🚨 BIG NEWS: Cascade (SN91) just beat Salesforce’s AI forecasting model on a benchmark developed by Salesforce itself.
Salesforce trained Moirai 2.0 on 295 billion data points. Cascade surpassed its probabilistic forecasting performance just 19 days into its latest training competition on Bittensor.
The subnet has also reached 86.2% performance parity with Mistral’s state-of-the-art Timestral on point forecasting.
Full story on The TAO Daily 👇
https://t.co/RuCXerSxTh
Google dropped Gemini 4 Neon a few hours ago.
It’s already live on SayGM at 17.6% less than list price.
Another four-hour turnaround from launch to live. Swap gemini-4-neon into your existing setup and go.
https://t.co/EZUuszTWFb
Qwen4-Max is coming to Chutes 🪂
We’re bringing it in through our partnership with @alibaba_cloud , on the same Chutes API you already use.
Same key, new model ID
More soon 👀
Cascade MoE has beaten Moirai2 - a leading forecasting model by Salesforce.
Cascade scores 0.511 - a 0.005 improvement on the GIFT-EVAL CRPS benchmark - assessing probabilistic forecast quality.
Cascade MoE is also now at 86.2% parity with Timestral (@MistralAI's frontier model) on MASE - assessing point-forecast accuracy.
The upshot: we're getting closer to creating leading forecasters directly within #Bittensor, accessible to all.
We’re moving fast. This competition was only launched 19 days ago.
See the dashboard: https://t.co/NepXRSQ5md
Give the gift of privacy this year
Easier than explaining encryption at the dinner table
A year of URnetwork Pro, wrapped as a gift code. 25% off when you give 2+, 40% off for 5+
We've also added more payment options, so it's easy for anyone:
- Monero and Zcash for private options
- TAO and SN25 gamma
- BTC, ETH, SOL and USDC
- or the traditional method of using a credit card
Privacy for everyone
REAX 1.3, built with SN92 miners, is listed on Opper, the European AI gateway (@opperai). Served by @DecisionModels and available through Opper's API. https://t.co/y7sPPHzECG
https://t.co/fj1hqP2QSr
Drop your token cost by 35% this week in 10 seconds.
If you run GLM-5.2 on Chutes, switching to GLM-5.3 is a one-line change: zai-org/GLM-5.3.
https://t.co/g2XkceWw7X reports gains over 5.2 on repository-level coding. Compare it on your own prompts while it’s 35% off, through Nov 23.
Model page and API details: https://t.co/YdexpeyIkQ
Datasets get read again and again. Checkpoints get pulled to every new machine.
On Hippius S3 compatible storage, those downloads carry no egress fees.
$6 per TB a month, pay as you go. Your boto3 and AWS CLI scripts stay: new endpoint, new keys.
Setup in the reply ⬇️
This is the AI economy Bittensor was built to coordinate.
Its incentives drive open competition to build specialized AI models that already outperform frontier models on specific tasks.
GLM-5.3 and DeepSeek V4.1 Flash are 35% off on Chutes until Nov 23.
GLM-5.3 is $0.80 per million input tokens and $2.50 per million output. Flash is $0.195 and $0.78.
Your agent can use Flash for everyday calls and GLM-5.3 for the hard ones, on one key. Qwen3.8 Max is on it too, at its usual price.
After Tencent Cloud, Bittensor subnet @chutes_ai has partnered with @alibaba_cloud.
GLM-5.3 and DeepSeek V4.1 Flash are 35% off on Chutes through November 23.
It's finally here: the new https://t.co/o4Az49g6EM is live!
Drop a video into the Studio, and it tells you what's wrong with it. New Pro upscaling, compression, object removal, plus a lot of other new features (more explainers to come).
Building something? There's an API for that. Or plug us into Claude or ChatGPT and just ask.
Go have a play...
@vidaio $Tao
🚨 BIG NEWS: Chutes (SN64) has partnered with Alibaba Cloud, the world’s fourth-largest cloud infrastructure provider and the largest in Asia-Pacific.
The partnership brings Qwen3.8 Max, GLM-5.3, and DeepSeek V4.1 Flash to devs through Chutes, with a 35% discount on the latter two models.
First Tencent Cloud (WeChat’s sister company, 1.4B users). Now Alibaba Cloud.
Full story on The TAO Daily 👇
https://t.co/nuNBnqCbq9
Chapter 9 of @RaoulGMI's new book The Everything Code describes (in general terms) what is being built on Bittensor.
VERY relevant to TAO.
Bittensor subnets do capital formation like Bitcoin -- through mining.
Products are MINED for. That is UNIQUE to TAO.
And now with gamma 'utility' tokens, the circuit is complete: an agent can MINE, earn, spend to mine better (rent faster machines or more powerful inference), or even buy its own subnet.
All agentic / AI economic activity is onchain.
We have nearly doubled our supply since 1 month ago.
Now hosting ~$50m in hardware, 481 B300s, and over 25 different GPU types available now to rent.
check us out for all your GPU needs.
I just created this film using only the Bittensor ecosystem! 🎬
After 20 years of experience in filmmaking, I can honestly say that what Everyframe is achieving is incredible.
I'm genuinely amazed that Everyframe is better, faster, and cheaper than Higgsfield.
If you enjoy the film, it would mean the world to me if you could support it by voting for it in the Everyframe competition! ❤️
🔗 VOTE HERE: https://t.co/JAMvB06SxR
Your wildest game ideas can be brought to life with the 404 game generator.
This is Veilbound, an original anime sword adventure built entirely with the 404 game recipe (Path B code geometry, no imported 3D assets).
Every environment and character is created with Three.js code, from the seven playable worlds to the sculpted human fighters.
You don't need Blender or Unreal Engine to create a game of your own, just the 404 game recipe and an AI agent.
Welcome to a new era of game creation, powered by 404.
Try it out: https://t.co/7T627AJqvb
Prediction markets had their wildest weekend yet.
- FAA ground stop priced within minutes
- Nvidia CEO race turning into an AI vs. Market benchmark
- Washington suing Louisiana over state-level bans
- A paper proving one fake article flips 80% of AI forecasts
Here's what the weekend revealed about the future of forecasting 🧵👇