people dont realize how much time making videos takes beyond editing..
watch hours of footage, find clips, write posts, make thumbnails.. sometimes this takes longer than editing itself
This Riverside Agents just launched to handle all this, and nothing goes live without approval
what used to take days could now take hours..
🤝 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:
Introducing WeatherNext 3️⃣— our most advanced global weather AI model yet from @GoogleDeepmind and @GoogleResearch
With prediction capabilities that are up to 5x sharper than WeatherNext 2, the model generates a forecast with high spatial resolution in order to catch fast-evolving rainstorms, map local temperature shifts, and even help wind farms predict their power output.
So, how does it do that?
While traditional weather models rely on massive, physics-based supercomputer simulations that can carry a 6-hour forecast lag, WeatherNext 3 leverages live geostationary satellite observations as inputs and trains directly on real-world surface and atmospheric observations.
By pulling this raw satellite data, it’s able to update the global forecast every single hour. And because weather develops at lightning speed, these quick, detailed insights can help bring more localized forecasting to billions of people and local businesses, especially in regions that are historically underserved due to the high costs of traditional weather forecasting models.
new stream, following paper on fiber-level cloth detail kuiwuchn.github.io/rtfr.html, using math, #threejs and little baking in Blender,
demo: knitstream.vercel.app/
video: youtube.com/live/nZk9gI4y8E8
This guy used Grok Bot to build a Quant Trend system and it made $1,519 a day on Polymarket
The result is already +$268,805 PnL in 177 days with about $173 per average trade, repeating the same setup 27 times every hour across BTC "Up or Down" markets
Several AI agents work together as one algorithm:
1. Aroon detects whether BTC is repeatedly making fresh highs or lows
The bot measures how recently the strongest high and low appeared:
Aroon Up = 100 × (N - Periods Since High) / N
Aroon Down = 100 × (N - Periods Since Low) / N
Then:
Aroon Up > Aroon Down → Up bias
Aroon Down > Aroon Up → Down bias
A fresh high pushes Aroon Up toward 100
A fresh low does the same for Aroon Down
2. The Aroon Oscillator measures how dominant that trend actually is
The system combines both readings:
Aroon Oscillator = Aroon Up - Aroon Down
Then:
Strong positive value → stronger Up signal
Strong negative value → stronger Down signal
When both sides stay close together, the move has no clear control and the setup is ignored
This is the first agent that will create a trading bot strategy for you and then build it:join.horizon.trade/Quant
This trader’s Polymarket account: PBot-6
Most profitable trades:
$2,796 → $6,360 (+$3,564)
$1,630 → $3,989 (+$2,359)
$1,300 → $3,602 (+$2,302)
The system uses Aroon to identify the active trend and the oscillator to measure how strongly one side controls it
Sherif retweeted
Here's a simple demo of why and when you'd use #Jev from @typesafeai.
It doesn't generate text. It doesn't mean it can't hallucinate but if you know you have certain classification paths, it can classify with lightning speed and low cost and onward a query to the step where a traditional LLM is better.
Here, I do a walkthrough of a 100 questions with Jev versus Haiku and show why and when I'd use it. Not shown in video is the cost:
- for 2x 100-query run, Jev was $0.006 and Haiku was $0.019
- The second run was 1 question at a time, whereas the one shown is 4 questions at a time, but this did not affect latency too much
The original thread for what I was applying this on is at: xitter.twitterapi.xyz/SiddhitSanghavi/status…
So what use cases do you have for Jev?
Sherif retweeted
Congrats to @CompleteSkeptic & @typesafeai , I didn't know how much I needed this model until I got access. My Simplified Breakdown of Jev 👇
Sherif retweeted
what if copy/paste was smart?
powered by @typesafeai jev
it feels like every computer interaction will get rewritten
Sherif retweeted
I built a voice controlled computer-use for my mac using @typesafeai's Jev and it's INSANE how fast it is!
I can dictate "open the notes app and create..." and the app opens before I even finish my sentence.
Sherif retweeted
Seedance 2.5 on Higgsfield AI
Prompt:
A tired woman in <image1> in a loose tank top and sleep shorts, slow habitual movement. Slightly smeared eyeliner, bare feet, heavy posture, detached face.
ENVIRONMENT: A cramped cluttered apartment with an unmade mattress, scattered clothes, a narrow hallway, a damp bathroom with dim tile reflections, and a tiny kitchen crowded with dirty dishes and empty bottles. Warm practical lamps mix with sickly green neon leaking through blinds and door glass, turning the rooms into a humid late-night maze.
MOOD: Detached routine turns quietly uncanny, as if an unseen presence is floating above her and waiting for her to notice.
COLOR LOGIC: Matrix Green Look
CAMERA: POV overhead follow in a strict bird's eye view, locked directly above the top of her head at all times, perfectly centered over her body from start to finish, floating smoothly with no shake, tilt, angle drift, or side offset, passing through ceilings and door frames as one uninterrupted camera event. 24mm wide, digital clean look, locked overhead tracking package throughout.
SCENE:
She wakes on the mattress. Sits up under the lens.
Still centered under the lens, reaches to the floor. Picks up the cigarette and lighter. Places the cigarette between her lips. Lights it. Drops the lighter on the mattress. Stands up with the cigarette still with her.
Under the same overhead lock, crosses the cluttered room.
The lens tracks directly above her into the narrow hallway. Enters the bathroom.
Still pinned overhead, keeps the cigarette in her right hand. Extends that arm away from the running water. Leans on the sink. Turns on the tap with her left hand. Splashes water onto her face with her left hand.
The overhead follow carries her back out of the bathroom into the hallway. Moves along the hallway past the bathroom door. Turns into the tiny kitchen.
Still centered under the camera, keeps the cigarette with her. Reaches across the dirty dishes with her free hand. Picks up a glass from the counter.
Stops exactly under the lens. Holds the cigarette in her right hand and the glass in her left hand.
The lens stays fixed above her. Freezes. Looks right. Looks left. Takes a drag from the cigarette. Snaps her head straight up into the lens. Blows smoke toward the camera. Locks eye contact.
SFX: lighter flick, inhale, faint city hum, refrigerator buzz, soft bare footsteps, water run. Sodium amber particles, toxic green neon reflect off tile, smoke, bottles, and damp surface.
Sherif retweeted
introducing Space: a cloud filesystem built for work
instead of waiting, you can:
→ mount one persistent drive for you and your agents
→ instantly work in the cloud like local
→ only stream the bytes you need
→ no compression on any of your files
try it for yourself today
Sherif retweeted
Introducing ObsidianUI
- React & Tailwind CSS Components Library
- Agents MCP
- Redesigned UI
GPT 6 Sol cooked well - in less than 20 mins
video made with HyperFrames with only a few prompts! pretty good results so far
copy the source or install via shadcn-cli
Free, open source, no sign-up
Sherif retweeted
Chamath talks about how he uses customized AI agents and skills for his own life and work.
- a Nash equilibrium AI agent for his high-stakes negotiations
- a personal AI world model for major life decisions
- he has effectively built a persistent microservices around a foundation model
----
From "Chamath Palihapitiya" YouTube channel, (link in comment)

























