developer VS windmill

> much of the work is repetitive, but it comes with its edge cases that we need to look out for

Then don't use AI for it.

Bluntly.

This is a poor use-case; it doesn't matter what model you use, you'll get a disappointing result.

These are the domains where using AI coding currently shines:

1) You're approaching a new well established domain (eg. building an android app in kotlin), and you already know how to build things / apps, but not specifically that exact domain.

Example: How do I do X but for an android app in kotlin?

2) You're building out a generic scaffold for a project and need some tedious (but generic) work done.

Example: https://github.com/smol-ai/developer

3) You have a standard, but specific question regarding your code, and although related Q/A answers exist, nothing seems to specifically target the issue you're having.

Example: My nginx configuration is giving me [SPECIFIC ERROR] for [CONFIG FILE]. What's wrong and how can I fix it?

The domains where it does not work are:

1) You have some generic code with domain/company/whatever specific edge cases.

The edge cases, broadly speaking, no matter how well documented, will not be handled well by the model.

Edge cases are exactly that; edge cases; the common medium of 'how to x' does not cover edge cases; the edge cases will not be covered and the results will require you to review and complete them manually.

2) You have some specific piece of code you want to refactor 'to solve xxx', but the code is not covered well by tests.

LLMs struggle to refactor existing code, and the difficulty is proportional to the code length. There are technical reasons for this (mainly randomizing token weights), but tldr; it's basically a crap shot.

Might work. Might not. If you have no tests who knows? You have to manually verify both the new functionality and the old functionality, but maybe it helps a bit, at scale, for trivial problems.

3) You're doing some obscure BS or using a new library / new version of the library.

The LLM will have no context for this, and will generate rubbish / old deprecated content.

...

So. Concrete advice:

1) sigh~

> a friend of mine came and suggested that I use Retrieval-Augmented Generation (RAG), I have yet to try it, with a setup Langchain + Ollama.

Ignore this advice. RAG and langchain are not the solutions you are looking for.

2) Use a normal coding assistant like copilot.

This is the most effective way to use AI right now.

There are some frameworks that let you use open source models if you don't want to use openAI.

3) Do not attempt to bulk generate code.

AI coding isn't at that level. Right now, the tooling is primitive, and large scale coherent code generation is... not impossible, but it is difficult (see below).

You will be more effective using an existing proven path that uses 'copilot' style helpers.

However...

...if you do want to pursue code generation, here's a broad blueprint to follow:

- decompose your task into steps

- decompose you steps in functions

- generate or write tests and function definitions

- generate an api specification (eg. .d.ts file) for your function definitions

- for each function definition, generate the code for the function passing the api specification in as the context. eg. "Given functions x, y, z with the specs... ; generate an implementation of q that does ...".

- repeated generate multiple outputs for the above until you get one that passes the tests you wrote.

This approach broadly scales to reasonably complex problems, so long as you partition your problem into module sized chunks.

I personally like to put something like "you're building a library/package to do xxx" or "as a one file header" as a top level in the prompt, as it seems to link into the 'this should be isolated and a package' style of output.

check out smol-developer (https://github.com/smol-ai/developer)

4. https://github.com/smol-ai/developer

How can ChatGPT be effectively utilized for reading library source code, resolving coding issues, and serving as a dedicated coding assistant tailored for a specific programming language?

The smol developer AI tool was built by a developer called Swyx using ChatGPT. This library is designed to act like a personal, junior developer, performing a huge array of simple, routine tasks as well as some sophisticated tasks. By using a spec that you provide in a prompt, you can even use smol developer to pair program with an AI tool!

And this is where most of these tools fall short, with tools like Smol-Developer creating decent client and server code that work great on their own, but unfortunately don’t work together!

1) Show HN: Bloop – Answer questions about your code with an LLM agent (github.com/bloopai)

https://news.ycombinator.com/item?id=36260961

2) https://github.com/paul-gauthier/aider

3) Show HN: GPT Repo Loader – load entire code repos into GPT prompts (github.com/mpoon)

https://news.ycombinator.com/item?id=35191303

4) https://github.com/smol-ai/developer

5) codium

6) copilot

7) using gpt in the playground / chatgpt

8) jam.dev/jamgpt

9) magic.dev

10) https://github.com/kristoferlund/duet-gpt

Which ones am I missing?

I had this same idea and started working on something for this purpose called j-dev [0]. It started as a fork off smol-dev [1] which basically gets GPT to write your entire project from scratch. And then you would have to iterate the prompt to nuke everything and re-write everything, filling in increasingly complicated statements like "oh except in this function make sure you return a promise"

j-dev is basically a CLI where it gives a prompt similar to the one in the parent article. You start with a prompt and the CLI fills in the directory contents (excluding gitignore). Then it requests access to the files it thinks it wants. And then it can edit, delete or add files or ask for followup based on your response.

It also addresses the problem that a lot of these tools eat up way too many tokens so a single prompt to something like smol-dev would eat up a few dollars on every iterations.

It's still very much a work in progress and i'll prob do a show hn next week but I would love some feedback

[0] https://github.com/breeko/j-dev

[1] https://github.com/smol-ai/developer

Smol AI’s “Smol-Developer” gained a lot of notoriety very quickly by being one of the first such tools on the scene. It is a simple set of python scripts that allow a user to build prototype apps using natural language in an iterative approach.

Data Handling: Utilizes Windmill for data pipelines, with a primary database powered by PostgreSQL. Auxiliary data storage is handled by MongoDB, with Redis for caching to optimize performance

Look very similar to the script builder portion of https://github.com/windmill-labs/windmill, but not open-source, not self-hostable, and without open-source integrations (https://hub.windmill.dev/)

disclaimer: I'm founder of ^

If you need a job queue on Postgres, https://windmill.dev provide an all-integrated developer platform with a Pg queue at its core that support jobs defined in python/typescript/sql

windmill.dev - Windmill is an open-source developer platform to quickly build production-grade multi-step automation and internal apps from minimal Python and Typescript scripts. As a free user, you can create and be a member of at most three non-premium workspaces.

For an alternative to airplane.dev, you can checkout Windmill.

https://github.com/windmill-labs/windmill

"Open-source developer infrastructure for internal tools (APIs, background jobs, workflows and UIs). Self-hostable alternative to Airplane, Pipedream, Superblocks and a simplified Temporal with autogenerated UIsm and custom UIs to trigger workflows and scripts as internal apps.

Scripts are turned into sharable UIs automatically, and can be composed together into flows or used into richer apps built with low-code. Supported script languages supported are: Python, TypeScript, Go, Bash, SQL, and GraphQL. "

If you search HN, you'll find the creator of Windmill comment on comparisons to airplane.dev:

https://hn.algolia.com/?dateRange=all&page=0&prefix=false&qu...

https://windmill.dev is a self-hostable OSS alternative to pipedream

(disclaimer: I'm founder)

I'm genuinely curious what server-side stuff on BC you are referring to. That may have been something added after our assessment. The way I'd generally approach something like that for any of the platforms would be using an external low/no code solution to process webhook data. But it would depend heavily on the use case. For a more developer friendly option I've been really impressed by windmill.dev. We use a mix of n8n and windmill for various needs.

Yes it goes in that direction, however note that you can already do this in a not too hard way.

Our openflow spec is both open-source and has a full openapi definition: https://github.com/windmill-labs/windmill/blob/main/openflow...

you can use that to generate client sdks in any languages and build your own dag with it. That's what one of our customer did building a reactflow to openflow library: https://github.com/Devessier/reactflow-to-windmill

It's not as good as the decorator way but we move fast and if you still have interest for it we could prioritize it (and ask for feedbacks :))