Books • Learning • Self Growth • Wisdom
Joined July 2022
- Tweets28.9K
- Following24
- Followers193K
- Likes64.7K
Library Path retweeted
The reason we’d try Riverside Agents: it's an AI production team built only for video.
Our last tool did everything a bit and video worst of all. @RiversidedotFM
🤝 Paid partnership
Meet Riverside Agents, the first AI production team built only for video.
Producer preps the session, Editor creates the full edit, Clipper cuts the best moments, and Marketer gets it live.
They’re experts at video and know how to take your content to the next level. You call the shots.
Watch the demo:
Library Path retweeted
Waiting between edit rounds is where video projects stall.
Riverside Agents sending a change back while you're still in the flow matters more than any single agent.
🤝 Paid partnership
Meet Riverside Agents, the first AI production team built only for video.
Producer preps the session, Editor creates the full edit, Clipper cuts the best moments, and Marketer gets it live.
They’re experts at video and know how to take your content to the next level. You call the shots.
Watch the demo:
Library Path retweeted
Riverside Agents launches Monday: four agents, one per production stage, and nothing posts without the creator's sign-off.
Long episodes will be the real test
🤝 Paid partnership
Meet Riverside Agents, the first AI production team built only for video.
Producer preps the session, Editor creates the full edit, Clipper cuts the best moments, and Marketer gets it live.
They’re experts at video and know how to take your content to the next level. You call the shots.
Watch the demo:
Library Path retweeted
For years, you’ve been texting AI.
Starting this fall, it texts you first.
Anthropic just unveiled Claude Duet, an assistant that works in the background and only contacts you when something needs your attention.
Here’s how it works:
Library Path retweeted
If you own an agency, I'm begging you:
• Pay 20-30% over market rate
• Stop believing your closer when he blames the leads
• Stop being your own ops manager
• Stop thinking info will fix your agency
If you want to get past $100k/mo…
Here's what I'd do:
Library Path retweeted
2027 is around the corner.
If I had to start from 0 and become a profitable trader by the end of 2026...
This is exactly what I’d do:
Library Path retweeted
🚨Breaking: Nvidia CEO Jensen Huang said that AI will create more millionaires in the next 5 years than the internet did in the last 20.
Here is how some people are actually using AI + social media to create revenue today
Library Path retweeted
If you have a 9-5, I’m begging you:
• Start a home cleaning business
• Charge clients $200 per clean
• Hire a cleaner from Indeed
• Pay them & keep the rest
If you want to be financially free…
Follow this exact blueprint:
Library Path retweeted
I wanted this week's real AI-in-fashion story, not the hype, so I saved the whole job as a Loop.
In @Teamily_AI, a Loop chains AI agents into a workflow you can run again anytime. Mine finds the story, writes it in my voice, fact-checks every line, then sends it back to me for review before anything goes out.
On the first run, it caught a claim the source couldn't back up. Then I added one rule: no emojis, under 200 characters. When I ran the Loop again, the post came back publish-ready at 199 characters. I never repeated the rule.
A chatbot gives me one answer and forgets my rules. This Loop remembers them every time it runs.
Watch it 👇
Library Path retweeted
Context grows. Memory doesn’t.
Rock Matrix open-sourced EdgeRock-4B, a text and image reasoning model with attention memory fixed at 72 MiB from 4K to 256K tokens.
Rock Memory Anchors let it recall details long after they leave the local window. EdgeRock-4B achieves 82.9% mean pass@1 on AIME 2024-2026, versus at most 18.8% for the evaluated bounded-state models, including 14B-class models.
By combining recurrent state, local attention, and Rock Memory Anchors (RMA), EdgeRock-4B is designed to preserve important information without letting its attention KV cache grow with every token. The result is a different approach to long-context reasoning, built to make memory use more predictable and efficient.
For AI developers, this could mean serving more requests on the same hardware while supporting longer reasoning tasks. Feel free to download EdgeRock-4B and give it a try!
