99 wrote: post #48
arikrahman wrote: post #9

Migrating my workflow to Reasonix with cache hits on Deepseek make requests practically free, and that's on unsubsidized American providers.

Sorry, what did that have to do with the article?

They also migrated and that also made the workflow cheaper.

It has everything to do with the article.

Re: Migrating a production AI agent to GPT-5.6: 2.2x faster, 27% cheaper

#54

Post by CookieCrisp »

justAnotherHero wrote: post #21
w4yai wrote: post #10

Earlier quoted context omitted.

Can we get over the detective work about if the text was written by LLM or not in 2026 already ? This is a lost cause, and we could instead focus on substance over syntax.

To me it's a useful signal not to read an article that someone didn't bother to write. Which is a shame as real insights are buried inside some of these articles, which if the author bothered to write in his own words could have reached an audience that would have appreciated them. Writing is one of the areas where I want no LLM involvement.

More often it's the difference between finishing something and not finishing it - so often LLM's are helping them reach an audience that would appreciate them, even if that audience doesn't include you

Re: Migrating a production AI agent to GPT-5.6: 2.2x faster, 27% cheaper

#55

Post by auspiv »

bob1029 wrote: post #16

> we’ve made GPT 5.6 Sol the default model powering every Ploy workspace I would consider Luna for parts of the workload that touch actual tools. It is surprisingly capable and it runs fast. Sol is great at talking to the human and orchestration of agent calls, but it's just too expensive to use everywhere. You can get 5 Luna runs for the cost of 1 Sol run. Statistically speaking, going from one to five samples is a…

Statistically speaking if each part of the Luna run has a 90% chance of being correct, 5 of those is 0.9^5 = 0.59 = 59%. Or one Sol run being maybe 95% correct? Exact numbers vary of course. But then again having sol verify at end may be cheaper.

Re: Migrating a production AI agent to GPT-5.6: 2.2x faster, 27% cheaper

#56

Post by toddmorey »

w4yai wrote: post #10
kristianp wrote: post #6

> Numbers like that buy a model a real migration effort. Such a silly choice of words. I wish the human directing the LLM writing the article put some effort into rewriting the worst examples of LLM style. > But it did extremely well, and the promise was immediate and specific: builds finishing in less than half the wall-clock time, at 27% lower cost, scoring at or above our incumbent on completed work. The way the L…

Can we get over the detective work about if the text was written by LLM or not in 2026 already ? This is a lost cause, and we could instead focus on substance over syntax.

But it's not about whether it was AI or human authored. That misses the point. We're all fatigued on the writing style. The same cadence and patterns; the same phrases and terms like "load-bearing". Used everywhere, they create a super fatiguing monoculture in all the writing. It's like if every illustration on the internet suddenly contained Garfield the cat.

Re: Migrating a production AI agent to GPT-5.6: 2.2x faster, 27% cheaper

#57

Post by narmiouh »

redfather918 wrote: post #47

The cost reduction is impressive, but I think consistency matters even more for production agents. I'd be interested to know whether prompt engineering or tool-calling workflows had to change significantly.

He actually talks about that in the article. Including how they had to rearchitect tool calling using nulls as well as limitations of prompt caching

Re: Migrating a production AI agent to GPT-5.6: 2.2x faster, 27% cheaper

#59

Post by weakfish »

TacticalCoder wrote: post #24
kristianp wrote: post #6

> Numbers like that buy a model a real migration effort. Such a silly choice of words. I wish the human directing the LLM writing the article put some effort into rewriting the worst examples of LLM style. > But it did extremely well, and the promise was immediate and specific: builds finishing in less than half the wall-clock time, at 27% lower cost, scoring at or above our incumbent on completed work. The way the L…

> The way the LLMs write (Claude perhaps?) With short phrases separated by colons, commas or full stops, is so poor and frustrating. Yup llmish (from now on it's called "llmish") sucks. But I'd say: at this point it's probably trivial to write a browser extension that detects llmish and that rewrites the worst sentences: from llmish to something less irritating to read. Heck, I could spent tokens on that: an extensio…

As a certified Gen Z member: respectfully, what the fuck are you on about?

The mythical Gen Z you are describing is the hyperbolic exaggeration that is equivalent to me describing all boomers as racist, all Gen X as entitled, all millennials as lazy, etc.

Post reply on HN