Author of Crawl4AI. AI & software builder, systems thinker, founder of Kidocode. I build, analyze, and advise on hard technical problems.
Singapore
- Tweets 2,786
- Following 375
- Followers 3,124
- Likes 3,670
Another good use I found for @typesafeai’s Jev: automatically switching Claude Code models based on what I’m working on.
I built JevShift for this. It looks at the task and recent context, then picks a model. Here’s a quick demo 👇
4
3
12
733
Code and installation: github.com/unclecode/jevshif…
Next I want to do the same for thinking effort, so Jev can pick both the model and how much thinking the task needs.
2
80
i fingerprinted this "union alpha" which turned out it is (unbiased/pareto) for 15 times in 100 minutes:
02:05-02:34 UTC: a fingerprint matching hermes-4-405b in my library, 4 of 4 probes.
02:37: every probe value changes at once. new model.
02:40-03:46: a signature matching nothing i have measured. unknown model.
and in 10 of the 15 runs, the same text sent twice, seconds apart, was billed with two different token counts.
people spent the stealth week arguing whether it was openai, llama, qwen or glm. everyone was right. they were fingerprinting different models behind one name.
Not only for mystery models. Your daily OpenAI or Gemini API deserves the same check. modelprint.ai
Union Alpha is revealed on OpenRouter as @TheUnbiasedCo Pareto!
Impressive detective work and demand from the community cut this stealth period short, but you can continue using it now: openrouter.ai/unbiased/paret…
1
2
2
356
This is how I matched: modelprint fingerprints 23 known models every day, so when a mystery signature shows up i just compare. modelprint.ai/history
btw i also measured the models the viral post says are inside pareto. none of them match what it served me. rumors need measurement too :)
50
@unclecode curious about your take as your last forensic analysis was soooo to the point.
1
1
103
Unclecode (Hossein) retweeted
New in Claude Code: claude plugin eval
See what value your plugin is adding, or if it needs more work.
You can create test cases, run your plugin or skill against those test cases, score those runs, then run each case again without the plugin to see the differences.
198
422
6,114
943,316
I really wonder how will be the saas model? Here @treg_ai let us access to 2800+ saas and pay as u go!
Grok bot just killed 2800+ SaaS...
Instead of paying $600 subscriptions, build a loop with Treg
Try it at treg.to/grokbot
Cost cents per call, and tailored to just your needs
No subscription, 0% markup
Fully open sourced, git repo below 👇
3
5
581
True agent native solutions like @treg_ai are gonna be the next big thing..
1
1
26
Fabel 5.1 is where finally I feel claude code talk concise and relevant! It gets the point much faster, do not generate long essay result for a simple question and so far so good!
Fable 5.1 makes Claude Tag even more useful. Here it builds a last-minute leadership deck from a metrics spreadsheet and other data across Slack, spots a vendor report that disagrees with the numbers, and flags it before moving on.
Claude Tag is available in Slack on Team and Enterprise plans.
4
669
I think paying for all LLM should become pay as you go! Pay only when u use and not monthly subscription! Unless u r a heavy users. Is that something u look? Check this treg oss library and hosted version
Fable 5.1 + Treg = Run GTM fully in a terminal
No more $200 subscriptions, just $0.0004/call
Fable 5.1 excels at complex, long-running tasks + @treg_ai connects it to 2800+ data & tools:
Leads enrich, SEO, social, ads
Fully open sourced
No subscription, 0% markup
Try it at treg.to/fable
Git Repo below 👇
2
417
An AI agent to make sense, needs many tools, or better to make many api calls, and imagine if you want to subscribe to each of em and never never to their cap! How come you make that agent into a profitable business? The solution is a proxy that lets you pay just for the API calls you make! Here @treg_ai is doing that and more: tool routing, team account, remvoe the need to share api keys between team members and many more.
Introducing Claude for people-search
No more $600 subscriptions, juts $0.0089/lead
Claude is now the best people finder in the world
#1 on People Search Bench
Fully open source, 0% markup
Try it at treg.to/people-search
Git Repo below 👇
1
1
10
758
Ok the mystery the ox-alpha is GLM-5.3-Flash, And modelprint.ai was right! ox alpha was the first real test I did. day one, the fingerprint said glm family, 4 of 4 tokenizer probes. day five, z.ai confirmed it. today i reran it on the official glm-5.3-flash endpoint: same values, 47, 56, 60, 90. the label changed, the model did not.
anyway the guessing game was fun, but it was not the point for me. but the real question: can you fingerprint a model from its behavior alone, without access to weights? even for open models, reading the weights is slow. behavior is fast.
if that works, you get something bigger: a version control system for models that does not depend on the lab, the provider, or anyone's word. the API itself is the source of truth.
so now it is a tool, and it is open. join, contribute, add probes. and when the next mystery model appears, we run it again. modelprint.ai
Introducing GLM-5.3-Flash
- Leading capabilities at a highly competitive price
- Natively multimodal with a 1M-token context window
- A 320B-A18B model released under the MIT License
- Previously previewed as Ox Alpha, running entirely on Chinese AI chips
Blog: z.ai/blog/glm-5.3-flash
Available now across all official platforms:
Weights: huggingface.co/zai-org/GLM-5…
API: docs.z.ai/guides/llm/glm-5.3…
Coding Plan: z.ai/subscribe
ZCode: zcode.z.ai/en
Chat: chat.z.ai
AutoClaw: autoclaw.z.ai
1
3
558
Bloomberg says Z.ai confirmed it: Ox Alpha is GLM. I did not guess. 5 days ago I fingerprinted the API: the GLM family matched on all 4 tokenizer probes. MiMo 2 of 4. Gemini 1 of 9. Grok and Claude 0. The measurement called it before the label. modelprint.ai
42T tokens of Ox Alpha in 6 days
Most used model after DeepSeek Flash's 56 day run
Reveal in a few hours
2
14
11,782
update: the official name is out, glm-5.3-flash. i reran the fingerprint on the new endpoint and compared with day one of the stealth run: tokenizer probes 47, 56, 60, 90 then. 47, 56, 60, 90 now. same template delta. the label changed, the model did not. modelprint.ai/history
69
Introducing GLM-5.3-Flash
- Leading capabilities at a highly competitive price
- Natively multimodal with a 1M-token context window
- A 320B-A18B model released under the MIT License
- Previously previewed as Ox Alpha, running entirely on Chinese AI chips
Blog: z.ai/blog/glm-5.3-flash
Available now across all official platforms:
Weights: huggingface.co/zai-org/GLM-5…
API: docs.z.ai/guides/llm/glm-5.3…
Coding Plan: z.ai/subscribe
ZCode: zcode.z.ai/en
Chat: chat.z.ai
AutoClaw: autoclaw.z.ai
1,003
2,616
23,860
6,940,236
congrats on the release :) great job you guys have done here, kudos, btw for anyone curious, this was measurable from outside. i fingerprinted ox alpha on day one and the glm family matched all 4 tokenizer probes. the label came 5 days after the data:
Bloomberg says Z.ai confirmed it: Ox Alpha is GLM. I did not guess. 5 days ago I fingerprinted the API: the GLM family matched on all 4 tokenizer probes. MiMo 2 of 4. Gemini 1 of 9. Grok and Claude 0. The measurement called it before the label. modelprint.ai
136
this was my change, excited to roll it out
Claude now has a SendFeedback tool so instead of you guys having to hit /feedback and write up a report, you can just tell Claude to draft and approve it
the feedback helps us improve and understand problems, so it's very appreciated
Claude Code can now draft feedback for you.
When something fails, when Claude notices it made a mistake, or when you tell it something went wrong, it writes up the report itself.
You can review, modify and approve the feedback to send.
168
35
1,210
170,226
🇨🇳 Ox Alpha was not some mysterious model that appeared out of nowhere after all as it was built in China by Zhipu, and the company is now going to release the weights - Bloomberg
*I believe it matters far more than just another strong benchmark result.
➡️ The model exploded on OpenRouter within days, even overtaking DeepSeek on some usage metrics. Ox Alpha is currently free but developers seem perfectly willing to use a Chinese model at scale, including for coding, reasoning and agentic tasks.
💰 Much cheaper intelligence would be extremely bullish for AI adoption without necessarily being equally bullish for the economic rents of model labs. Compute demand could still explode but how value will ultimately be split between semiconductors, hyperscalers, model developers and applications could become the real deal.
The one missing piece is still Ox Alpha’s true cost. If it turns out to be materially cheaper, we may have to ask whether the US is investing hundreds of billions of dollars into a technology whose economic rents are being commoditized far faster than expected.
*Link: bloomberg.com/news/articles/…
3
7
45
8,792
the interesting part: this was detectable without any inside source. i fingerprinted the api 5 days ago and it matched the glm family on all 4 probes:
Bloomberg says Z.ai confirmed it: Ox Alpha is GLM. I did not guess. 5 days ago I fingerprinted the API: the GLM family matched on all 4 tokenizer probes. MiMo 2 of 4. Gemini 1 of 9. Grok and Claude 0. The measurement called it before the label. modelprint.ai
110
Ox Alpha is GLM. @Zai_org just confirmed it and told Bloomberg the weights go public tonight.
We already have it on six free routes in Codex, and the thing we kept worrying about was that a free preview can get pulled without notice and nobody would even say who owned the model.
1m context, 131k output, multimodal.
Probably another MIT drop like the rest of the GLM, though nobody has said. zai-org on huggingface, where every GLM has landed.
The routes can still dry up on us but nobody can pull the model back after Wednesday.
看起来我可以公开了，是的，Ox Alpha是 @Zai_org 的模型！
这个是一个非常惊人的模型，因为在此之前Zai刚刚发布了GLM5.3这个开源的SOTA模型。
当我第一次测试时，其实我对于它没有抱有什么期待，因为在此之前Zai的视觉模型已经更久没有更新了。
但实际的效果大大超出了我的预期！
同时它的成本和速度也非常优秀（请记住这是一个Flash模型）！
我们最快会在今天见到这个模型（是个开源模型～）！
8
1
48
10,759
fun detail: the routes were telling on it the whole time. fingerprinted it 5 days ago, glm 4 of 4 probes:
Bloomberg says Z.ai confirmed it: Ox Alpha is GLM. I did not guess. 5 days ago I fingerprinted the API: the GLM family matched on all 4 tokenizer probes. MiMo 2 of 4. Gemini 1 of 9. Grok and Claude 0. The measurement called it before the label. modelprint.ai
1
1
198
mysterious "ox alpha" is apparently a GLM iteration (likely 5.3 flash)
and is expected to be announced today, with open weights dropping tonight.
guess their CEO really meant it when he told Musk they'd ship a Mythos-level open-weight model before year-end
The new AI model that’s swept to the top of online usage charts with high performance at zero cost was created by China’s Z.AI, also known as Zhipu bloomberg.com/news/articles/…
13
6
130
9,176
not even apparently, its measurable. i fingerprinted the endpoint 5 days ago and glm matched all 4 tokenizer probes:
Bloomberg says Z.ai confirmed it: Ox Alpha is GLM. I did not guess. 5 days ago I fingerprinted the API: the GLM family matched on all 4 tokenizer probes. MiMo 2 of 4. Gemini 1 of 9. Grok and Claude 0. The measurement called it before the label. modelprint.ai
119
🚨Ox Alpha has officially been revealed
Zai have confirmed Ox Alpha is theirs and a new GLM model, with the weights dropping tonight
Looks like the GLM 5.3 Flash theory aged pretty well
44
72
1,460
272,716
and it was verifiable before the confirmation. my fingerprint gave glm 4 of 4 probes, gemini 1 of 9, claude and grok 0. measurement first, label later:
Bloomberg says Z.ai confirmed it: Ox Alpha is GLM. I did not guess. 5 days ago I fingerprinted the API: the GLM family matched on all 4 tokenizer probes. MiMo 2 of 4. Gemini 1 of 9. Grok and Claude 0. The measurement called it before the label. modelprint.ai
1
580