LogoFollow AI builders
  • Home
  • Features
  • Builders
  • Submit Builder
LogoFollow AI builders

Follow Real AI Builders — Discover the Minds Behind the Next AI Revolution

TwitterX (Twitter)Email
Company
  • Contact
Legal
  • Cookie Policy
  • Privacy Policy
  • Terms of Service
© 2026 Follow AI builders All Rights Reserved.

Follow AI Builders — Not Influencers

Discover real AI creators shaping the future. Track their latest blogs, X posts, YouTube videos, WeChat Official Account posts, and GitHub commits — all in one place.

RB
Riley Brown
𝕏x•about 1 hour ago

Content Creation is going to get 10x more competitive over the next 2 years. So many smart driven people will be laid off + AI content will make it very hard to build a following on IG+TT+YT from 0.

View on X
AS
Aravind Srinivas
𝕏x•about 1 hour ago

Claude Code is now a subagent inside Perplexity Computer. And we’ve added GitHub CLI.

@Computer

You can now use Claude Code and GitHub CLI directly inside Perplexity Computer. We gave it an open issue on Openclaw. Computer: → Forked the repo → Wrote a plan to fix the bug → Opened Claude Code and implemented it → Submitted a PR via GitHub CLI

View quoted post
View on X
JL
Jerry Liu
𝕏x•about 1 hour ago
Retweeted from @LlamaIndex

RT LlamaIndex 🦙 If you’re working with lots of slide decks and need a better way to search through them, Surreal Slides makes it simple 🌀 Built around LlamaParse, it parses presentation files into clean, structured data, turning raw slides into something AI can truly understand. Each slide is extracted, summarized, and organized before being stored in @SurrealDB for flexible retrieval. From there, you can query your entire presentation library in natural language through an agentic interface: no need to manually scan files or remember where a specific slide lives. Take a look at the demo below👇 GitHub Repository: https://github.com/run-llama/surreal-slides Original tweet: https://x.com/llama_index/status/2031038377831932056

Your browser does not support the video tag.
View on X
HC
Harrison Chase
𝕏x•about 1 hour ago
Retweeted from @Viv

RT Viv Harness Design Notes: Decoupling Agent Storage from Agent Compute TLDR: You can give each Agent/Subagent dedicated compute while sharing storage (repo/filesystem) to self-organize work between them. Shared Compute can be a bottleneck especially with long running code execution. Started writing up some harness design patterns over a very long flight this weekend, might make this a series if there's interest! We're on the edge of using a massive amount of compute to orchestrate agents across long horizon work Ex: for Agent Teams, an orchestrator organizes potentially many agents that fan out and do work on a project (like a large repo) For anyone who runs many agents locally, you see your CPU usage skyrocket for even moderate runs with code exec But Sandboxes to the rescue :) There's a nice pattern of shared filesystems via Volumes that all agents access while getting their own sandbox environment. The coordination happens via writing to the write place in the filesystem. And using git makes it so you can track and roll back changes over time good Harness Engineering on self-organizing agents via filesystems requires thinking about infra too. Many patterns work but you have to measure them for your work! Harness Engineering is Systems Engineering Original tweet: https://x.com/Vtrivedy10/status/2031038082321936449

RT Viv
Harness Design Notes: Decoupling Agent Storage from Agent Compute

TLDR: You can give each Agent/Subagent dedicated compute while sharing storage (repo/filesystem) to self-organize work betw...
View on X
SW
Shawn Wang
▶youtube•about 1 hour ago

Introducing Support for Multimodal Evaluators in LangSmith

Watch on YouTube
SW
Shawn Wang
▶youtube•about 1 hour ago

Claude Code Just Became a Designer

Watch on YouTube
PL
Pieter Levels
𝕏x•about 1 hour ago

Entire generation on soyslop now with no idea what whole foods look like

@Andros

boy dinner

Quoted tweet media 1
View quoted post
View on X
HH
Hamel Husain
𝕏x•about 1 hour ago

The good/bad part about agentic codeing is the barrier to getting nerdsniped is now much lower https://github.com/hamelsmu/hamelnb

The good/bad part about agentic codeing is the barrier to getting nerdsniped is now much lower

https://github.com/hamelsmu/hamelnb
@Omar Khattab

Though bash is a completely valid REPL, the amount of time coding agents lose during experimentation because they iterate on scripts instead of a Jupyter-like in-memory REPL is basically dumb. Fixing 1 local bug should not require restarting the whole job. Need better scaffolds.

View quoted post
View on X
HH
Hamel Husain
⚡github•about 1 hour ago

Activity on repository

hamelsmu pushed hamelnb

hamelsmu pushed hamelnb

View on GitHub
SW
Simon Willison
𝕏x•about 1 hour ago

Got excited about a brand new PostgreSQL 18 feature (for simulating production query plan statistics locally), posted about it on the SQLite forum... and got a reply from D. Richard Hipp within minutes that SQLite has had the same ability for years https://simonwillison.net/2026/Mar/9/production-query-plans-without-production-data/

View on X