Avatar
plantimals
dd81a8bacbab0b5c3007d1672fb8301383b4e9583d431835985057223eb298a5
ΔC https://drss.io -- bringing back the republic of blogs. and onramp for bringing RSS content, including podcasts, into NOSTR https://npub.dev -- configure your outbox https://npub.blog -- experimenting with reading articles in a client-side only setup

interesting conversaton on AI and software development with vibe bob and dexter horthy

https://youtu.be/LEOA19Ss9lc

is anyone building a nostr-based agentic communication / orchestration app?

I don't enjoy having to say this, but nostr:nprofile1qyx8wumn8ghj7cnjvghxjmcpz4mhxue69uhk2er9dchxummnw3ezumrpdejqqgp4kg7dqtfdwhj4em3clhhzd0yz78g460y4szqqkp9smghdkaghaglmys9t your emails and notifications constantly jamming offers at me is not something sovereign people tolerate much of. your service and app have been incredibly useful. I'd really not like to have to block all notifications from your app or emails from you. but that is the next step if the panhandling doesn't stop.

this is solid advice for how to think about context engineering generally, and configuring your CLAUDE.md specifically:

https://www.humanlayer.dev/blog/writing-a-good-claude-md

self-improvising memory. it rhymes with AI

https://www.mdpi.com/1099-4300/26/6/481

context engineering seems like a valid concept. I've had good results following this approach https://github.com/humanlayer/advanced-context-engineering-for-coding-agents/blob/main/ace-fca.md

finally got my claude code set up the way I like it

https://www.youtube.com/watch?v=VddS5IWxHd8

I should go back and try 3.7, it's been a few weeks, and my methods have evolved as well. o3 has been good at research, but as a non-driving code-pairing partner, doesn't do well. it might be better with tool use, but it is cost prohibitive.