kylenessen

I vividly remember watching on television a man losing control of his paper shredder as it ate his tie because of Y2K. I think both points can be true

I agree with the author. Writing serves many purposes, and there is a continuum in how much humanity needs to be present in the text. A eulogy is not the same as a git commit.

I’m hoping he’s right that this is a passing moral panic, because the persecution of “AI smell” is exhausting. If it works, it works, right? Do we have to be so precious about how we got there?

Did you read the blog? I found it well written and easy to follow.

The trap was hidden text instructing the AI to use the word “Madagascar” in a nonsensical way. The assignment was about the Industrial Revolution. “Madagascar wore a toaster to the basketball game” is an example of what a student turned in. The instructor says it was the midterm, but looks like it was more of an online discussion. Anyway, I knew cheating was bad, but this is just flagrant.

I really wanted to like this, but unfortunately couldn't see how it improves my experience over Obsidian or VS Code.

The fact that I have to juggle between OpenKnowledge and Codex to engage the AI, while also accepting a barebones Obsidian, is a real bummer. From what I can tell, you are saving me a few key strokes with moving prompts around. What I really want is the AI to live IN the app, like VS Code, and then move around the documents like it is Obsidian. I'll accept a plain terminal, but a pretty UI would feel like a better fit. My sense is that the new value add here is a set of skills and mcp servers, which probably already exist for Obsidian, or could more productively be spun up. I looked at the plugins again in Obsidian and found Claudian, which lets me bring my local models and Codex in the right pane. This is perfect, so sorry your app is not for me (yet), but thanks for getting me to look again at my tooling.

I want to throw my vote in for local models. Gemma4-31b is working well for me on these types of tasks, and not having an easy way to plug that in is a deal breaker. Embeddings should certainly have a local option, as they are cheap to compute. For what it is worth, I use LMStudio which supports OpenAI and Anthropic compatible api endpoints, so it should be easy to wire in.

A big caveat, I'm not trying to share my vault with other people, and I can see making that pain go away being worth switching. That said, I feel like you're targeting a weird market, where you want people technical enough to use LLMs and GitHub, but not so technical they can't customize a shared environment.

I would switch if the whole experience was self contained and "clean." Right now, it feels like a well dressed wrapper for pretty basic functionality.

I had Fable apply some edits to my monarch butterfly paper and kept getting bumped to Opus. Im not exactly sure why, but I suspect it happened when it ran my analysis scripts to double check my numbers.

My great grandfather supported a family of 7 making brooms. He didn’t own the broom factory. He was an employee, and was paid by the broom. My great grandmother stayed at home to raise 5 children. There was even enough to lend to the local grocery store, apparently. This was at the turn of the 20th century in Canada.

This seems like really great research, and the first time I’ve seen overwhelming praise on HN. Congrats!

I wanted to comment though that your title is not doing you any favors, and I suspect that is why this is not getting more traction (which it deserves). I fully expected some half baked GitHub repo, but instead found something truly awesome.

To use your own words, Neel, “ a very different type of computer use model” would have had me clicking faster. I’m not great at titles, however, and maybe there are better ideas out there.

Anyway, can’t wait to see how this develops! Especially looking forward to the CAD work.

Why not iNaturalist?