Your AI Research Agent & browser Sidebar for Chrome & Edge, plus iOS, Android and Desktop apps. Empowering over 10 million users around the world.

Joined June 2023
196 Photos and videos
Apr 23
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 👇 sider.ai/create/image/gpt-im… #WorldBookDay#Sider_AI
5
12
1,561
Apr 23
For the readers who wanted to escape to another world entirely. #WorldBookDay#Sider_AI
4
5
1,103
Apr 23
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. 🔗 sider.ai/create/image/gpt-im… #WorldBookDay #AI #Sider_AI
1
1
863
Apr 22
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 👇 sider.ai/create/image/gpt-im…
4
6
44
140,527
Feb 27
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.
4
2
12
2,274
Feb 18
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.
10
2
7
2,367
Feb 17
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
1
2
14
2,378
Feb 16
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 ➡️: sider.ai Check out this demo generated in Sider. Can’t wait to show you more! 😉 #Sider #Seedance2_0 #AIVideo #BetaTest #AIGC
6
7
29
17,540
Feb 12
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.
2
1
7
1,657
Feb 10
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.
2
5
1,128
Feb 10
👇 claude sonnet 3.5 and grok
1
1
833
Side-by-side model comparison is one of our favorite use cases for Artifacts. Both outputs are impressive in different ways. That's the whole point of multi-model access: pick the right tool for the job.
Feb 6
Testing the new Claude Opus 4.6 vs. Gemini 3 Pro on @Sider_AI’s Artifacts! 🚀 I love turning complex articles into "interactive reading" to boost my efficiency. With the new Claude Opus 4.6 out, I ran a head-to-head comparison. Here's the breakdown: 1/ Gemini 3 Pro: The "Gamified" Experience 🎮 The interface is incredibly clean and minimalist, but the real magic is the interactivity. It’s highly engaging and fun—honestly, it feels like playing a game. It turns passive reading into an active exploration where you actually enjoy clicking through the content. 2/ Claude Opus 4.6: The "High-Tech" Analyst 🧠 The visuals are dazzling—it has a super cool, futuristic vibe. But beyond the look, the breakdown is insanely detailed. It dissects complex concepts from multiple granular angles. It feels like examining the DNA of the article. The Verdict: Choose Gemini 3 Pro for a clean layout with a fun, game-like vibe. Choose Claude Opus 4.6 for "cooler" visuals and superior, microscopic content breakdown. Both are game-changers for "chewing" through difficult papers! 📖✨ Which style do you prefer?
1
3
7
1,244
Jan 19
10 winners. Here they are: @ShinChven @blazemhan @SarahAnnabels @riyazmd774 @TheAIColony @mattinway @RAVIKUMARSAHU78 @alifcoder @IMyselfAndMeOnX @abdulrahmanway Congrats! You've got Sider Plus for 2026. To claim: DM us your Sider UID within 7 days and we'll activate your annual plan. Didn't win? We'll be doing more of these. Stay tuned.
5
1
8
1,752
Jan 19
That's a wrap on the giveaway. Huge thanks to everyone who followed and entered. The response was way beyond what we expected. We're verifying entries now. 10 winners will be announced on Jan 19 at 14:00 UTC. Turn on notifications for @Sider_AI if you want to catch it live👀
2
1
8
1,296
Jan 14
Why do some AI features click instantly while others feel like demos searching for a use case? The pattern we've notice: 1️⃣ start with the workflow people are already doing → don't invent a new way to work. 2️⃣ remove the friction from that workflow → make the obvious thing effortless. 3️⃣ let users choose their tools → workflows outlive any single model. Example: before, people were screenshotting YouTube transcripts and pasting them into chat. Painful. So we built: drop any video, instant transcript, chat with it. We didn't invent a new way to learn from videos. We just made the existing way actually work. That's our philosophy: watch how people solve problems, then get out of their way.
3
2
11
2,108
Jan 12
Your 2026 AI toolkit, on us. We're giving 10 people free access to Sider Plus for a full year ($299 value each). That's: • Access to every major AI models including GPT-5.2, Claude 4.5, and Gemini 3 without switching tabs • Turning meetings into searchable notes with AI Recording • Research anything with 100 sources in one click and more, whenever you need them. Follow @Sider_AI to enter. Ends Jan 18, 11:59 PM UTC. Don't sleep on this!
108
29
146
5,676
26 Dec 2025
Merry Christmas! 🎄 Wishing you all a peaceful holiday, quality time with loved ones, and a great start to the new year. From all of us at Sider ✨
3
1
20
2,324
13 Dec 2025
Chrome liked us in 2023. They still like us in 2025 🙂 Just got featured in Chrome's "Standout AI Extensions of the Year" list, again. Thank you to everyone who made Sider part of their workflow. Here's to building more together.
7
3
24
2,266