Hacker News: westoque

New comment by westoque in "NPM packages from Red Hat have been compromised"

westoque — Mon, 01 Jun 2026 15:00:44 +0000

i've been thinking about this as well. but having built a startup, i've learned that users don't care as long as they are given the value and most convenience. they don't really care much at security as much as we do. just look at openclaw? but maybe it's our job to make sure it is taken care of vs assuming the user cares and just make it look seamless.

New comment by westoque in "Tell HN: Litellm 1.82.7 and 1.82.8 on PyPI are compromised"

westoque — Tue, 24 Mar 2026 17:57:41 +0000

my takeaway from this is that it should now be MANDATORY to have an LLM do a scan on the entire codebase prior to release or artifact creation. do NOT use third party plugins for this. it's so easy to create your own github action to digest the whole codebase and inspect third party code. it costs tokens yes but it's also cached and should be negligible spend for the security it brings.

New comment by westoque in "OpenCode – Open source AI coding agent"

westoque — Fri, 20 Mar 2026 23:32:49 +0000

> The problem for me is that the development practices of the people that are working on it are suboptimal at best; they're constantly releasing at an extremely high cadence, where they don't even spend the time to test or fix things (or even build a proper list of changes for each release), and they add, remove, refine, change, fix, and break features constantly at that accelerated pace.

this is what i notice with openclaw as well. there have been releases where they break production features. unfortunately this is what happens when code becomes a commidity, everyone thinks that shipping fast is the moat but at the expense of suboptimality since they know a fix can be implemented quickly on the next release.

New comment by westoque in "AI has fixed my productivity"

westoque — Wed, 18 Feb 2026 14:52:22 +0000

one thing it did massively for me was save me time from questions like should i go with X or Y option questions. before i used to just think longer about tradeoffs but with AI it became a lot faster. no more procrastination due to decision fatigue.

New comment by westoque in "Show HN: isometric.nyc – giant isometric pixel art map of NYC"

westoque — Fri, 23 Jan 2026 18:08:29 +0000

> I simply booted up a VM with an H100, ssh’d into it with Cursor, and prompted the agent to set up an inference server that I could ping from my web generation app. What used to take hours or days of painful, slow debugging now takes literally minutes.

an awesome takeaway from this is that self-hosted models are the future! can't wait for hardware to catch up and we can do much more experiments on our laptops!

New comment by westoque in "Anthropic acquires Bun"

westoque — Tue, 02 Dec 2025 20:14:21 +0000

i really think this is part of the pitch deck for bun's funding. that a bigger company would acquire it for the technology. the only reason an AI company or any company for that matter would acquire it would be to:

1. acquire talent.

2. control the future roadmap of bun.

i think it's really 1.

New comment by westoque in "Show HN: Fixing Google Nano Banana Pixel Art with Rust"

westoque — Sun, 30 Nov 2025 22:20:47 +0000

> Current AI image models can't understand grid-based pixel art.

sounds like a good use case to fix this problem from the model layer. an image gen model that is trained to make pixel perfect art.

New comment by westoque in "Google Antigravity exfiltrates data via indirect prompt injection attack"

westoque — Tue, 25 Nov 2025 20:51:26 +0000

i like how claude code currently does it. it asks permission for every command to be ran before doing so. now having a local model with this behavior will certainly mitigate this behavior. imagine before the AI hits the webhook.site it asks you

AI will visit site webhook.site..... allow this command? 1. Yes 2. No

New comment by westoque in "Shai-Hulud Returns: Over 300 NPM Packages Infected"

westoque — Mon, 24 Nov 2025 11:01:47 +0000

a concern i have is that it's only a matter of time before a similar attack is done to electron based apps (which also have packages installed using npm). probably worse because it's installed in your computer and can potentially get any information especially given admin privileges.

New comment by westoque in "Ask HN: What Are You Working On? (Nov 2025)"

westoque — Mon, 10 Nov 2025 11:39:22 +0000

Recently launched an AI cafe ordering app https://www.hellocafe.ai using chat and voice.

We wanted to make concept for an app using all local models for chat (llama 3.1 8B) and voice (whisper). Deployed using kubernetes and easily scalable not to mention fully open source!

Show HN: Hellocafe.ai – open-source voice and chat enabled AI ordering system

westoque — Fri, 07 Nov 2025 15:57:09 +0000

we wanted to experiment on how feasible it is to build a cafe ordering system using chat and voice with 100% local models.

we were able to build this demo using llama 8B for the llm and whisper for tts/stt. it's deployed using kubernetes and could be used a base for any AI enabled application.

Comments URL: https://news.ycombinator.com/item?id=45847697

Points: 2

# Comments: 0

New comment by westoque in "Fluid Glass"

westoque — Sat, 04 Oct 2025 05:05:09 +0000

Refreshing that it's built using the vue framework vs the typical react.

New comment by westoque in "Cognition (Devin AI) to Acquire Windsurf"

westoque — Tue, 15 Jul 2025 02:50:40 +0000

> They're getting my $200 a month and it's easily the best money I spend

Can you explain? I don't see how $200 makes that much difference than what I get from paying $20/month with OpenAI? What's the use case?

New comment by westoque in "LLMs and Elixir: Windfall or Deathblow?"

westoque — Thu, 05 Jun 2025 14:44:46 +0000

Came here to say this. What makes a great general purpose language is not only in the programming part but also in transportability. I think Go takes the cake here. If only Elixir apps could be compiled and transported as a binary to similar systems and it works, then it would make it a great general purpose language. Until then, it's really only a good client/server language as it was intended to be.

New comment by westoque in "The Myth of Developer Obsolescence"

westoque — Tue, 27 May 2025 11:48:14 +0000

Such a great quote. Mostly true if viewed especially from a business standpoint. I for one also see code as creative expression, a form of art. I like coding because I can express a solution in a way that is elegant and nice to read for myself and others. A bit shallow but If you've read code that is written elegantly, you'll know that immediately.

New comment by westoque in "Writing an LLM from scratch, part 13 – attention heads are dumb"

westoque — Sun, 11 May 2025 20:09:16 +0000

Must be my ignorance but everytime I see explainers for LLMs similar to the post, it’s hard to believe that AGI is upon us. It just doesn’t feel that “intelligent” but again might just be my ignorance.

New comment by westoque in "Ask HN: What are you working on? (April 2025)"

westoque — Mon, 28 Apr 2025 10:49:40 +0000

> This weekend I’m working on mobile app that allows you to upload photos and it turns everything into a stitched anime (ghibli or not) with movements and eventually sound and script. Great to make mini animes from your day or travels or anything.

I vibe coded the above including everything: code, design, logos. Just did it solo. It has all error handling, video generation notifications (it takes a while) and credit system. I myself can't believe it's been done in a month with AI. It's already in closed beta in iOS and android app stores. Let me know if you want to try it out before public release.

My quoted comment above was 28 days ago. This is working on this part time and with a family.

EDIT: Added context.

New comment by westoque in "Ask HN: What are you working on? (March 2025)"

westoque — Sun, 30 Mar 2025 21:13:31 +0000

This weekend I’m working on mobile app that allows you to upload photos and it turns everything into a stitched anime (ghibli or not) with movements and eventually sound and script. Great to make mini animes from your day or travels or anything.

New comment by westoque in "Project Aardvark: reimagining AI weather prediction"

westoque — Mon, 24 Mar 2025 06:23:08 +0000

not to hijack this thread but my dad did extensive research in sea breeze and rainfall modeling and he would have loved to see these AI and machine learning advancements in weather prediction.

[0]: https://www.revistascca.unam.mx/atm/index.php/atm/article/do...

[1]: https://wmo.int/about-wmo/awards/international-meteorologica...

New comment by westoque in "Ask HN: What are you working on? (February 2025)"

westoque — Mon, 24 Feb 2025 07:43:36 +0000

working on cursor for desktop. why rely on AI agent that’s self-contained when it’s limited, can’t access the browser, can’t open apps or click around.

i simply want mine to be able to fill in forms in preview with a passport image as context. also to be able to do recurring tasks as if i was the desktop user. e.g., i’m going to bed keep working on this spreadsheet.

it’s working and built but very slow and buggy atm. uses multimodal LLMS and OCR but lots more optimizations needed. need to make it a lot faster. can demo it and need help if anyone is interested.