I built a free Chrome extension for exactly this: Ownfeed for X. It uses AI instead of muted words. Just chat with it about what you don't want to see ("gender wars, dating discourse") and it hides those posts with the reason shown. I'm the author. Free to install:
[https://t.co/54XjadiEi1](https://t.co/dcS1WGbEUM)
Introducing Fibona Agent: the last agent humans will ever need to write.
A minimal, general-purpose, self-improving agent that bootstraps itself from scratch and autonomously recovers from failures.
Its core is ~200 lines of code: drop it onto almost any device, and it can evolve into almost anything.
Fully open source, with a free online demo available!
Learn more👇
#RSI #AIAgents #AI #OpenSource
I built Oh My Phone Use: let your AI agent tap, type, scroll, and make calls on a real iPhone.
A Mac + ESP32. No jailbreak. Open source.
Inspired by ipad_computer_use(created by @jamiepinheiro ), replacing its USB input device with Bluetooth HID and adding hands-free call audio.
https://t.co/Tvpk52rMFa
Keep useful AI experiments. Skip course pitches and recycled lists.
Same topic. Sometimes the same author. Different value to you.
With Ownfeed, inspect the reason, reveal a post, or correct the decision.
Demo: https://t.co/gb2y6nv7ws
I open X to learn something, then spend half my time scrolling past ads, “DM me for the PDF” and “this changes everything.” “Not interested” never sticks, and I won’t unfollow people who sometimes post good stuff. So I built Ownfeed: tell it what to skip, it folds it away.
Keep the people. Lose the noise.
Ads. AI hype. “DM me for the PDF.” The same recycled advice.
Tell Ownfeed what you want to skip. It folds matching X posts and replies away—without unfollowing anyone.
Your feed. Your rules.
Chrome → https://t.co/E7WAlnM44p
I open X to learn something, then spend half my time scrolling past ads, “DM me for the PDF” and “this changes everything.” “Not interested” never sticks, and I won’t unfollow people who sometimes post good stuff. So I built Ownfeed: tell it what to skip, it folds it away.
@cerebras@typesafeai Why this matters for Ownfeed: attention ranking isn't ‘is this content good?’ It is content × person × current scene. A P1 alert beats a viral post at dinner; the same viral post may win tomorrow morning. Personalization without situational context is just a prettier inbox.
Which AI deserves to interrupt your dinner? In 5 minutes: a P1 outage, a $2,480 unknown charge, a child at 39.2°C, a flight moved 80 min—plus 8 noisy alerts. @cerebras Qwen ranks all 12; @typesafeai Jev fans out 12 decisions. Code owns hard rules. Only 4 break through.
@cerebras@typesafeai My current bet: code handles non-negotiable thresholds; Jev makes cheap calibrated decisions across every alert; Qwen sees only the ambiguous shortlist and writes the rationale. The interesting benchmark isn't ‘which model wins?’ It’s ‘which model earns the right to interrupt?’
Made a small site: StoryLens
https://t.co/GG7zdnl7k3
Instead of another binary MBTI quiz, you write a few stories and paste the context into AI.
It can help explore MBTI, Jungian functions, motives, and relationship patterns.
More like talking deeply with AI about yourself.
Rough Hermes WebUI experiment: what if agents had UI isolation too?
Chat stays central, but a PPT agent, research agent, or companion agent can grow its own workspace when needed.
Very early + messy, but the direction feels exciting.
https://t.co/Vrjq8dkx0D