Hacker News: kveykva

New comment by kveykva in "Show HN: Drive any macOS app in the background without stealing the cursor"

kveykva — Tue, 28 Apr 2026 20:49:10 +0000

Would you be open to sharing what you built for running the automation tests? I could really use this right now.

New comment by kveykva in "Sora 2"

kveykva — Tue, 30 Sep 2025 17:11:22 +0000

The example prompt "intense anime battle between a boy with a sword made of blue fire and an evil demon demon" is super clearly just replicating Blue Exorcist https://en.m.wikipedia.org/wiki/Blue_Exorcist

New comment by kveykva in "Show HN: Sculptor – A UI for Claude Code"

kveykva — Tue, 30 Sep 2025 17:05:52 +0000

Even design wise this looks virtually identical to https://terragonlabs.com/

New comment by kveykva in "Perplexity Comet"

kveykva — Wed, 09 Jul 2025 19:31:22 +0000

The scroll hijacking on this site itself erodes my trust in this being a browser I want to use because it demonstrates a lack of understanding of the web.

New comment by kveykva in "Ask HN: Who is hiring? (July 2025)"

kveykva — Wed, 02 Jul 2025 05:19:31 +0000

Max AI is building the financial operating system for healthcare—turning the broken, error-prone billing process into a lightning-fast, autonomous experience, much like swiping a credit card. Our ambient AI agents handle medical coding, claim submission, and fund collection the moment a doctor finishes charting—no humans in the loop.

We’re addressing a $350 billion market where billing errors cause delayed treatments, higher healthcare costs, and massive medical debt. By eliminating billing mistakes, we enable faster access to care, reduce administrative burden on doctors, and protect patients from surprise bills.

Team:

- PhD/Postdoc AI scientists from MIT and Caltech

- Ex-VP of Engineering at Curative (led engineering for over 25M medical claims billed)

- Founders who’ve scaled products to 40M+ downloads and 150M+ monthly users

- A team of experienced engineers from Discord, Google, Facebook, Airbnb, Brex, and Figma

If you want to help build the AI infrastructure that will transform healthcare finance apply at: https://app.dover.com/apply/Maxcare/3684f186-f343-439a-9500-...

New comment by kveykva in "Ask HN: Who is hiring? (June 2025)"

kveykva — Mon, 02 Jun 2025 18:23:16 +0000

We're a team of repeat founders and world-class builders:

- PhD/Postdoc AI scientists from MIT and Caltech

- Ex-VP of Engineering at Curative (led engineering for over 25M medical claims billed)

- Founders who’ve scaled products to 40M+ downloads and 150M+ monthly users

- A team of experienced engineers from Discord, Google, Facebook, Airbnb, Brex, and Figma

Traction:

- Launched in 2025

- Projecting $5M ARR in the next 2 months

- $2M in claims processed in the first 30 days (we earn 4–12% per claim)

We're 6 months in and just getting started. If you want to help build the AI infrastructure that will transform healthcare finance, reach out to: colton[@]maxcare[.]ai or apply at https://app.dover.com/apply/Maxcare/3684f186-f343-439a-9500-...

New comment by kveykva in "Show HN: AI assisted image editing with audio instructions"

kveykva — Mon, 01 Jul 2024 19:38:40 +0000

This pitches a lot but only seems to support a specific inpainting operation?

New comment by kveykva in "Farm: Fast vite compatible build tool written in Rust"

kveykva — Sat, 22 Jun 2024 19:58:36 +0000

Their code base is also weirdly convoluted, with many crates and files just proxying over to others. I've read and written a lot rust, and haven't seen this style really. Could be nothing but its odd.

New comment by kveykva in "Simple tasks showing reasoning breakdown in state-of-the-art LLMs"

kveykva — Wed, 05 Jun 2024 16:10:58 +0000

Have there ever been studies that demonstrate that those individuals don't simulate possible state transitions they'll go through in a different modality? I'd be curious if they visualize actions they'll take still, just not verbally.

New comment by kveykva in "Tinygrad 0.9.0"

kveykva — Wed, 29 May 2024 10:07:27 +0000

This is truly depressing because the aspirations of tinygrad are so appealing in terms of being concise, effective and maintainable. Then, instead, they throw comprehensibility entirely out of the window.

New comment by kveykva in "Figma’s Journey to TypeScript"

kveykva — Sat, 04 May 2024 08:06:34 +0000

Vector editing has a lot of CPU bound tasks. Evan has some writing regarding the transition to WASM https://medium.com/figma-design/webassembly-cut-figmas-load-...

New comment by kveykva in "A Full Hardware Guide to Deep Learning"

kveykva — Sun, 17 Dec 2023 04:54:51 +0000

There’s a 2023 article by the same author here it looks like https://timdettmers.com/2023/01/30/which-gpu-for-deep-learni...

New comment by kveykva in "Cerabyte: ceramic storage poised to usher in 'yottabyte era'"

kveykva — Fri, 08 Sep 2023 22:43:09 +0000

The miniaturization of what are in some senses fired clay tablets for information storage would be a fascinating development.

New comment by kveykva in "Figma makes 200 fixes and improvements to Dev Mode"

kveykva — Tue, 22 Aug 2023 21:44:41 +0000

Spline and Vectary are both in this space

New comment by kveykva in "What happened in this GPT-3 conversation?"

kveykva — Tue, 08 Aug 2023 21:42:49 +0000

You're not even close to baseline.

New comment by kveykva in "Show HN: LLMFlows – LangChain alternative for explicit and transparent apps"

kveykva — Sat, 29 Jul 2023 20:47:09 +0000

We're working on similar things! If you'd like to chat sometime I'd be interested. My HN username is also my twitter handle.

New comment by kveykva in "Chidori – Declarative framework for AI agents (Rust, Python, and Node.js)"

kveykva — Thu, 27 Jul 2023 07:53:23 +0000

That is correct

New comment by kveykva in "Chidori – Declarative framework for AI agents (Rust, Python, and Node.js)"

kveykva — Thu, 27 Jul 2023 07:52:01 +0000

The temptation to call something related to the replay functionality Sharingan is pretty strong now that I've used this name haha.

New comment by kveykva in "Chidori – Declarative framework for AI agents (Rust, Python, and Node.js)"

kveykva — Thu, 27 Jul 2023 06:36:13 +0000

In what I think of as engineering terms: an agent is a long running service that invokes LLMs during its execution. In contrast to an LLM driven application where the primary function is synchronous with the end user (like chatGPT). There's a blurry line there but that's how I think about it.

AutoGPT and BabyAGI are probably the two most well known examples so far.

A significant struggle when building these types of applications is understanding and debugging behavior many execution steps deep. This tries to assist with that by giving a framework for structuring the way your agent runs.

Maybe a similar concept is breaking out a web application into services, or individual route handlers, rather than implementing everything as one massive loop that responds to events.

New comment by kveykva in "Chidori – Declarative framework for AI agents (Rust, Python, and Node.js)"

kveykva — Thu, 27 Jul 2023 05:52:09 +0000

Currently it only supports openAI. I'm looking into patterns for supporting local LLMs! I think the best approach for that might be to allow you to update the api endpoint to your own and assume you're using something that mirrors the structure of their API.

The main escape hatch for everything right now are custom nodes though. But then you'll need to bring your own templating pattern.