Hacker News: ashu1461

New comment by ashu1461 in "Decisions API is in public beta"

ashu1461 — Wed, 07 Oct 2026 14:55:03 +0000

If there is reasoning involved, the output can't be this fast ?

New comment by ashu1461 in "Decisions API is in public beta"

ashu1461 — Wed, 07 Oct 2026 02:31:57 +0000

Output tokens anyway will be minimal in a decision scenario, so even if you use responses API the cost will be less.

New comment by ashu1461 in "Decisions API is in public beta"

ashu1461 — Wed, 07 Oct 2026 01:31:20 +0000

If we compare this with using the older solution of writing a prompt to find out the answer of the classification

- Cost : It is the same for both scenarios $0.10 per 1M tokens

- Speed : decisions is 10x faster than responses API

- Quality : I guess if we compare with luna which is a pretty good model it itself, both will be at par

So essentially it has to do more with speed vs any other factor.

New comment by ashu1461 in "Building an (almost) fully self-hosted, sandboxed, agentic software factory"

ashu1461 — Sat, 22 Aug 2026 22:28:40 +0000

This is a good insight.

While doing local development where your environment is already setup and dependencies are installed doing something like this seems viable after the initial effort.

But how would this work in a software-factory setup, where coding agents run on fresh VMs or when using something like Claude Code on the web? How do you quickly recreate the required environment and dependencies there?

New comment by ashu1461 in "Vibe Writing"

ashu1461 — Fri, 21 Aug 2026 19:42:32 +0000

I have found AI that autocompletes (like the GitHub Copilot VS code extension) to be more effective in these scenarios than AI that generates entire sections.

With autocomplete, I'm still writing the content and simply using AI to phrase it better. With generation, it may produce something that was not part of my original idea and once it is there, it becomes very hard to remove its bias.

New comment by ashu1461 in "Show HN: Declarative-forms – await an object the way prompt() awaits a string"

ashu1461 — Fri, 21 Aug 2026 19:33:12 +0000

It might be just me, but this is how frontend libraries should have been structured in the first place unlike relying on callbacks / state change hooks.

Linearly written code is much easier to understand and scan.

New comment by ashu1461 in "Building an (almost) fully self-hosted, sandboxed, agentic software factory"

ashu1461 — Fri, 21 Aug 2026 19:28:07 +0000

I don't know most of these tools either, but that is why I find posts like this useful. Don't you end up learning something new in cases like this?

New comment by ashu1461 in "Building an (almost) fully self-hosted, sandboxed, agentic software factory"

ashu1461 — Fri, 21 Aug 2026 19:25:52 +0000

In such systems, producing code is the easy part, verification is hard. Verification via test cases just feels like the same agent validating its own assumptions.

Wondering what the actual verification loop looks like once you start taking these systems to production.

New comment by ashu1461 in "Kobo can run apps now"

ashu1461 — Fri, 21 Aug 2026 18:44:16 +0000

Isn't everything vibecoded ?

New comment by ashu1461 in "Kobo can run apps now"

ashu1461 — Fri, 21 Aug 2026 18:42:56 +0000

In my personal experience, this can help in case the books are little technical and you have to switch to my laptop/mobile to get more information about the topic, which ends up consuming more time it should.

New comment by ashu1461 in "Hacking with Claude on a $27 smart watch"

ashu1461 — Thu, 20 Aug 2026 18:00:38 +0000

I just did a side project to show how many calories I consumed on my garmin watch

https://ashu1461.com/posts/a-calorie-tracker-on-my-garmin-wa...

Claude really helped in doing the heavy lifting.

You can't stop people from using AI

ashu1461 — Wed, 19 Aug 2026 18:35:32 +0000

Article URL: https://ashu1461.com/posts/you-cant-stop-people-from-using-ai/

Comments URL: https://news.ycombinator.com/item?id=49365427

Points: 7

# Comments: 0

Calorie tracker for my Garmin watch

ashu1461 — Sat, 15 Aug 2026 21:51:54 +0000

Article URL: https://ashu1461.com/posts/a-calorie-tracker-on-my-garmin-watch/

Comments URL: https://news.ycombinator.com/item?id=49314658

Points: 2

# Comments: 0

New comment by ashu1461 in "Don't classify, hallucinate!"

ashu1461 — Fri, 14 Aug 2026 13:30:12 +0000

Had stumbled on this library in the past

https://github.com/aurelio-labs/semantic-router

I guess it is based on the same fundamentals as well.

New comment by ashu1461 in "Don't classify, hallucinate!"

ashu1461 — Fri, 14 Aug 2026 13:28:16 +0000

It can do that on run time, but it does not store data like that. The data is typically stored as embeddings in which it is hard to query data in a structured form. Example give me all products whose price is less than 200$ vs suggest me products for my spouse's birthday.

New comment by ashu1461 in "Don't classify, hallucinate"

ashu1461 — Fri, 14 Aug 2026 13:26:50 +0000

With agentic commerce protocol / unified commerce protocol open ai and gemini are trying to solve this problem.

The idea is to make structured queries using these protocols which can be used to fetch top products matching the user needs instead of just relying on semantic search.

https://developers.openai.com/commerce/specs/file-upload/pro...

New comment by ashu1461 in "Anthropic to start embedding invisible watermarks"

ashu1461 — Wed, 12 Aug 2026 00:58:43 +0000

Ascii can't but I guess most of the text on the internet is unicode which easily can be.

New comment by ashu1461 in "Mojo 1.0"

ashu1461 — Wed, 12 Aug 2026 00:32:55 +0000

Pydantic is mainly about making Python strongly typed.

Mojo addresses the actual need to write code in other languages, such as C++ or CUDA, for low level and hardware specific work.

But I wonder if it has already missed the AI hype cycle, when a lot of low level code is being written. I'm not sure how the developer ecosystem will react now.

New comment by ashu1461 in "Nvidia Nemotron 3.5 Lightning and NeMo Switchyard"

ashu1461 — Wed, 12 Aug 2026 00:26:28 +0000

Right now there is a stark difference between what smaller models can do and bigger models can do.

Smaller models are suitable for simple tasks like classification / summarisation while larger models are better in agentic capabilities.

New comment by ashu1461 in "Nvidia Nemotron 3.5 Lightning and NeMo Switchyard"

ashu1461 — Wed, 12 Aug 2026 00:22:53 +0000

it takes more effort to write with conciseness