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

Opus 4.5 is not the normal AI agent experience that I have had thus far

burkeholland.github.io

Post reply on HN
Print view View original

931–940 of 1001 posts

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#931

Post by theshrike79 »

suzzer99 wrote: post #553
sksishbs wrote: post #359

Earlier quoted context omitted.

It’s kind of funny - there’s another thread up where a dev claimed a 20-50x speed up. To their credit they posted videos and links to the repo of their work. And when you check the work, a large portion of it was hand rolling an ORM (via an LLM). Relatively solved problem that an LLM would excel at, but also not meaningfully moving the needle when you could use an existing library. And likely just creating more debt…

I've hand-rolled my own ultra-light ORM because the off-the-shelf ones always do 100 things you don't need.* And of course the open source ones get abandoned pretty regularly. Type ORM, which a 3rd party vendor used on an app we farmed out to them, mutates/garbles your input array on a multi-line insert. That was a fun one to debug. The issue has been open forever and no one cares. https://github.com/typeorm/typeorm/…

This is the thing that will be changing the open source and small/medium SaaS world a lot.

Why use a 3rd party dependency that might have features you don't need when you can write a hyper-specific solution in a day with an LLM and then you control the full codebase.

Or why pay €€€ for a SaaS every month when you can replicate the relevant bits yourself?

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#932

Post by theshrike79 »

michaelsalim wrote: post #47
Herring wrote: post #17

Me and Opus have a lot in common. We both hit our weekly limit on Monday at 10am.

I use pay as you go for this very reason, so the limit is my pocket haha. It does make me conscious to keep it under $20 per month though.

You can use both btw. Get the $20 plan and turn on "extra usage" in billing. Then you can use the basic plan first and if it runs out, it uses token-based billing for the overflow.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#933

Post by hollowturtle »

xnx wrote: post #926
hollowturtle wrote: post #641

I'm tired of constantly debating the same thing again and again. Where are the products? Where is some great performing software all LLM/agent crafted? All I see is software bloatness and decline. Where is Discord that uses just a bunch of hundreds megs of ram? Where is unbloated faster Slack? Where is the Excel killer? Fast mobile apps? Browsers and the web platform improved? Why Cursor team don't use Cursor to get…

AI amplified development has the most impact on build-vs-buy decisions. We should expect the decreased difficulty of creating software to drive down prices.

> decreased difficulty of creating software to drive down prices.

And here we go again, if difficulty has been decreased so much, where are the fixes or the products?

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#934

Post by pluralmonad »

speedgoose wrote: post #189
theanonymousone wrote: post #70

Earlier quoted context omitted.

Is Claude "Code" anything special,or it's mostly the LLM and other CLIs (e.g. Copilot) also work?

It’s mostly the model, Copilot, Claude Code, OpenCode, snake oil like Oh My OpenCode, it’s not huge differences.

Why do you call Oh My OpenCode snake oil?

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#935

Post by wiml »

qwm wrote: post #408
wiml wrote: post #279

Earlier quoted context omitted.

We've been living in that world since the invention of the compiler ("automatic programming"). Few people write machine code any more. If you think of LLMs as a new variety of compiler, a lot of their shortcomings are easier to describe.

My compiler runs on my computer and produces the same machine code given the same input. Neither of these are true with AI.

You can run an LLM locally (and distributed compile systems, where the compiler runs in the cloud, are a thing, too) so that doesn't really produce a distinction between the two.

Likewise, many optimization techniques involve some randomness, whether it's approximating an NP-thorny subproblem, or using PGO guided by statistical sampling. People might disable those in pursuit of reproducible builds, but no one would claim that enabling those features makes GCC or LLVM no longer a compiler. So nondeterminism isn't really the distinguishing factor either.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#936

Post by gjvc »

winterbloom wrote: post #374
OldGreenYodaGPT wrote: post #33

Most software engineers are seriously sleeping on how good LLM agents are right now, especially something like Claude Code. Once you’ve got Claude Code set up, you can point it at your codebase, have it learn your conventions, pull in best practices, and refine everything until it’s basically operating like a super-powered teammate. The real unlock is building a solid set of reusable “skills” plus a few agents for th…

Didn't feel like reading all this so I shortened it! sorry! I shortened it for anyone else that might need it ---- Software engineers are sleeping on Claude Code agents. By teaching it your conventions, you can automate your entire workflow: Custom Skills: Generates code matching your UI library and API patterns. Quality Ops: Automates ESLint, doc syncing, and E2E coverage audits. Agentic Reviews: Performs deep PR ch…

you are part of the problem

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#937

Post by hu3 »

ycombiredd wrote: post #927

I can't quite figure out what sort of irony the blurb at the bottom of the post is. (I'm unsure if it was intentional snark, a human typo, or an inadvertent demonstration of Haiku not being well suited for spelling and grammar checks), but either way I got a chuckle: > Disclaimer: This post was written by a human and edited for spelling, grammer by Haiku 4.5

The most plausible explanation is that the only typo in that post was made by a human.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#938

Post by loandbehold »

parliament32 wrote: post #867
JDye wrote: post #813

Earlier quoted context omitted.

We have an in-house, Rust-based proxy server. Claude is unable to contribute to it meaningfully outside of grunt work like minor refactors across many files. It doesn't seem to understand proxying and how it works on both a protocol level and business logic level. With some entirely novel work we're doing, it's actually a hindrance as it consistently tells us the approach isn't valid/won't work (it will) and then ent…

> I still believe those who rave about it are not writing anything I would consider "engineering". Correct. In fact, this is the entire reason for the disconnect, where it seems like half the people here think LLMs are the best thing ever and the other half are confused about where the value is in these slop generators. The key difference is (despite everyone calling themselves an SWE nowadays) there's a difference b…

Coding agents as of Jan 2026 are great at what 95% of software engineers do. For remaining 5% that do really novel stuff -- the agents will get there in a few years.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#939

Post by klaussilveira »

nycdatasci wrote: post #879
klaussilveira wrote: post #325

Earlier quoted context omitted.

I made a similar comment on a different thread, but I think it also fits here: I think the disconnect between engineers is due to their own context. If you work with frontend applications, specially React/React Native/HTML/Mobile, your experience with LLMs is completely different than the experience of someone working with OpenGL, io_uring, libev and other lower level stuff. Sure, Opus 4.5 can one shot Windows utilit…

Have you experimented with all of these things on the latest models (e.g. Opus 4.5) since Nov 2025? They are significantly better at coding than earlier models.

Yes, December 2025 and January 2026.

Re: Opus 4.5 is not the normal AI agent experience that I have had thus far

#940

Post by andrekandre »

megalomanu wrote: post #743
andrekandre wrote: post #373

Earlier quoted context omitted.

> we have another Claude Code agent that does a full PR review, following a detailed markdown checklist we’ve written for it. (if you know) how is that compared to coderabbit? i'm seriously looking for something better rn...

Never tried coderabbit, just because this is already good enough with Claude Code. It helped us to catch dozens of important issues we wouldn't have caught. We gave some instructions in the CLAUDE.md doc in the repository - with including a nice personalized roast of the engineer that did the review in the intro and conclusion to make it fun! :) Basically, when you do a "create PR" from your Claude Code, it will help…

thanks for the reply, yea we have a claude.md file, but coderabbit doesn't seem to pick it up or ignore it... hmmm wish we could try out claude code.
Post reply on HN