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

571–580 of 1001 posts

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

#571

Post by seanmcdirmid »

friendzis wrote: post #568
seanmcdirmid wrote: post #552

Earlier quoted context omitted.

Pity, prompt engineering is just another kind of programming, I find it to be fun, but I guess lots of other people would see it differently.

The venn diagram of engineering and prompting is two circles, maybe a tiny overlap with integrated environments like claude code. A program, by definition, is analyzable and repeatable, whereas prompting is anything but that.

As long as your program is large and multi-threaded (most programs that matter commercially), it is not very analyzable or repeatable. You replace those qualities with QA and tests, the same is true with prompting.

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

#572

Post by suzzer99 »

pigpop wrote: post #410
koyote wrote: post #391

Earlier quoted context omitted.

A greenfield project is definitely 'easy mode' for an LLM; especially if the problem area is well understood (and documented). Opus is great and definitely speeds up development even in larger code bases and is reasonably good at matching coding style/standard to that of of the existing code base. In my opinion, the big issue is the relatively small context that quickly overwhelms the models when given a larger task…

You have to think of Opus as a developer whose job at your company lasts somewhere between 30 to 60 minutes before you fire them and hire a new one. Yes, it's absurd but it's a better metaphor than someone with a chronic long term memory deficit since it fits into the project management framework neatly. So this new developer who is starting today is ready to be assigned their first task, they're very eager to get st…

> You have to think of Opus as a developer whose job at your company lasts somewhere between 30 to 60 minutes before you fire them and hire a new one.

I am stealing the heck out of this.

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

#573

Post by littlestymaar »

spaceman_2020 wrote: post #464
littlestymaar wrote: post #211

Earlier quoted context omitted.

> I really think a lof of people tried AI coding earlier, got frustrated at the errors and gave up. That's where the rejection of all these doomer predictions comes from. It's not just the deficiencies of earlier versions, but the mismatch between the praise from AI enthusiasts and the reality. I mean maybe it is really different now and I should definitely try uploading all of my employer's IP on Claude's cloud and…

You enter some text and a computer spits out complex answers generated on the spot Right or wrong - doesn’t matter. You typed in a line of text and now your computer is making 3000 word stories, images, even videos based on it How are you NOT astounded by that? We used to have NONE of this even 4 years ago!

Of course I'm astounded. But being spectacular and being useful are entirely different things.

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

#574

Post by rleigh »

honeycrispy wrote: post #26

A couple weeks ago I had Opus 4.5 go over my project and improve anything it could find. It "worked" but the architecture decisions it made were baffling, and had many, many bugs. I had to rewrite half of the code. I'm not an AI hater, I love AI for tests, finding bugs, and small chores. Opus is great for specific, targeted tasks. But don't ask it to do any general architecture, because you'll be soon to regret it.

I've found it to be terrible when you allow it to be creative. Constrain it, and it does much better.

Have you tried the planning mode? Ask it to review the codebase and identify defects, but don't let it make any changes until you've discussed each one or each category and planned out what to do to correct them. I've had it refactor code perfectly, but only when given examples of exactly what you want it to do, or given clear direction on what to do (or not to do).

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

#575

Post by troupo »

EMM_386 wrote: post #304
troupo wrote: post #208

Earlier quoted context omitted.

> Opus 4.5 really is at a new tier however. It just...works. Literally tried it yesterday. I didn't see a single difference with whatever model Claude Code was using two months ago. Same crippled context window. Same "I'll read 10 irrelevant lines from a file", same random changes etc.

The context window isn't "crippled". Create a markdown document of your task (or use CLAUDE.md), put it in "plan mode" which allows Claude to use tool calls to ask questions before it generates the plan. When it finishes one part of the plan, have it create a another markdown document - "progress.md" or whatever with the whole plan and what is completed at that point. Type /clear (no more context window), tell Claude…

> The context window isn't "crippled".

... Proceeds to explain how it's crippled and all the workarounds you have to do to make it less crippled.

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

#576

Post by keychera »

tripledry wrote: post #549

Putting the performance aside for now as I just started trying out Opus 4.5, can't say too much yet, I don't hype or hate AI as of now, it's simply useful. Time will tell what happens, but if programming becomes "prompt engineering", I'm planning on quitting my job and pivoting to something else. It's nice to get stuff working fast, but AI just sucks the joy out of building for me. Trying to not feel the pressure/anx…

I have similar stance to you. LLM has been very useful for me but it doesn't really change the fun-ness of programming since my circumstances has allowed me find programming to be very fun. I also want to pivot out to something else if English prompt becomes the main way to develop complex software. Though my other passion is having worse career horizon in the generative AI world (art making). We'll see.

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

#577

Post by paipa »

sksishbs wrote: post #359
fenwick67 wrote: post #336

Earlier quoted context omitted.

Another thing that gets me with projects like this, there are already many examples of image converters, minesweeper clones etc that you can just fork on GitHub, the value of the LLM here is largely just stripping the copyright off

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…

"And likely just creating more debt down the road"

In the most inflationary era of capabilities we've seen yet, it could be the right move. What's debt when in a matter of months you'll be able to clear it in one shot?

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

#578

Post by rleigh »

jdthedisciple wrote: post #540

To those of you who use it: How much does Claude Code cost you a month on avg? I only use VS Code with Copilot subscription ($10) and already get quite a lot out of it. My experience is that Claude Code really drains your pocket extremely fast.

I started on the cheapest £15/mo "Pro" plan and it was great for home use when I'd do a bit of coding in the evenings only, but it wasn't really that usable with Opus--you can burn through your session allowance in a few minutes, but was fine with Sonnet. I used the PAYG option to add more, but cost me £200 in December, so I opted for the £90/mo "Max" plan which is great. I've used Opus 4.5 continuously and it's done great work.

I think when you look at it from the perspective of how much you get out of it compared with paying a human to do the same (including yourself), it is still very good value for money whether you use it for work or for your own projects. I do both. But when I look what I can now do for my own projects including open-source stuff, I'm very time-limited, and some of the things I want to do would take multiple years. Some of these tools can take that down to weeks, do I can do more with less, and from that perspective the cost is worth it.

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

#579

Post by Krei-se »

bombdailer wrote: post #275
YesBox wrote: post #245

I've noticed a huge drop in negative comments on HN when discussing LLMs in the last 1-2 months. All the LLM coded projects I've seen shared so far[1] have been tech toys though. I've watched things pop up on my twitter feed (usually games related), then quietly go off air before reaching a gold release (I manually keep up to date with what I've found, so it's not the algorithm). I find this all very interesting: LLM…

The type of people to use AI are necessarily the people who will struggle most when it comes time to do the last essential 20% of the work that AI can't do. Once thinking is required to bring all the parts into a whole, the person who gives over their thinking skills to AI will not be equipped to do the work, either because they never had the capacity to begin with or because AI has smoothed out the ripples of their…

I think you can tell from some answers here that people talk to these models a lot and adapt their language structure :( Means they stop asking themselves whether it makes any sense what they ask the model for. It does not turn middle management into developers it turns developers into middle managers that just shout louder or replace a critical mind with another yesman or the next super best model that finally brings their genius ideas to life. Then well they get to the same wall of having to learn for themselves to reach gold and ofc that's an insult to any manager. Whoever cannot do the insane job has to be wrong, never the one asking for insanity.

Sad i had to scroll so far down to get some fitting description of why those projects all die. Maybe it's not just me leaving all social networks even HN because well you may not talk to 100% bots but you sure talk to 90% of people that talk to models a lot instead of using them as a tool.

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

#580

Post by ensocode »

raesene9 wrote: post #566
qnleigh wrote: post #563

So much of the conversation is around these models replacing software engineers. But the use cases described in the article sound like pretty compelling business opportunities; if the custom apps he built for his wife's business have been useful, probably there are lots of businesses that would pay for the service he just provided his wife. Small, custom apps can be made way more cheaply now, so Jeven's paradox says…

One problem with the idea of making businesses out of this kind of application is actually mentioned in passing in the article "I decided to make up for my dereliction of duties by building her another app for her sign business that would make her life just a bit more delightful - and eliminate two other apps she is currently paying for" OP used Opus to re-write existing applications that his wife was paying for. So…

so everybody is making their own apps for their specific problem? Sounds as it will get a mess in the end. So maybe it will be more about ideas and concepts and not so much about know how to code.
Post reply on HN