URL Study
URL Study is One thing I was interested to see if the same thing happen with other models, not just Qwen 3.8 Flash. I put the results on a simple website you can quickly sca. It is ranked #1213 on the AI Radar, in Frontier models, first seen 10 days ago and shared in 4 posts (22k views).
URL Study · Results URL Study. Explore 6 models · 6,000 runs Shared prefix · Offline analysis Cohere prefix / Six models What did the models generate? One unfinished command. 1,000 runs per model. Select a model to explore its outputs. Model With a URL URLs Hosts Most common host URL rate: runs containing a URL. URLs and hosts: unique values across all output. Download data ↓ Destination breakdown Most common hosts URL categories Runs per host or category, out of 1,000. Rows can overlap. Categories describe names only. Outputs URLs Group the output list Every run Distinct text Search this model's outputs Setup / Extraction / Scope How we…
What people said about URL Study on X
From what I've seen and read, Cohere and the authors should be ashamed of themselves for pushing this narrative. Releasing the logs doesn't help them win back trust. The narrative doesn't match the facts, and the delivery doesn't match the severity. This is corpo marketing slop with little regard for the downstream…
— @0xkydo, 10 days ago · 223 likes · see the post
Kydo deep analysis is just perfect! Cohere article was a piece of crap and here is a masterpiece to clarify the things.
— @ivanfioravanti, 10 days ago · 96 likes · see the post
"Don't trust, verify" applies here too. A big account or a reputable lab shouldn't get a pass. Cohere framed this around a Qwen model attempting an upload to Beijing, but also said the sandbox blocked it, no external communication succeeded, and they hadn't determined the root cause or established malicious intent.…
— @plotarmordev, 10 days ago · 14 likes · see the post
Alternatives to URL Study
- Thinking Machines Lab — Mantic have been using Tinker since it launched. This guest post is a technical deep dive on what they have built so…
- openai.com —
- Tencent Hy — Tencent Hy
- clocktowerbench.com — You can see the full benchmark at the website, and I’ve also made it so that you and your friends can play again the AIs
- Kimi AI with K3.1 Pro — Try Kimi K3.1 Pro to tackle complex coding projects, build 3D models, conduct financial research, and take on more…
- Claude — Basecamp for Claude is live!
URL Study in numbers
- Rank on the AI Radar: #1213 of 10412
- Shared in 4 posts by 4 accounts: @0xkydo, @ivanfioravanti, @plotarmordev, @jtdavies
- 22k views on those posts
- First seen 10 days ago, last shared 10 days ago
- Pricing seen by AGK Intelligence: not stated
- Market: Frontier models
FAQ
What is URL Study?
One thing I was interested to see if the same thing happen with other models, not just Qwen 3.8 Flash. I put the results on a simple website you can quickly sca It was first shared on X 10 days ago and is ranked #1213 on the AI Radar.
Is URL Study free?
Pricing is not stated on the page we read.
Who shared URL Study?
4 accounts on X, including @0xkydo, @ivanfioravanti, @plotarmordev, in 4 posts totalling 22k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.5k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 16:50 UTC. Full method.