Jacob Kim @iamjacobkim

Making cool stuff @ https://t.co/1f9eY9lsVd. UofM alum github.com/jpoly1219 San Francisco, CA Joined September 2024

Tweets

27
Followers

24
Following

251
Likes

159

Continue @continuedev

2 days ago

Meet Instinct, our open Next Edit model, built on real-world coding patterns. → Edit faster → Stay in flow → Available in VS Code + @ollama today.

Nate Sesti @NateSesti

2 days ago

Meet Instinct, our open Next Edit model, built on real-world coding patterns. → Edit faster → Stay in flow → Available in VS Code + @ollama today.

16 30 213 48K 138

Download Gif

2 19 133 14K 45

Nate Sesti @NateSesti

2 days ago

Introducing Instinct 🐺, a new state-of-the-art open Next Edit model trained by @continuedev Runnable with @ollama and available today in VS Code

16 30 213 48K 138

Download Gif

My Programming Language Pragmatics videos on Syntax have been fun! The latest video closes the series, covering * Connections between parsing techniques and automata theory * Parsing error recovery with panic mode * Generalized LR parsers and Parsing Expression Grammars (PEGs)

2 7 72 3K 42

Download Image

Dmitrii Kovanikov @ChShersh

6 days ago

I'm working on a C++ project in my free time. No deadlines. No requirements. No rush. At times, I feel like refactoring and cleaning up the code. At other times, I just want to write dirty code as fast as possible, which just does the job. I realise that many dev practices I…

17 10 289 15K 77

zack (in SF) @zack_overflow

a week ago

Why should you learn an FP lang? Almost every programming language feature you love was invented in an FP lang decades before it became mainstream: - Garbage collection (lisp, 1950s) - Generics (ML, 1978) - Closures (scheme 1975) - Sum types and pattern matching (NPL 1970s)

13 20 270 16K 63

Jacob Kim @iamjacobkim

2 weeks ago

It's so nice to use Continue with Neovim :)

Continue @continuedev

2 weeks ago

It's so nice to use Continue with Neovim :)

10 45 250 35K 122

Download Image

0 0 2 565 0

Continue @continuedev

2 weeks ago

🚀 Continue CLI is here! The async coding agent that actually understands your codebase. Making AI continuous in your dev workflow. - Stream AI responses in real-time - Run parallel background tasks - Smart commit messages, code analysis & more

10 45 250 35K 122

Download Image

Jacob Kim @iamjacobkim

2 weeks ago

whoa y combinator👀

0 0 2 53 0

Download Image

Geoffrey Litt @geoffreylitt

2 weeks ago

Very cool to see Notion shipping offline mode, building on research we did at @inkandswitch on rich text CRDTs! If you're curious why rich text CRDTs matter, why they're hard, and how the Peritext algorithm works, here's an 8min conf talk sharing the key highlights:

Ivan Zhao @ivanhzhao

3 weeks ago

10 30 362 83K 135

16 34 400 35K 330

Download Video

nate parrott @nateparrott

10 months ago

I’ve been working on a new way to make software! It’s called 42pages. it feels like a design tool: mock something up, then LLM infers the functionality, turning it into real code. now available for anyone to try!

23 34 664 92K 557

Download Video

kepano @kepano

10 months ago

Thoughts on Omnivore shutting down: Many people enjoyed Omnivore because it was free, but being free was part of its demise. As an independent app maker, you must have a way to generate revenue or your product will die. As a user you must demand a way to pay makers for the…

kepano @kepano

2 years ago

45 219 1K 402K 577

Download Image

34 60 732 125K 327

Gabriel Elbling @gabelbling

10 months ago

Amazing graphical representation of a neural net, never seen anything like it.

49 3K 20K 1.6M 11K

Download Video

andrew blinn @disconcision

11 months ago

my OOPSLA talk yesterday on providing context for LLM code completion using typed holes: youtube.com/watch?v=-DYe8F…

1 10 47 3K 14

Mike Dodds @miike

11 months ago

I’ve done a lot of formal methods “technical sales” - trying to scope projects for Galois clients that solve their problem and fit into a budget. I gave a talk last week on some things that I learned along the way: mikedodds.github.io/files/talks/20…

14 97 394 37K 238

Download Image

Rohan Paul @rohanpaul_ai

11 months ago

Nice paper for a long read across 114 pages. "Ultimate Guide to Fine-Tuning LLMs" Some of the things they cover 📊 Fine-tuning Pipeline Outlines a seven-stage process for fine-tuning LLMs, from data preparation to deployment and maintenance. 🧠 Advanced Fine-tuning Methods…

25 525 3K 239K 5K

Download Image

tldraw @tldraw

11 months ago

let's compute

2 5 51 5K 16

Download Gif

Samuel Timbó @io_sammt

11 months ago

Very quick way to start live programming inside a worker thread:

6 12 171 12K 105

Download Video

Thorsten Ball @thorstenball

11 months ago

Wrote about how I use git.

19 29 895 116K 932

Download Image

Joel Chan | 🦣: [email protected] @JoelChan86

11 months ago

Can #toolsforthought like RoamResearch, Obsidian, and Notion actually help us think better? If so, how? In our #UIST2024 paper, we distill hypertext patterns from real-world usage that augment sensemaking by addressing temporal + spatial fragmentation of sensemaking

12 35 212 17K 164

Download Video

Wil Chung @iamwil

11 months ago

Structured programming did a lot to move programming forward, away from GOTOs. But it seems like some of the things we want to do nowadays--incremental computation, reactive systems, algebraic handlers, light cooperative concurrency--end up writing their own runtime in userland.