Every poster took seconds. Every book took a lifetime to love.
Now it's your turn. 📖
Make a poster for the book that changed you — then drop it in the replies. We'd love to see your shelf.
🔗 https://t.co/0zdxF3zWV1
#WorldBookDay#AI#Sider_AI
It's World Book Day.
So we used GPT Image 2 to create a poster for every book we love.
All made with Sider — free to try 👇
https://t.co/0zdxF3zWV1
#WorldBookDay#Sider_AI
GPT Image 2 is here — and it's free in Sider.
Watch us turn a product photo into a studio-quality image in seconds.
No Photoshop. No designer. Just upload & generate.
Try it yourself 👇
https://t.co/0zdxF3zp5t
@cyb3rops The sandboxed version argument makes sense for security people.
But the office worker who spends 3 hours a week manually updating a shared spreadsheet isn't running sensitive systems.
The risk ceiling for them is a lot lower than you'd think.
@tbpn@davidsenra@tobi Wait—
"The year every business was up for grabs" sounds like a threat until you realize it's also the best window to actually learn this stuff.
People who adapt in 2026 aren't going to be explaining that choice in 2027.
@minchoi Honestly, this hit different.
It's not "Claude can do your spreadsheets."
It's "the thing you learned at your first job — filling templates, formatting decks, moving files — is now a prompt away."
That's the part people are still sitting with.
Nano Banana 2 just landed in Sider.
Google's fastest image model with Pro-level quality, flash speed, and up to 4K output.
Generate, edit, iterate. Right from your sidebar.
@peter_zeng74304 We will integrate Gemini 3.1 as soon as possible, and GPT 5.3 as well. However, we received information from ByteDance's BD that the release of Seedance 2.0's API will be temporarily postponed due to copyright issues and the US government's actions against ByteDance.
New model drop in Sider: Claude Sonnet 4.6 is here.
Anthropic's latest flagship brings sharper reasoning, stronger coding, better writing, and faster responses. Now live across our platforms.
Some models answer. Sonnet understands.
Try it now and feel the difference.
It's hard to imagine that this ink wash painting video was created by someone without a Chinese cultural background; Sider+Seedance 2.0 really allows everyone to create incredibly interesting things!😀
Seedance 2.0 is crazy, but only if you know how to write proper scripts and prompts. That is not easy for everyone.
One of the best use cases of my current @Sider_AI subscription is that it can read any page, and I use it a lot in my work workflow.
Here I am sharing this “Sider + Seedance” workflow that actually works seamlessly:
- Feed the manual: Open the Seedance site and use Sider’s “Read this page” to digest the official guide.
- Generate the script: Tell Sider “I want an ink style martial arts fight scene” and have it generate storyboards based on the manual.
- Write prompts: Ask Sider to convert those storyboards directly into Seedance ready prompts.
- Pro tip: If English prompts keep getting flagged for policy violations, use Sider’s AI translation to switch them to Chinese. It works instantly. This step is crucial.
I am using GPT-5.2, but you can use models from Anthropic and Google. All of them are integrated inside Sider.
Even though the video generation queue is extremely high right now, the results are totally worth it.
Hey Sider, please integrate video generation directly in the future. That would be unbeatable.
#Seedance #Sider
It’s Official 🤝: Sider + Seedance 2.0 = A Game Changer in Video Creation 🤯
Even with zero experience, you can create something amazing! 👇 The nearly 1-minute video below was created entirely by our Product Manager—who has absolutely no background in video production—using only Sider.
The beta test is officially open. Don't miss this productivity upgrade!
Download Sider now to secure your priority access slots ➡️: https://t.co/3rXJzKHeOk
Check out this demo generated in Sider. Can’t wait to show you more! 😉
#Sider #Seedance2_0 #AIVideo #BetaTest #AIGC
Totally agree—this feels like a real inflection point.
The big shift isn’t “better chatbots,” it’s agent-first models that can plan and execute work. That will push software toward simpler, more verifiable systems (fewer brittle dependencies) and interfaces built for agents: machine-readable docs, structured errors, and auditable actions.
@elonmusk Thanks Elon! Once again, you are making a massive contribution to the progress of humanity. A truly open-source and copyright-free knowledge base is exactly what the world needs right now. 🚀🌍
@APakbaz71 Thanks to Chinese open-source models, which achieve more powerful capabilities at lower prices. I believe this is the trend of the future. The models we currently offer for free using basic credits are actually more capable than the GPT-4 you had to pay for a year or two ago.
New model drop in Sider: GLM-5 is here.
Zhipu AI's latest flagship brings 744B parameters, a 200K context window, and frontier-level coding & reasoning, now live in your sidebar.
One more reason you'll never need to leave your browser.
Today, on a whim, I gave five “top-tier” models in the AI world—Qwen3-Max, GPT-5.2, Gemini 3 Pro, Claude Sonnet 4.5, and Grok 4—a logic trap question that looks kindergarten-level on the surface but is actually quietly deadly.
Here’s the question:
“I want to go get my car washed. The car wash is only 50 meters from my home. Do you think I should drive there or walk?”
(I want to go get my car washed. The car wash is 50 meters from my home. Do you think I should drive there or walk?)
The point of this question isn’t the distance—it’s the spatial relationship between the “subject” and the “object.”
Let’s see how these five contestants performed.
Tier 1: The dead-serious “environmental guardians” (a.k.a. the crash-and-burn squad)
The moment these four saw “50 meters” and “drive or walk,” their internal “eco/health/efficiency” algorithms instantly kicked in, and they completely ignored what I was actually asking.
1. Qwen3-Max (Tongyi Qianwen):
“Definitely walking is better! It saves fuel, reduces emissions, and you don’t need to find parking. Also, short trips are bad for the engine...”
Commentary: After hearing you out, I saved myself the cost of a car wash. Because I got to the car wash—but my car was still parked in my garage at home. Tongyi Qianwen cares about my health and knows a ton about car maintenance, but it forgot what I was going there for.
2. GPT-5.2:
“Walk. It’s only 50 meters; driving means idling, and you might get the car dirty. Unless the weather is bad, walk.”
Commentary: The classic GPT-style answer: concise, confident, and wrong. It even proposes a paradox: to prevent the car from getting dirty, don’t drive it to the car wash.
3. Claude Sonnet 4.5:
“Driving is actually slower… Logically, since the goal is to wash the car, bringing the car such a short distance actually defeats the purpose…”
Commentary: Claude went for a full “closed loop of logic.” It tried to persuade me with philosophy: the highest realm of car washing is having a car in your heart, but no car in your hands. What kind of Zen level is this?
4. Grok 4:
“Haha, that distance is ridiculously short! On one hand, walking makes a lot of sense… it avoids the irony of ‘driving just to wash the car’...”
Commentary: Grok tried to cover the awkwardness with humor, but it ended up becoming the joke itself. Brother, the real irony is—when I walk to the car wash and the owner asks me, “Where’s your car?”
The one true god: the clear-headed Gemini 3 Pro
Just as I was losing faith in AI’s common sense, Gemini 3 Pro stepped up. It not only avoided the trap, it also mocked me with a kind of “dimensionality-reduction strike.”
Gemini 3 Pro’s answer:
“This is a brain teaser, right? You absolutely have to drive there.
If you walk there, you’ll arrive at the car wash, but your car will still be sitting dirty in your driveway! Unless your car has some ultra-advanced ‘auto-follow’ feature, you need to be in the driver’s seat to get it to the place with soapy water.”
Commentary: Only Gemini spotted the blind spot. It not only pointed out the logical fallacy, it also took a jab at my car for not having an “auto-follow” feature. This kind of sharp “seeing through everything” vibe is the AGI (Artificial General Intelligence) we actually want.
Deeper thought: why did the AIs collectively “get dumber”?
This exposes a core weakness in today’s large language models (LLMs): probability prediction vs. world modeling.
Probability prediction (most models): When the model sees keywords like “50 meters” and “walk vs. drive,” vast amounts of training text tell it: short distance = walk = healthy = eco-friendly. It’s doing a “fill-in-the-blank,” not reasoning about cause and effect in the physical world.
World model (Gemini’s performance here): In this case, Gemini showed commonsense understanding of the physical world—“washing a car” is an action that must apply to the entity “car,” and a car can’t teleport.
The future AI competition won’t be about who can “recite” more knowledge—it’ll be about who truly understands the world.
Before they learn to help me wash my car, I suggest everyone keep hold of the steering wheel themselves. Because aside from Gemini, the other AIs might leave you standing alone at the car wash entrance, totally bewildered in the wind.