Hacker Newsnew | past | comments | ask | show | jobs | submit | jamest's commentslogin

Alex (the OpenRouter founder) and I went for walks to Sightglass coffee on Divisadero St during our weekly office hours @ HF0 in the Fall of '23.

On one walk I asked 'why are you doing another startup?'

For context, his last one, OpenSea, was valued well into the billions, so it wasn't for money.

His reply: "I just love solving all the puzzles."

It's incredibly hard to compete with someone who is playing the game for the love of the game.

Kudos on playing well, Alex.


OpenSea is full of scams, has not added any real value to anyone or society.

DOn't get me wrong, great for him to make money and being able to move fast and succeed, but you could play this game to if you want.


nah, the reason is money, you can get puzzle fix somewhere else


I’ve been using this local debugger for the last ~week.

Seeing traces in real-time (and Claude seeing them too) is so so good. The velocity speed up is hard to understate.

Request for the Raindrop team: I wish your eval support was better. It’s not great having it completely disconnected from my CI system.


They actually deliver on the promise of "relational queries && real-time," which is no small feat.

Though, their console feels like it didn't get the love that the rest of the infra / website did.

Congrats on the 1.0 launch! I'm excited to keep building with Instant.


Thank you! We spent a lot of time with the demos on the home page, the essays page, and upgrading the docs.

We're going to redesign the dashboard in the next few weeks.

One interesting observation from our users: though they use the dashboard less in some ways (the AI agents spin up apps and make schema changes for them), we found people use them _more_ in other ways. Instant comes with an Explorer component, which lets you query your data. We found users want to engage with that a lot more.


Add a list of people (PMs) who have added feature requests. Have their username be "<username> (<Full Name>) - <karma points>" and then I can click through to see their bio.


It was not on my bingo card to see the Shell Grotto on HN.

I loved this place as a kid and would marvel at the patterns.

The air of mystery around who made it and why invites some fun speculation.



I don't trust an AI model to operate my computer, but giving me my own VM that AIs can use on my behalf is a brilliant way to do this.

Kudos Tasklet.


Genie 3 is super impressive -- but you can't manipulate it programmatically like Minecraft.

We've built our infra so that we can plug in any simulation environment. If an AI-generated world starts being programmatically modifiable (and has really solid object permanance :) then we'd happily use it!


Hi HN -

Minecraft has a DSL that lets you manipulate the world. We've piggy-backed on that, along with a K8s infra to run N worlds in parallel, to let you create simulations of arbitrary complexity.

We think simulations are the best way to test frontier AIs due to their degrees of freedom and expressivity.

AMA!


I built an app (HN Clone, of course) with Instant's MCP hooked up to Claude Code.

The experience was brilliant.

Pros:

+ Fast

+ Easy

+ "Vibe coding on steroids" basically

+ The sense of 'wow' that comes very rarely with new tech

Cons:

- It used Instant as the database/backend, but I wasn't sure what it had done / how exactly it worked and had to spend a bunch of time asking Claude + reading the code to get it. It seemed reasonable, but if I were doing a prod system vs a PoC, this is where the time would be spent. ("Vibe coding lets you create tech debt 10x faster")

Net-net: This is the way for prototyping / validating. This is probably the way for production systems in N months too once the toolchain + agents get better.


Would you mind sharing the code, as well as prompts if you're comfortable? I'm trying to sample anecdata to help re-baseline my intuition on these things.


> as well as prompts if you're comfortable?

This made me wonder: can I share Claude Code's conversation history? Turns Claude stores them.

So I made a full-stack "snippet" app with Claude and Instant. You can:

1. Upload jsonl files 2. Share them in a nice UI

(Going meta) here's the first conversation I had with Claude in order to build it:

https://claude-code-viewer.vercel.app/view/c4ca91ac-9624-40f...

After I deployed, I asked it to fix the tool use UI:

https://claude-code-viewer.vercel.app/view/faf9b2cc-c3cf-4d0...

I used Instant's auth to gate uploads. Views are public, but limited only to the snippets you know (i.e have links for).

If you want to upload your own conversations:

1. They live in ~/.claude. Head on over and grab a file 2. Go to https://claude-code-viewer.vercel.app and sign up 3. Start uploading : )

Some notes:

* Be careful when sharing log files. Claude can include secrets in there. Some hackers may notice an adminToken in the convo. I rotated it before we pushed.

* It was fun to see Claude use the query language. It thought we had a `$startsWith` modifier. Right now we only have $like. But `$startsWith` is a great idea, we may just implement it real quick!


> It thought we had a `$startsWith` modifier. Right now we only have $like. But `$startsWith` is a great idea, we may just implement it real quick!

Haha, that's great. Turns out that "hallucinations" are just things that make sense in context, and that can translate to feature requests from our agents :)


Claude code now has an /export command for this use case. You can run it from within a session.


TIL, thank you!


I don't have the prompts, but here you go:

  - https://the-inference.vercel.app
  - https://github.com/jamestamplin/instant-test


If they get better. At the moment the progress is on the toolchains because the LLMs progress as such slows down because of the lack of training data


Have you tried Convex?


+1 to Shortwave being great


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: