Hacker News: mattew

New comment by mattew in "An update on recent Claude Code quality reports"

mattew — Thu, 23 Apr 2026 20:22:51 +0000

It was odd that there was no mention of the forced adaptive reasoning in the article. My guess is they don't have enough compute to do anything else here.

New comment by mattew in "The Lovable Shopify Integration"

mattew — Tue, 21 Oct 2025 15:51:49 +0000

Looks like Lovable is expanding out to platform specific development with their just announced Shopify Integration

The Lovable Shopify Integration

mattew — Tue, 21 Oct 2025 15:51:49 +0000

Article URL: https://lovable.dev/blog/shopify-integration

Comments URL: https://news.ycombinator.com/item?id=45657293

Points: 2

# Comments: 1

New comment by mattew in "Ask HN: Cursor or Windsurf?"

mattew — Mon, 12 May 2025 12:41:44 +0000

I’ve only played with Junie and Aider so far and like the approach the Junie agent takes of reading the code to understand it vs the Aider approach of using the repo map to understand the codebase.

New comment by mattew in "I've been using Claude Code for a couple of days"

mattew — Sun, 09 Mar 2025 18:21:27 +0000

I saw something mentioned of voice control in aider.chat

New comment by mattew in "Show HN: Flow – A dynamic task engine for building AI agents"

mattew — Wed, 04 Dec 2024 05:21:20 +0000

Thanks!

New comment by mattew in "Show HN: Flow – A dynamic task engine for building AI agents"

mattew — Tue, 03 Dec 2024 13:14:59 +0000

Thanks for sharing. Can you add a simple example that is more concrete and less abstrwct to the docs? It would be easier for people to understand if you did.

New comment by mattew in "Financial market applications of LLMs"

mattew — Sun, 21 Apr 2024 14:19:35 +0000

This makes sense. Can you clarify what you mean by journal management in this context?

New comment by mattew in "Ask HN: Is anybody getting value from AI Agents? How so?"

mattew — Sun, 31 Mar 2024 17:45:32 +0000

I’ve found the OpenAI assistants API not really up to snuff in terms of predictable behavior yet.

That said, I’m very bullish on agents overall though and expect that once they get their assistants behaving a bit more predictably we will see some cool stuff.

It’s really quite magical to see one of these think through how to solve a problem, use custom tools that you implement to help solve it, and come to a solution.

New comment by mattew in "Show HN: Fructose – LLM calls as strongly typed functions"

mattew — Wed, 06 Mar 2024 19:32:51 +0000

Good stuff. How does this compare to Instructor? I’ve been using this extensively

https://jxnl.github.io/instructor/

New comment by mattew in "Why Custom GPTs are better than plugins"

mattew — Wed, 31 Jan 2024 13:54:30 +0000

This right here is actually the coolest part about developing with LLMs. You just changed the functionality with a sentence rather than a config file, or writing code. It’s great to be able to break out functionalty into things that can be easily handled in English (or your human language of choice) or what should be done in code.

New comment by mattew in "Leonard vs. Pepsico, Inc"

mattew — Sun, 12 Nov 2023 14:10:00 +0000

I also think of pudding guy every time something like this comes up.

New comment by mattew in "A 6 channel GPS receiver from 1993"

mattew — Sat, 04 Nov 2023 18:44:16 +0000

That’s right. It was selective availability and you used differential post correction to clean the data up and get accurate locations for the data you were capturing. Thanks for the correction!

New comment by mattew in "A 6 channel GPS receiver from 1993"

mattew — Sat, 04 Nov 2023 18:35:55 +0000

The interesting thing about GPS back then was that the location data you got back were randomly slightly incorrect every time you got a reading. I’m pretty sure this was so it wasn’t useful for military purposes.

I think it was called differential post correction but if you had a base station with a known location you could snap your incorrect points to the difference generated at that correction level and get the true location after the fact.

Source: GIS major in late 90s when this stuff was a lot more magical

New comment by mattew in "The Killer Use Case for LLMs Is Summarization"

mattew — Thu, 19 Oct 2023 18:08:25 +0000

Don’t forget classification. Even the zero shot classification can be quite decent, but put a solid prompt together, or fine tune a set of examples and it’s way easier with an LLM than previous methods in my experience.

New comment by mattew in "Every database will become a vector database sooner or later"

mattew — Tue, 03 Oct 2023 12:34:47 +0000

Maybe I’ve been using PostgreSQL too long but when faced with the choice of adding vector support to PostgreSQL or using a new technology, my first choice was to start with the PostgreSQL addition.

I’m not criticizing the specialized case for a true vector database, but for most workloads I agree that the big database players will be the right choice for many users.

New comment by mattew in "Ask HN: SaaS pricing pages with high prices and not “contact sales”"

mattew — Sat, 30 Sep 2023 18:14:57 +0000

I’m fine if you have a “contact us” for a true enterprise plan, but companies that have actual pricing plans should post them. I way prefer to buy from SaaS companies that display their pricing up front rather than trying to get me on the phone to talk with an account executive.

I’m not scared to pay serious money for a service, but putting your service behind a sales person is more than likely going to cost you my business.

New comment by mattew in "Weird things you can buy online"

mattew — Fri, 29 Sep 2023 16:25:55 +0000

Haha - I posted this one too. Always good for a laugh reading the reviews for this one.

New comment by mattew in "Weird things you can buy online"

mattew — Fri, 29 Sep 2023 14:06:21 +0000

The 55 gallon drum of lube on Amazon always cracks me up. The reviews are classic.

https://www.amazon.com/Passion-Lubes-Natural-Water-Based-Lub...

New comment by mattew in "Transformers as Support Vector Machines"

mattew — Sun, 03 Sep 2023 15:25:28 +0000

What I find entertaining/confounding is how difficult the abstracts to these new AI papers are to understand. It feels like academia is pushing this style, so it’s hard to blame the authors since they have to play the game.

For reference I have an undergrad degree in computer science, have been working professionally for 25 years, and am fairly data centric in my work.

I’m hoping when I run this through GPT4 to get an explanation for a mortal software developer something sensible comes out the other end.