A shared brain for your whole team.
Joined May 2026
- Tweets 36
- Following 8
- Followers 751
- Likes 32
6 Photos and videos
gbrain.io retweeted
Jun 4
One fun thing about building stuff with AI is how you can make really amazing internal tooling.
This is a @gbrainio LiveView tool where I can perform manual upgrades to brains or follow along as an agent calls the same upgrade tooling to perform machine upgrades.
1
1
11
1,046
Will be upgrading to this shortly.
Jun 3
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.
3
342
You can also spin up a hosted brain at gbrain.io if you want this up and running in under 90s.
GBrain is free MIT-licensed open source and available at github.com/garrytan/gbrain
I use it with my own 350k markdown knowledge LLM wiki OpenClaw/Hermes Agent setup. You can have my setup in about 30 minutes. (The agent does most of the work!)
1
324
This is already built into @gbrainio because people want an easy way to switch between personal brains and various business/org brains.
Hey @sama, love ChatGPT and all of the progress. Could you guys look at multiple account support? It's a PITA to switch between my enterprise and personal account all the time.
1
1
340
gbrain.io retweeted
May 29
I'm using it to build @gbrainio. You can't really tell from this screenshot, but Elixir is connected to a bunch of different servers coordinating agents, servers, & UI seamlessly. It's bonkers.
When scrolling down, LiveView debounces the "recent message" cursor on the server.
1
2
7
1,922
gbrain.io retweeted
May 27
Tokenmaxing some changes for the core @gbrainio harness tonight that I hope fill make for a sane OpenClaw.
The idea is to give people the raw power of OpenClaw & gbrain while making it easy to recover from oopsies.
Like a souped up Lambo with a great insurance policy.
🏎️💨
1
1
8
938
Gbrain is always getting better.
Early review of GBrain - I am working on it day-to-day, dropped more than 20 PRs in the last week, so it is a young codebase growing quickly and changing. This is great feedback.
GBrain getting better every day
vectorize.io/articles/gbrain…
1
1
15
16,603
It’s also much harder to find a good domain these days.
May 24
Q: How are job postings for software engineers rising rapidly despite AI agents automating coding?
A: Because there’s far more code to manage than ever before. We’re already seeing a 14x YoY increase in GitHub commits, and it’s accelerating.
AI has dramatically lowered the cost of writing code, so it’s now being used across far more businesses, applications, and use cases.
We’re at the beginning of a massive productivity boom driven by the proliferation of bespoke software throughout the entire economy.
Coding has been AI’s breakout use case this year. The fact that it’s increased demand for software engineers — rather than decreased it — should call into question the entire “AI will cause mass job loss” narrative.
915
If you told be a year ago I’d be cooking code, I’d have thought you were crazy.
"let it cook" is the line Anthropic engineers just repeated all day at Code with Claude London.
Boris Cherny said it in the keynote. Ravi Trivedi said it in the next talk. Katelyn Lesse said it at the panel.
it means: stop micromanaging the prompts. write the routine. let Claude prompt itself.
his framing:
> routines are higher-order prompts.
> the runtime is shipped.
> the prompts are the bottleneck.
what they didn't say on stage: most routines die without 3 specific properties.
i tested 30. 9 made it. the other 21 violated one of the three.
the 9 that survived are in the article.
all verbatim, just copy-paste.
worth more than $300 of "prompt engineering consulting" before you build anything.
3
1,184
At some level you just have to embrace it. If it looks good, who cares?
BTW my images are all AI generated too.
Is it perfect? Far from it, but when devs run into something that looks crappy, they spend a bit of extra time prompting something better.
What’s new is old again.
10
2
20
19,541
Stop drinking almond milk ya’ll
May 19
Over at Substack, @JoshEakle asks: "It's 2026, and I have yet to see an anti-almond farm protest."
3
2
14
15,700
The other thing you need are strong guard rails.
I’m written in Elixir, so there’s a bunch of tests, test coverage analysis, module boundary enforcement, and linting to keep things in the rails.
The current 1400 test suite runs in about 2s.
May 20
When your agent tells you to look at or do something on its behalf to figure out why its not working, close the loop by giving it the the tools it needs to look at it and fix it itself.
This is a core skill you have to learn to build stuff with AI.
That and strong guardrails.
1
4
8
7,527
idk about you guys, but when I build stuff these days I try to maximize the amount of markdown that's committed.
Still a decent amount of imperative code to build out all the blast radii infrastructure, but inside those load bearing walls is markdown that writes code.
Realization: in the past, we wrote code to call LLMs
Today, we write prompts and skill files for LLMs to execute code.
Tomorrow? Yet unwritten. We will find out soon.
2
10
4,830
We're still so early.
The NYT is predictably tearing down Reese Witherspoon for encouraging moms to try AI before they ingest the anti-AI pablum as truth
Instead of linking to the NYT op-ed, I think you should watch this video and encourage you to follow Reese Witherspoon on Instagram
1
2,750
