One of the best ways to stay on top of software right now is to leverage Grok to query what people are discussing related to a given topic you're thinking about and want to stay on top of
1
187
Keith Galli retweeted
last call: heroic lofi for vibe coding. twenty tracks, about 47 minutes, made to code to.
youtu.be/Lq1RZYq4caM
Here's my technique for adversarial code review if I'm driving from Codex: "Review this with claude".
And when I'm in Claude: "Review this with codex".
Models know how to to kick off a review using the cli. Know how to take turns. Know how to settle an argument.
No magic.
A big challenge right now is managing all the different agents and providing each the right context & permissions. Some tasks in Claude, other tasks in Codex. Use of Cursor occasionally.
I have team agents running Openclaw & Hermes in a VPS.
How do you keep it all organized?
9
4
360
Hey @OpenAI, am I missing a setting for dot in Slack? I explicitly allowed teammate collaboration, but they still get an owner-only warning. A teammate's direct question went unanswered for 10 min until I nudged dot. How do I get it to reliably respond to teammates?
🤖 Made with AI
1
289
Back on YouTube!! Check out the new vid 😎
Teaching my Homie AI (Claude Code Tutorial)
youtu.be/lO4iiiRhrIA
1
228
Would love if @X could fix the problem where people post a fake story above a video to make it seem like it's true. This is like every other post in my feed 😢
1
243
Just published a 5-hour course on building analytics reports, slideshows, dashboards & websites using Python & Quarto Markdown!
Quarto has been a super helpful in my freelance work recently, turn Python analyses into client-ready deliverables in minutes instead of hours.
Hosting a data analysis livestream (& fundraiser) on Friday at 12pm EST!
youtube.com/live/m6v7a3sZlL8…
I'm partnering with @GiveInternet to help provide laptops & internet access to students in need. 1.2B people globally can't afford internet despite living in areas with coverage.
Hope to see you there!
9
745
I participated in a Kaggle Competition testing Google Gemini's 1M+ token context window!
Using a government API, I pulled data on all recent Congressional bills. I then leveraged Gemini's caching feature to load the data (600k+ tokens) once into the model's memory. This made it efficient to run multiple queries without needing to fully reload the data each time.
Check out my quick video walkthrough 🤠
youtu.be/3TrXbSR01NE?si=lPUw…
12
795













