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

71–80 of 144 posts

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

#71

Post by ianberdin »

ianberdin wrote: post #70

We at Playcode.io - a company similar to Ploy are still using Opus 4.6. "Why?" you might ask. Because GPT 5.6 Sol, while fast and pleasant to use, is essentially the same model as 5.5 wrapped in new marketing packaging, just to avoid losing ground to Anthropic. In practice, it's the same quality: it generates the same garbage, tons of code, and can never solve even a single complex task. We simply don't trust it to w…

Everyone probably has the same question: what about Fable? Fable 5 is sick.

It is simply the best model in the world out of everything we have ever tried. It's absolutely fantastic. It solves almost any task from start to finish, the way it should be done — no errors, perfect code. It's a miracle.

If there's any way to make it a little more affordable, that would be incredible.

As for GPT-5.6 Sol — it doesn't even come close. I honestly don't understand why people even try to compare them. It feels like Sam's attempt to hold onto his audience with those endless daily limit resets. A clever trick, nothing more.

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

#73

Post by baxtr »

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…

Whenever I suspect an article is LLM authored I stop reading it immediately and instead give it to my LLM tool of choice to summarize/ paraphrase.

This way I can at least somewhat control the style of the output.

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

#74

Post by jchw »

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.

It's not detective work, it is literally blatantly obvious and impossible to ignore.

And no we can't get over it either. But I already have talked about that before and said roughly all I have to say on that front, so I'm just going to link back to my last comment regarding this.

https://news.ycombinator.com/item?id=48861849

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

#75

Post by gexla »

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…

My solution to this is to dump it into an LLM and a prompt that roughly does something like...

Hand wavy list just to get a general idea...

1) Give me a condensed summary 2) Is this adding anything to what we already have? (I save good articles along with annotations and whatever notes I may write to go along with it.) 3) Locate any upstream ideas on this (often AI articles are rehashing much better written ideas.) ...

Something like that. Not that I have some great system for it. I find these articles are so full of fluff that I have lost patience to attempt to get through them. So, I pull out the AI to parse the AI. I know that the AI may miss some hidden gems, but I'm okay with that.

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

#76

Post by porker »

ianberdin wrote: post #71
ianberdin wrote: post #70

We at Playcode.io - a company similar to Ploy are still using Opus 4.6. "Why?" you might ask. Because GPT 5.6 Sol, while fast and pleasant to use, is essentially the same model as 5.5 wrapped in new marketing packaging, just to avoid losing ground to Anthropic. In practice, it's the same quality: it generates the same garbage, tons of code, and can never solve even a single complex task. We simply don't trust it to w…

Everyone probably has the same question: what about Fable? Fable 5 is sick. It is simply the best model in the world out of everything we have ever tried. It's absolutely fantastic. It solves almost any task from start to finish, the way it should be done — no errors, perfect code. It's a miracle. If there's any way to make it a little more affordable, that would be incredible. As for GPT-5.6 Sol — it doesn't even co…

> Fable 5 is sick. [It] solves almost any task from start to finish, the way it should be done — no errors, perfect code. It's a miracle.

> As for GPT-5.6 Sol — it doesn't even come close. I honestly don't understand why people even try to compare them.

What kind of problems are you working on? I like Fable but when planning work on a complex C codebase it's making more mistakes than 5.6 Sol xhigh for me.

In what scenarios is Fable giving you "no errors, perfect code"?

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

#77

Post by gbalduzzi »

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.

I agree with the copy-pasted slop that you see sometimes, that is probably generated from a short prompt and therefore has no real substance to it.

If an article has interesting content (which comes from an human) and the LLM is just used to help the author finish off the article, I don't have any problem with that.

Labeling both scenarios in the same category feels completely wrong to it, as equating vibe coded stuff (as in no human ever read the produced code) and agent-assisted good old software engineering

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

#78

Post by xeyownt »

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.

100% this.

The AI police is there to say what is worth reading and what is not, because THEY know what people like.

Or not.

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

#79

Post by wqaatwt »

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…

You are reading it wrong. Ask your LLM to read and summarize based on your style preferences. Better yet don’t read anything at all, just tell your agent to convert it to a skill file for it’s future reference..

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

#80

Post by wqaatwt »

SR2Z wrote: post #37
spongebobstoes wrote: post #33

Earlier quoted context omitted.

critique of writing style isn't made better by claiming it was authored by an LLM

No but it's a useful shorthand to describe a type of bad writing. I also think that people should focus on substance and not if AI was used, but AI writes like shit and I find myself retching a bit when I have to read long AI-written documents. Do they say something useful? Maybe, but when my eyes are glazing over because it's just so exhausting trying to parse what's written, I can't tell. I certainly think less of…

To be fair internet (or rather shovelware websites like Medium) were already flooded by crap articles based on a set of templates. Of course the issue is that LLMs are actually better than the robot-humans who used to write them so now it takes more time until you figure whether it’s worth reading or not..
Post reply on HN