Hacker News Reader

Comment by jumploops | Hacker News Reader

Everyone is looking down on LLM-assisted dev here, but I think it's a great fit.

I also don't believe it can be one-shotted (there's too many deltas between Notion's API and Obsidian).

With that said, LLMs are great for enumerating edge-cases, and this feels like the perfect task for Codex/Claude Code.

I'd implore the obsidian team/maintainers to take a stab at building this with LLMs. Based on personal experience, the cost is likely within the same magnitude ($100-$1k in API cost + dev time), but the additional context (tests, docs, etc.) will be invaluable to future changes to either API surface.

View on HN

> Everyone is looking down on LLM-assisted dev here, but I think it's a great fit.

From my own experience, I don't think that's the case. I've wrote a similar sync-script obsidian<->notion-databases myself some months ago, and I also used AI in the beginning; but I learned really fast what an annoying mess Notions API is, and how fast LLMs are hanging up on edge-cases. AI is good to get a start into the API, but at the end you still have to fix it up yourself.

LLMs are wonderful for migration. Also, are good at exploring APIs.

A month ago I migrated company's website and blog from Framer to Astro (https://quesma.com/blog/ is you would like to see the end result).

This weekend I created a summary of Grafana dashboard data. LLMs are tireless at checking hypothesis, running grunt code, seeing results, and iterating on that.

What takes more than a single is to check if the result is correct (nothing missed, nothing confabulated, no default fallbacks) and to maintain code quality (I refactor early and often, here is a place in Claude Code that there is no other way than using Opus 4.1). Most of my time spend talking with Claude Code ais in refactoring - and it requires most knowledge of tooling, abstraction, etc.

Someone's given it a shot: https://github.com/obsidianmd/obsidian-importer/pull/424

Can't help but think if the author of that PR had been less defeatist and snarky they would have had a chance at decent discussion about it being a viable option (with AI).

It's 1100 lines of code in a single file that nobody understands. That's instant spaghetti right there, not a valid PR.

At least have it be split into some files and structured in some way.

how is a single 1100 line file that handles Notion’s API format “spaghetti”?

spaghetti code is code that snakes through the code base in a hard-to-follow way

It’s funny reading these threads. A gif of a few clicks is evidence “it works” for the author. It’s like citing lines of code as a measure of your productivity. Appears impressive on first glance, but any expert will call you out as a snake oil salesman.

My guess is this is close to the level of testing they put forth for ensuring the AI generated code works (based off my experience with other AI heavy devs). They didn’t take any time to thoroughly review nor understand the code. A large file doesn’t necessarily mean shoddy work, but it certainly indicates it’s likely that.

I don’t get the llm shilling. If you think you can earn 50k with some prompts, then earn it. Why _instead_ shill for llms? Feels like stock traders having courses for how YOU could earn big bucks. They themselves have photos taken with one day rented Ferraris…

We all lean on LLMs in one way or another, but HN is becoming infested with wishful prompt engineers. Show, dont tell. Compete on the market instead of yet another PoC.

>Feels like stock traders having courses for how YOU could earn big bucks. They themselves have photos taken with one day rented Ferraris…

Do you think the person you are replying to is Sam Altman?

Uh, sorry?

The bounty here is just $5k, and if you read my comment, I’m suggesting that the maintainer(s), even with LLMs, will likely spend a similar amount in inference + cost of their own time, however they’ll likely produce a solution more robust than what the bounty alone will produce.

To be clear: I’m not advocating that someone simply vibe-codes this up.

That’s already happening (2 PRs when this hit HN), both with negative feedback.

I’m suggesting that the maintainers should give LLM-assisted dev a try here, as they already have context on the Obsidian-side API.

Reply on news.ycombinator.com