creative director @LabyrnthCo - AI/Web3 video content creator, educational videos | member of @aiscwork

Joined December 2021
how to build your first ai agent in claude code start with one job you repeat every week example: turning a new ai update into a verified x post create 3 files → best-posts.md → writing-rules.md → trusted-sources.md then ask claude code “create a project agent called content-researcher give it only file reading and web search tools when i send a topic, check primary sources and return → 5 verified facts → 3 opening lines → 1 finished post cite every claim and mark anything you cannot verify” test it on 3 topics you already know well every time it gets something wrong, add the correction to its instructions your first agent is ready when you can give it a topic instead of explaining the whole job again
25
3
50
1,035
asking claude to “write me a post” is the weakest way to use it build one content agent with your best posts, video transcripts, audience questions and the words you never use then use the same agent for research, video outlines, drafts and final review it starts from your work instead of guessing your voice every time
36
6
87
4,804
the speed wasn’t the best thing about parallel agents i tested it after posting this three agents handled one research task at once and opening each result separately made the final answer much easier to check
chatgpt just stopped working alone astra pro can now split one request across multiple agents and run them in parallel research, analysis and production can all happen at the same time
47
1
55
3,229
chatgpt just stopped working alone astra pro can now split one request across multiple agents and run them in parallel research, analysis and production can all happen at the same time
GPT-6 Astra Pro in ChatGPT got an upgrade with faster responses and improved use of plugins and tools. And now, multiple agents can tackle different parts of a task in parallel. You can follow each agent’s progress and open completed tasks to review their work. Now available to Pro users in the Chat tab.
34
4
2
56
11,802
tesla fell 12% over the past year but a dip-buying strategy tested by @StingrayFI returned 27% with 6 profitable trades the idea was simple, buy below the lower bollinger band and sell on the rebound you can test strategies like this just by sending a text of course, 6 trades aren’t enough to prove it’ll work again
🤝 Paid partnership
51
9
99
4,799
Biscuit retweeted
millions of people vote on arena to pick the better ai arena is now worth $3.1B and the voters got $0
60
7
138
5,299
millions of people vote on arena to pick the better ai arena is now worth $3.1B and the voters got $0
60
7
138
5,299
Biscuit retweeted
grok bot finds new clients while you sleep almost nobody is using it this way
61
2
128
5,534
ai solving math gets the headline openai is putting $5m behind the less visible work: verifying, understanding and extending what models produce until other researchers can build on a result, it’s a demo, not a discovery
We want to support the mathematics community in turning progress in AI into deeper human understanding and new discoveries. To support that goal, we are contributing $5 million to a new Simons Foundation initiative to help mathematicians examine, understand, and build on results produced by AI, including the results we recently published. The funding, managed and awarded by the @SimonsFdn will support workshops, conferences, and special programs. We will also provide access to our models and computing resources to Simons Foundation-supported researchers.
23
1
1
40
1,618
grok bot finds new clients while you sleep almost nobody is using it this way
61
2
128
5,534
the next big ai businesses won’t sell agents small business use in europe is up 8x businesses don’t want another ai tool they want the work done
European businesses are rapidly expanding their use of AI agents. More than half of the AI use among our EU enterprise and business customers now involves these tools, and the number of small business users has grown 8x across the region. Our latest Economic Research report explores Europe’s shift toward agentic AI—and the opportunity to turn broader adoption into deeper use. openai.com/index/the-eus-nex…
45
1
74
4,817
Biscuit retweeted
zach yadegari is 19 and just raised $10M his new ai is free that is the problem
49
1
108
6,381
you finally get an AI video looking right and it randomly adds music you never asked for then you have to generate the whole thing again and hope nothing else changes @MireloAI’s SFX 2.0 lets you redo the sound without changing the video or dialogue i’ve wasted enough credits on this exact problem
🤝 Paid partnership
AI Videos finally sound real. Introducing Mirelo SFX 2.0. It watches your video, cuts the music you never prompted, keeps the dialogue, and builds a full sound design synced to the action and consistent across any length clips. You’ve made it look right. We’ll make it sound right. Live today through our API, on @runwayml and @fal. Other platforms coming soon. (Thread)
51
95
5,894
zach yadegari is 19 and just raised $10M his new ai is free that is the problem
49
1
108
6,381
Biscuit retweeted
Meta’s AI agent just hit a wall that money can’t fix. Watch this before you trust an AI with anything 👇
38
2
94
7,140
why this article is gold if you want to earn with ai it gives you a 7-day plan to choose something people pay for, learn what you need and build a sample you can show them there’s a prompt for your learning plan, steps to review your work and a full day for turning it into an offer
33
8
83
3,979
AI agents are starting to handle payments, bookings and actual business tasks but what happens when one makes an expensive mistake? @harborai_ just raised $10M to build insurance for risks involving AI agents i’m surprised more companies aren’t working on this already
🤝 Paid partnership
AI needs clear liability. Today, @harborai_ comes out of stealth with a $10M seed round led by @Base10Partners, @AbstractVC and @8vc. @elechi_v0, Cristian, Luis and I started @harborai_ with one mission: to insure the agentic economy. Rather than pacing the frontier, we believe the solution lies in pushing this frontier with real skin in the game.
48
4
88
3,949
Meta’s AI agent just hit a wall that money can’t fix. Watch this before you trust an AI with anything 👇
38
2
94
7,140
meta wants the work we already give claude and chatgpt muse wonder is launching with access through muse, muse code and the api i’d start with a half-built app, the error logs and the previous attempts at fixing it see whether it can finish the job without making me start over
Introducing Muse Wonder, our new family of frontier models with state of the art performance for personal and professional agentic work.
27
3
1
70
1,390