Elixir v1.20 released! Now officially a gradually typed language: Elixir type checks every single line of code, finding bugs and dead code, without developer overhead (no typing signatures) and extremely low false positives rate. Plus a faster compiler! Links and reports below.
Woot! The Tidewave gem for Rails has crossed 1M downloads: https://t.co/WK44NEvlmo
https://t.co/KNZbk8apeI is the best way to use coding agents for building web applications and we will have some more exciting updates soon! Give it a try!
Claude/Codex + Elixir + Phoenix + LiveView is such an insane superpower.
The entire stack, from low-level distributed systems modeling all the way up to the UI, is all built in one language & runtime that's easy to reason through.
pretty sure Anthropic CEO is having the best week of his life.
- Opus 4.8 released
- raised $65 billion at a $965 billion valuation
- $47B ARR vs OpenAI $25B
- officially BIGGER than OpenAI now
Claude Opus 4.8 is now available in Devin CLI ⚡️
I'm giving away 10 @devinai Max subscriptions ($200 each) for you to try it out!
Just comment below with what you're building or want to build to enter!
New in Claude Code (research preview): dynamic workflows.
Claude writes an orchestration script on the fly, then spins up a large fleet of coordinated subagents in parallel to take on your most complex tasks.
Use the word "workflow" in a prompt to get started.
Want to run Python, Go, or other languages inside your Elixir app without leaving the BEAM?
@superchris explores WebAssembly Components, wasmex, and sandboxed polyglot apps at ElixirConf US 2025.
https://t.co/pFhn6oU2EV
Chicago Early Bird tickets:
https://t.co/t8EsPImXvf
Elixir v1.20.0-rc.5 is out with our latest batch of typing and performance improvements. We are really close to the final release, so please give it a try and report what you find! https://t.co/8dWT2KdA5h
3 years using Claude every day.
Shipped production AI for 100K+ users.
The accelerant wasn't the model. It was a small library of prompts I refined into something I trust.
50 of them. $39 founders edition. https://t.co/RnFq5gCL7D
Drop this in Claude before you merge:
"Act as a Staff engineer reviewing for blast radius.
1. What depends on this path?
2. Worst realistic failure mode?
3. Reversible without backfill?
End: SAFE / MERGE WITH MITIGATION / HOLD."
49 more: https://t.co/RnFq5gDiXb
THIS GUY BUILT A PHYSICAL DEVICE THAT SITS ON YOUR DESK AND SHOWS YOUR CLAUDE CODE USAGE LIMITS IN REAL TIME
it's called clawdmeter. it runs on a $32 waveshare ESP32 dev board with a 480x480 AMOLED display
instead of checking the claude code UI or guessing how much usage you have left, you can now just glance at your desk
at this point anthropic should just mail these to us for free
but i also don't need MORE claude usage anxiety
AND it's open source on github.
this situation says EVERYTHING about the current state of the product
the claude code accessory market is booming in real time
The thing that's changed how I ship code isn't Cursor. It's not Copilot.
It's a small library of prompts I've refined into something I trust. 50 of them, $39, lifetime updates:
https://t.co/RnFq5gDiXb
The thing that's changed how I ship code isn't Cursor. It's not Copilot.
It's a small library of prompts I've refined into something I trust. 50 of them, $39, lifetime updates:
https://t.co/RnFq5gDiXb
Most AI prompts read like junior devs wrote them.
Mine don't.
50 prompts I use as a staff level engineer. Code review, debugging, refactoring, system design, docs. Plus drop-in .cursorrules and CLAUDE.md starters.
$39 founders edition →
https://t.co/RnFq5gDiXb
We’ve agreed to a partnership with @SpaceX that will substantially increase our compute capacity.
This, along with our other recent compute deals, means that we’ve been able to increase our usage limits for Claude Code and the Claude API.