Anthropic dropped out of the general "AGI" race and seems to be purely focused on coding, maybe racing to get the first "automated machine learning programmer". Whatever the case, it seems to be paying (coding) dividends to just be focusing on coding.
Opus 4.5 is not the normal AI agent experience that I have had thus far
61–70 of 1001 posts
Re: Opus 4.5 is not the normal AI agent experience that I have had thus far
#62this is just optimizing for token windows. flat code = less context. we did the same thing with java when memory was expensive, called it "lightweight frameworks"
Re: Opus 4.5 is not the normal AI agent experience that I have had thus far
#63Opus 4.5 has become really capable. Not in terms of knowledge. That was already phenomenal. But in its ability to act independently: to make decisions, collaborate with me to solve problems, ask follow-up questions, write plans and actually execute them. You have to experience it yourself on your own real problems and over the course of days or weeks. Every coding problem I was able to define clearly enough within th…
> You have to experience it yourself on your own real problems and over the course of days or weeks. How do you stop it from over-engineering everything?
Difficult and it really depends on the complexity. I definitely work in a spec-driven way, with a step-by-step implementation phase. If it goes the wrong way I prefer to rewrite the spec and throw away the code.
Re: Opus 4.5 is not the normal AI agent experience that I have had thus far
#64Earlier quoted context omitted.
> You have to experience it yourself on your own real problems and over the course of days or weeks. How do you stop it from over-engineering everything?
This has always been my problem whether it's Gemini, openai or Claude. Unless you hand-hold it to an extreme degree, it is going to build a mountain next to a molehill. It may end up working, but the thing is going to convolute apis and abstractions and mix patterns basically everywhere
It's very good at following instructions. You can build dedicated agents for different tasks (backend, API design, database design) and make it follow design and coding patterns.
It's verbose by default but a few hours of custom instructions and you can make it code just like anyone
Re: Opus 4.5 is not the normal AI agent experience that I have had thus far
#65Opus 4.5 has become really capable. Not in terms of knowledge. That was already phenomenal. But in its ability to act independently: to make decisions, collaborate with me to solve problems, ask follow-up questions, write plans and actually execute them. You have to experience it yourself on your own real problems and over the course of days or weeks. Every coding problem I was able to define clearly enough within th…
> You have to experience it yourself on your own real problems and over the course of days or weeks. How do you stop it from over-engineering everything?
I personally try to narrow scope as much as possible to prevent this. If a human hands me a PR that is not digestible size-wise and content-wise (to me), I am not reviewing and merging it. Same thing with what claude generates with my guidance.
Re: Opus 4.5 is not the normal AI agent experience that I have had thus far
#66Earlier quoted context omitted.
Everybody says how good Claude is and I go to my code base and I can't get it to correctly update one xaml file for me. It is quicker to make changes myself than to explain exactly what I need or learn how to do "prompt engineering". Disclaimer: I don't have access to Claude Code. My employer has only granted me Claude Teams. Supposedly, they don't use my poopy code to train their models if I use my work email Claude…
What's even the point of this comment if you self-admittedly don't have access to the flagship tool that everyone has been using to make these big bold coding claims?
Because the same claims of "AI tool does everything" are made over and over again.
Re: Opus 4.5 is not the normal AI agent experience that I have had thus far
#67These are very simple utilities. I expect AI to be able to build them easily. Maybe in a few years it will be able to write a complete photo editor or CAD application from first principles.
Re: Opus 4.5 is not the normal AI agent experience that I have had thus far
#68What's the best coding agent you can run locally? How far behind Opus 4.5 is it?
The best is probably something like GLM 4.7/Minimax M2.1, and those are probably at most Sonnet 4 level, which is behind Opus 4.1, which is behind Sonnet 4.5, which is behind Opus 4.5 ;)
And honestly Opus 4.5 is a visible step change above previous Anthropic models.
Re: Opus 4.5 is not the normal AI agent experience that I have had thus far
#69Earlier quoted context omitted.
That may be true now, but think about how far we've come in a year alone! This is really impressive, and even if the models don't improve, someone will build skills to attack these specific scenarios. Over time, I imagine even cloud providers, app stores etc can start doing automated security scanning for these types of failure modes, or give a more restricted version of the experience to ensure safety too.
There's a fallacy in here that is often repeated. We've made it from 0 to 5, so we'll be at 10 any day now! But in reality there are any number of roadblocks that might mean progress halts at 7 for years, if not forever.
Even if progress halts here at 5, I think the programming profession is forever changed. That’s not hyperbole. Claude Code— if it doesn’t improve at all— has changed how I approach my job. I don’t know that I like this new world, but I don’t think there’s any going back.
Re: Opus 4.5 is not the normal AI agent experience that I have had thus far
#70Most 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…
Is Claude "Code" anything special,or it's mostly the LLM and other CLIs (e.g. Copilot) also work?