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

Show HN: Plandex – an AI coding engine for complex tasks

github.com

Post reply on HN
Print view View original

31–40 of 112 posts

Re: Show HN: Plandex – an AI coding engine for complex tasks

#31

Post by ENGNR »

danenania wrote: post #29
brap wrote: post #26

This seems very interesting, but I think the interface choice is not good. There would have been much less friction if this was purely a GitHub/GitLab/etc bot.

I see where you're coming from and I do plan to add a web UI and plugin/integration options in the future. I personally wanted something with a tighter feedback loop that felt more akin to git. I also thought that simplifying the UI side would help me stay focused on getting the data structures and basic mechanics right in the initial version. But now that the core functionality is in place, I think it will work well…

I haven't tried it yet, but I think making it fast iteration and simple initially is the right way to go. Nice one sharing this as open source!

Re: Show HN: Plandex – an AI coding engine for complex tasks

#32

Post by IshKebab »

ldelossa wrote: post #27

Show me one of these things do something more complex then a front end intern project.

I agree, these things seem to do okish on trivial web projects. I've never seen them do anything more than that.

I still use ChatGPT for some coding tasks, e.g. I asked it to write C code to do some annoying fork/execve stuff (can't remember the details) and it did a decentish job, but it's like 90% right. Great for figuring out a rough shape and what functions to search for, but you definitely can't just take the code and expect it to work.

Same when I asked it to write a device driver for some simple peripheral. It had the shape of an answer but with random hallucinated numbers.

I've also noticed that because there is a ton of noob-level code on the internet it will tend to do noob-level things too, like for the device driver it inserted fixed delays to wait for the device to perform an operation rather than monitoring for when it had actually finished.

I wonder if coding AIs would benefit from fine tuning on programming best practices so they don't copy beginner mistakes.

Re: Show HN: Plandex – an AI coding engine for complex tasks

#33

Post by danenania »

kekebo wrote: post #23
danenania wrote: post #9

Earlier quoted context omitted.

Thanks, I need to spend some time digging into OpenRouter. The main requirement would be reliable function calling and JSON, since Plandex relies heavily on that. I'm also expecting to need some model-specific prompts, considering how much prompt iteration was needed to get things behaving how I wanted on OpenAI. I've also looked at Together ( https://www.together.ai/ ) for this purpose. Can anyone speak to the diffe…

I can't speak to the differences of Openrouter to Together but the Openrouter endpoint should work as a drop-in replacement for OpenAI api calls after replacing the endpoint url and the value of $OPENAI_API_KEY. The model names may differ to other apis but everything else should work the same.

Awesome, looking forward to trying it out.

Re: Show HN: Plandex – an AI coding engine for complex tasks

#34

Post by danenania »

IshKebab wrote: post #32
ldelossa wrote: post #27

Show me one of these things do something more complex then a front end intern project.

I agree, these things seem to do okish on trivial web projects. I've never seen them do anything more than that. I still use ChatGPT for some coding tasks, e.g. I asked it to write C code to do some annoying fork/execve stuff (can't remember the details) and it did a decentish job, but it's like 90% right. Great for figuring out a rough shape and what functions to search for, but you definitely can't just take the co…

I used a web project in the demo because I figured it would be familiar to a wide range of developers, but actually many nontrivial pieces of Plandex have been built with the help of Plandex itself.

That's not to say it's perfect or will never make "noob-level" mistakes. That can definitely happen and is ultimately a function of the underlying model's intelligence. But I can at least assure you that it's quite capable of going far beyond a trivial web project.

It's also on me to show more indepth examples, so thanks for calling it out. I'd love it if you would try some of the projects you mention and let me know how it goes.

Re: Show HN: Plandex – an AI coding engine for complex tasks

#36

Post by danenania »

Cieric wrote: post #3
lprubin wrote: post #2

Looks interesting. Can you go into more detail about why you like this better for large/complex tasks compared to GH Copilot?

Not the author, but I'm in a discord with him, I believe the main selling point here is that it allows you to manage your updates and conversations in a branching pattern that's saved. So if you can't get the AI to do something you can always revert to a prior state and try a different method. Also it doesn't work on a "small view of the world" like Copilot from when I was using it could only insert code around your…

Yes, couldn't have said it better myself!

Re: Show HN: Plandex – an AI coding engine for complex tasks

#37

Post by visarga »

This approach works. I just built a SPA in 3 days with GPT-4 of which about 50% was generated. My only tooling was a bash script to list all the files in the repo (with some exceptions), including a README.md planning the project, a file list, and at the end I type my task.

I run about 10-15 rounds with it. At the beginning I was using GPT more heavily, but in the middle I found it easier to just fix the code myself. The context got as big as 10k tokens, but was not a problem. At some point I might need to filter the files more aggressively.

But surprisingly all that is needed for a bare-bone repo-level coding assistant is a script to list all the files so I could easily copy paste the whole thing into the chatGPT window.

Re: Show HN: Plandex – an AI coding engine for complex tasks

#38

Post by danenania »

visarga wrote: post #37

This approach works. I just built a SPA in 3 days with GPT-4 of which about 50% was generated. My only tooling was a bash script to list all the files in the repo (with some exceptions), including a README.md planning the project, a file list, and at the end I type my task. I run about 10-15 rounds with it. At the beginning I was using GPT more heavily, but in the middle I found it easier to just fix the code myself.…

Yes, well said. Doing exactly this kind of thing for months with ChatGPT is what convinced me the idea could work in the first place. I knew the underlying intelligence was there--the challenge is giving it the right prompts and supporting infra.

Re: Show HN: Plandex – an AI coding engine for complex tasks

#39

Post by p1esk »

danenania wrote: post #13
npace12 wrote: post #11

Earlier quoted context omitted.

I think Mistral-2-Pro would work really well for this, judging by the great results I've had with it on another heavy on tool calling project [1] [1] https://github.com/radareorg/r2ai

Thanks, I'll give it a try. Plandex's model settings are version-controlled like everything else and play well with branches, so it will be fun to start comparing how all different kinds of models do vs. each other on longer coding tasks using a branch for each one.

For challenging tasks, I typically get code outputs from all three top models (gpt4, opus, and ultra), and pick the best one. It would be nice if your tool could simply this for me: run all three models and perhaps even facilitate some type of model interaction to produce a better outcome.

Re: Show HN: Plandex – an AI coding engine for complex tasks

#40

Post by danenania »

p1esk wrote: post #39
danenania wrote: post #13

Earlier quoted context omitted.

Thanks, I'll give it a try. Plandex's model settings are version-controlled like everything else and play well with branches, so it will be fun to start comparing how all different kinds of models do vs. each other on longer coding tasks using a branch for each one.

For challenging tasks, I typically get code outputs from all three top models (gpt4, opus, and ultra), and pick the best one. It would be nice if your tool could simply this for me: run all three models and perhaps even facilitate some type of model interaction to produce a better outcome.

Definitely, I'm very interested in doing something along these lines.
Post reply on HN