Dustin 11 months ago

2 days into using cline in vs studio rather than copy/pasting from pycharm into Claude UI…. And I think I like the flow better. This is nice for a big code base. Don’t have to leave the editor. More in line code editing. Still getting used to it and it has a few quirks… but feels noticeably less tedious

Dustin 11 months ago

“Side-project” has 100+ authors lol

Dustin 11 months ago

arXiv.org

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

General reasoning represents a long-standing and formidable challenge in artificial intelligence. Recent breakthroughs, exemplified by large langua...

Dustin 11 months ago

Anybody got a @Wavlake exercise playlist they like?

Dustin 11 months ago

This looks fun

Saving Satoshi

Saving Satoshi

Explore the mysteries of Satoshi and learn about bitcoin along the way.

Dustin 11 months ago

Why would you make a whole second season of Silo to end it terribly in the last 5 minutes

Dustin 11 months ago

haha this is neat #zappybird

Dustin 11 months ago

Could I get a test zap real quick?

Dustin 11 months ago

It’s broken, working on it, no more test zaps needed, thanks yall View quoted note →

Dustin 11 months ago

Refreshed my lightning setup for nostr, anybody mind throwing me a test zap?

Dustin 11 months ago

simplifying overly-complicated logic is a special kind of dopamine hit

Dustin 11 months ago

GM. Running second round of performance tests on the new version of DVMDash

Dustin 1 year ago

If you are following developments in AI, you have to follow Rao (unfortunately I don’t believe he is on Nostr yet). This analysis on inference time compute being nothing new in AI is spot-on.

#sundayharangue #neurips2024 #ai | Subbarao Kambhampati | 18 comments

𝐈𝐧𝐟𝐞𝐫𝐞𝐧𝐜𝐞 𝐓𝐢𝐦𝐞 𝐂𝐨𝐦𝐩𝐮𝐭𝐚𝐭𝐢𝐨𝐧 𝐢𝐬 𝐍𝐎𝐓 𝐧𝐞𝐰--𝐰𝐞 �...

Dustin 1 year ago

😢

Dustin 1 year ago

Custom feeds on Nostr are a killer feature I never realized I wanted. Love the new primal UX to make your own, except that it feels too hidden. If I didn’t see a vid of someone explaining how to do it, I never would have known.

Dustin 1 year ago

productivity tip for working with LLMs: 1. keep everything you've copied around with a tool like Copy 'em (on Mac) 2. star or favorite common context related to your LLM conversations 3. when prompting your llm, paste in relevant context like the codebase README, example files, etc.