Viewing profile — mattew

I mostly use Opus for skill development. Once I have a solid skill implementation with a good eval, I move ongoing execution to a cheaper model running under Goose. With the eval y…

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.

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

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 underst…

I saw something mentioned of voice control in aider.chat

Thanks!

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.

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

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…

Good stuff. How does this compare to Instructor? I’ve been using this extensively https://jxnl.github.io/instructor/

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 t…

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

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 th…

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…

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 …

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 Pos…

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 …

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

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...

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 th…

I’ve thought recently about using LLMs as part of the data build process or ML projects. This looks like a decent start in that direction by providing access to an LLM from scikit

That blew my mind as well. I would have thought a much larger dataset would have been required.

I’m thinking about data for an LLM from a different angle for ecommerce analytics. 1. Build up a set of instructions on how to interpret a particular type of data in the system pro…