zackproser

Well, this particular moron reads hacker news, too, and actually has a formal diagnosis for both autism and severe ADHD. But thank you for calling me a moron because someone took the article I published for free to be of help to similar folks. Your day is obviously off to a better start than mine. Le sigh indeed.

Maybe, maybe that's FUD...I can't predict the future.

Me too :)

I feel it will get there in short order..but for the time being I feel that we'll be doing some combination of scattershot smaller & maintenance tasks across Codex while continuing to build and do serious refactoring in an IDE...

Not trying to be snarky, but the example prompt you provided is about 1/15th the length and detail of prompts I usually send when working with Cursor.

I tend to exhaustively detail what I want, including package names and versions because I've been to that movie before...

This

Ah nicely done! I was just about to build this

Great game

Had the same experience. Cursor ux and also Zed are designed to make copy pasta'ing back and forth obsolete. It's certainly more comfortable to iterate within the IDE, for me.

Very cool. Thanks for sharing

Few months in with Cursor as my daily driver and I completely agree. I cannot unsee my productivity gains.

Excited to try Zed, but FWIW, this is exactly Cursor's default behavior if you use the side chat panel

Yeah +1, the current top LLMs do pretty well with TypeScript

https://zackproser.com/blog/mnist-pytorch-hand-drawn-digit-r...

Did this recently.

Looks great on my old pixel, Dolev!

Very nice

Here's a real world example of a custom RAG pipeline built with Langchain

https://zackproser.com/chat

I did a full tutorial with source code that's linked at the top of that page ^

Fwiw I think it's a good idea to build with and without Langchain for deeper understanding.

https://www.pinecone.io/blog/pain-poetry-python/

This was the write up I did last year

But increasingly I prefer to ask LLMs the same things I used to search Google for...

Meaningful velocity increase while keeping quality high enough for the services to function in production and charge users..

What you say tracks - but I'm wondering what happens if they manage to unlock some meaningful velocity increase to the point where they can begin tackling other domains and shuttling out products at a higher rate...Agree with your thoughts on search - it's f'ing unusable now and frustrating to look at.

After reading this I'm wondering how the indy code autocomplete tools are going to be able to compete longterm with this giant feedback rich data machine Google has built...do engineering orgs of sufficient scale ultimately hoard their tooling for competitive advantage, thereby leaving independent players to cater to developers outside of Google? Feels like yes...but plenty of inventions trickle out in various forms.

Having a similar experience but in the other direction. I have a lot of backend and frontend development experience but no ml background. Being able to ask stupid questions to get further faster has been making difference for me.

And, for what it's worth, I also share because I love building things and learning. I taught myself how to code using free resources online, so it felt perfectly natural to publish and open-source everything I figured out.

I also wouldn't mind eventually making some money off delivering reliable value to others.

This is helpful - thank you for sharing. I've been down a mental rabbit hole lately and reached similar conclusions.

+1 - I picked up my first semi-stalker / email harasser recently from blogging and sending out a newsletter about apps I build and open-source. Pretty weird experience.

Good suggestion - thanks!

I appreciate and use asciinema, but a big plus one for VHS.

I like being able to store my tapes in a repo and edit them:

https://github.com/zackproser/vhs-scratch

And as the official VHS docs show you can do even more interesting things with CI/CD

This very much gels with my own experience.

It was my first time working with Pulumi and despite not being sure yet how I truly feel about TypeScript - it was a pleasant experience to be able to use programming constructs I'm already familiar with.

I think that's the real leg up that Pulumi has on Terraform.

With HCL / Terraform - you're supposed to be dealing with configuration, but - we also need loops and maps - so we sort of get a mix between a configuration language and a programming language.

As soon as you need to do something even moderately complex you're in a world of pain (automatically deploying and validating Route 53 records via DNS in AWS, I'm looking at you...).

Thanks for your question!

The images were generated via DALL-E - so they're not technically "autogenerated". They were created using a generative model, however.

The content itself definitely was not generated by an LLM - although that feels like a low-effort comment =/ What in particular felt LLM-generated to you?

I think this is on the main page because being able to set 3 environment variables and run `pulumi up` to get to a production-ready system in your own AWS account, without having to purchase anything, is a massive time-saver for anyone with a high-scale use cases that wants to use Pinecone's vector database.

Thanks so much for your support

We are finding that JavaScript is an often overlooked language for working in AI:

https://www.pinecone.io/learn/javascript-ai/

There's also a very nice synergy between using a language like JavaScript (many are familiar enough to read through and understand what's happening) and the type safety that TypeScript introduces.

We are seeing a lot of interest in working with Typescript hence why many of our examples are TypeScript applications.

I appreciate the feedback, but we may need to agree to disagree on this one :)

As a professional dev, I enjoy articles with eye candy and AI-generated images, especially those with a pixel-art bent make me happy.