111–120 of 388 posts
Claude Code is hard to describe. It’s almost like I changed jobs when I started using it. I’ve been all-in with Claude as a workflow tool, but this is literally steroids. If you haven’t tried it, I can’t recommend it enough. It’s the first time it really does feel like working with a junior engineer to me.
Earlier quoted context omitted.
Some great advice I've found that seems to work very well: ask it to keep a succinct journal of all the issues and roadblocks found during the project development, and what was done to resolve or circumvent them. As for avoiding bloating the code base with scatterbrained changes, having a tidy architecture with good separation of concerns helps leading it into working solutions, but you need to actively guide it. For…
to continue on this, I wouldn't let claude or any agent actually create a project structure, i'd guide it in the custom system prompt. and then in each of the folders continue to have specific prompts for what you expect the assets to be coded like, and common behavior, libraries, etc....
btw, I'm not throwing shade. I personally think upfront design through a large lumbering document is actually a good way to develop stuff. As you either do it upfront, or through endless iterations in sprints for years.
PSA: you can use CC with any model via https://github.com/musistudio/claude-code-router The recent Kimi-K2 supposedly works great.
Earlier quoted context omitted.
It's always POC apps in js or python, or very small libraries in other popular languages with good structure from the start. There are ways to make them somewhat better in other cases (automated testing/validation/linting being a big one), but for the type of thing that 95% of developers are doing day to day (working on a big, sprawling code base where none of those attributes apply), it's not close to being there. T…
> They're amazing. But the moment you try to do the more "serious" work with them, it falls apart rapidly. Sorry, but this is just not true. I'm using agents with a totally idiosyncratic code base of Haskell + Bazel + Flutter. It's a stack that is so quirky and niche that even Google hasn't been able to make it work well despite all their developer talent and years of SWEs pushing for things like Haskell support inte…
If you honestly believe that "agents" are making you better than Goole SWEs then you severely need to take a step back and reevaluate, because you are wrong.
Earlier quoted context omitted.
Weirdly enough I have the opposite experience where it will take several minutes to do something, then I go in and debug for a while because the app has become fubar, then finally realize it did the whole thing incorrectly and throw it all away. And I reach for Claude quite a bit because if it worked as well for me like everyone here says, that would be amazing. But at best it’ll get a bunch of boilerplate done after…
Sigh. As others have commented, over and over again in the last 6 months we've seen discussions on HN with the same basic variation of "Claude Code [or whatever] is amazing" with a reply along the lines of "It doesn't work for me, it just creates a bunch of slop in my codebase." I sympathize with both experiences and have had both. But I think we've reached the point where such posts (both positive and negative) are…
- Some believe LLMs will be a winner-take-all market and reinforce divergences in economic and political power.
- Some believe LLMs have no path of evolution and have therefore already plateaued and too low to be sustainable with these investments in compute, which would imply it's a flash in the pan that will collapse.
- Some believe LLMs will all be hosted forever, always living in remote services because the hardware requirements will always be massive.
- Some believe LLMs will create new, worse kinds of harm without enough offsetting creation of new kinds of defense.
- Some believe LLMs and AI will only ever give low-skilled people mid-skill results and therefore work against high-skill people by diluting mid-end value without creating new high-end value for them.
We need to be more aware of how we are framing this conversation because not everyone agrees on these big premises. It very strongly affects the views that depend on them. When we don't talk about these points and just judge and reply based on whether the conclusion reinforces our premises, the conversation becomes more political.
Confirmation bias is a thing. Individual interests are a thing. Some of the outcomes, like regulation and job disruption, depend on what we generally believe. People know this and so begin replying and voting according to their interests, to convince others to aid their cause without respect for the truth. This can be counter-productive to the individual if they are wrong about the premises and end up pushing an agenda that doesn't even actually benefit them.
We can't tell people not to advance their chosen horse at every turn of a conversation, but those of us who actually care about the truth of the conversation can take some time to consider the foundations of the argument and remind ourselves to explore that and bring it to the surface.
Claude Code is hard to describe. It’s almost like I changed jobs when I started using it. I’ve been all-in with Claude as a workflow tool, but this is literally steroids. If you haven’t tried it, I can’t recommend it enough. It’s the first time it really does feel like working with a junior engineer to me.
Could you elaborate a bit on the tasks,languages,domain etc you’re using it with? People have such widely varying experiences and I’m wondering why.
[flagged]
Anyone using it for game dev? Like just having the agent try to build a game?
I tried using aider with godot. CC would probably be better. Aider with 4o/o3-mini wasn't very good at gdscript, and it was terrible at editing tres/tscn files (which are usually modified through the editor). If you had a very code-centric game, it could turn out OK, but if you have resources/assets that you normally edit with special programs, it is going to struggle.
Earlier quoted context omitted.
I wish there was a Max trial (while on Pro) to test if this was the case or not. Even if it was just a 24 hour trial. Max is an expensive trigger to pull, and hope it just solves this.
FWIW I went Claude Max after Pro, and the trick is to turn off Opus. If you do that you can pretty much use Sonnet all working day in a normal session. I don't personally find Opus that useful, and it burns through quota at 5x the speed of Sonnet.
It's great for me. I have a claude.md at the root of every folder generally, outlined in piped text for minimal context addition about the rulesets for that folder, it always creates tests for what it's doing and is set to do so in a very specific folder in a very specific way otherwise it tries to create debug files instead. I also have set rules for re-use so that way it doesn't proliferate with "enhanced" class va…
I've only tried Claude Code with an external model once (Kimi K2) but it performed poorly.