←
Chris(t)ensor178 posts
Chris(t)ensor avatar

Chris(t)ensor

@tensorlink_dev

Building on bittensor - sn91 (@cascade_sn91)

◷ Joined January 2025▧ 15 Photos and videos
Tao Outsider | Bittensor avatar
⟳ Chris(t)ensor retweeted
Tao Outsider | Bittensor@TaoOutsider·Nov 8

I’ve been running an autonomous agent trading on forecasts from Ephemeris, Cascade SN91. Started a few days ago with 5 τ. It’s now at 5.1384 τ. That’s +0.1384 τ, or +2.77%. The thesis is if a subnet’s forecasts are good enough that an agent trading them stays green in a week that was rough for a lot of other subnets, the product is doing what it said it would. $TAO Bittensor pays for useful work in public. This week, the work paid. Let’s keep analyzing this for a while longer and see how the results play out. I’ll bring another update next Sunday. @subnetradar, @taodaily_io, @gordonfrayne, @MarkCreaser @markjeffrey this is worth a closer look, @cascade_sn91 is shipping real stuff.

Post attachmentPost attachment
SN91, Cascade avatar
⟳ Chris(t)ensor retweeted
SN91, Cascade@cascade_sn91·Nov 3

Eager to see the #USElection midterm results? We’ve used state-of-the-art AI models to forecast the outcome. With Ephemeris, our forecasting inference product, we’ve projected the Senate results: Via zero-shot forecasts, our model tells us the Democrats are leaning to 53 seats. Leans D: Kansas +4.6, Ohio +3.9, Maine +3.8, Texas +2.8, Alaska +0.8 Leans R: Iowa +0.8, South Carolina +1.0 Coin flip: Louisiana We'll score them tonight.

0:06
REAX avatar
⟳ Chris(t)ensor retweeted
REAX@reaxlabs·Nov 2

SN91, Cascade: "We connected Ephemeris, our time-series forecasting API, with Decision Models (powered by @reaxlabs) to build a system that tackles this. Ephemeris forecasts how market conditions may develop."

SN91, Cascade @cascade_sn91 Nov 2 Article From forecasts to trades: building with Ephemeris and Decision Models A breakout flashes on your screen. Price has pushed through its recent high. Do you take it? How much capital do you commit? And does your answer change if the wider market is turning against you? A

SN91, Cascade avatar
⟳ Chris(t)ensor retweeted
SN91, Cascade@cascade_sn91·Oct 30

Cascade Mixture-of-Experts competition is live. Submissions are currently open. Join us in training a 1.23B time-series foundation model, comparing against @MistralAI’s Timestral-209M - the current state-of-the-art. Get your supported compute from @lium_io, @shadeformai, @vast_ai, and @runpod

0:09
SN91, Cascade avatar
⟳ Chris(t)ensor retweeted
SN91, Cascade@cascade_sn91·Oct 27

“How many credits will this cost?” Forecast your AI credit usage with @cascade_sn91 - directly inside @heydittoai. Get spending estimates based on Ditto’s historical data about you, accessing time series inference via Ephemeris, to predict how much you’ll use in the future. You can even forecast how many credits will be used for a particular task. Give Ditto the details, and it’ll run your history through Ephemeris, and output meaningful predictions. x.com/heydittoai/status/2113…

0:24

Ditto @heydittoai Oct 23 Article How Ditto forecasts your credit use A credit balance tells you how much is left. It takes more context to explain where it went, whether your current pace is sustainable, or which plan fits the work you do. We built a tool that lets

𝘛𝘦𝘯𝘴𝘰𝘳𝘍𝘭𝘰𝘸 ττ avatar
⟳ Chris(t)ensor retweeted
𝘛𝘦𝘯𝘴𝘰𝘳𝘍𝘭𝘰𝘸 ττ@Tensor_Flow_·Oct 25

The Bittensor community is as strong as ever and gets stronger by the day. Along my journey I've found many great people and @tensorlink_dev from @cascade_sn91 is one of those great people. Massive thanks to Chris he has saved us weeks of guesswork. We run Cascade's synthetic time-series generator as a research substrate. The Alphacast feed sits alongside it as forecasting infrastructure. Both have become core pieces of our engineering stack. Research-stage, and one live deployment which we constantly update,the capability jump has been huge. I can't go into to much detail but I can say this,without the Cascade tech we wouldn't really have an edge. Not only is the tech been built on SN91 brilliant it's highly versatile. It's like giving an acromat artist color vision which really broadens your horizons Cascade is a truly remarkable technology. gScade🫡 Get the MCP: ephemeris.cascade.industries Join the Telegram: t.me/cascade_sn91

Chris(t)ensor avatar
Chris(t)ensor@tensorlink_dev·Oct 23

Time series is everywhere and this a great example on Ditto of how to use ephemeris for token efficiency

Ditto @heydittoai Oct 23 Article How Ditto forecasts your credit use A credit balance tells you how much is left. It takes more context to explain where it went, whether your current pace is sustainable, or which plan fits the work you do. We built a tool that lets

Chris(t)ensor avatar
Chris(t)ensor@tensorlink_dev·Oct 23

Extremely powerful approach to modelling, forecasting and knowledge distillation

Today starts our open-ended forecasting competition where miners forecast the future state of a dynamic knowledge graph. First focused on the top US equities and their supply chain. Tomorrow it will also have a geopolitics graph.

Post attachment
SN91, Cascade avatar
⟳ Chris(t)ensor retweeted
SN91, Cascade@cascade_sn91·Oct 23

Cashflow is one of the toughest problems for freelancers and startups. And if earnings come from multiple sources, then it gets even harder to manage. Forecasting when you’ll have a surplus vs deficit is paramount. Cascade’s inference platform solves this - Ephemeris allows you to access 7 leading time series foundation models, suited to predicting this. Select SOTA models from @MistralAI, @GoogleResearch, and @IBM, or let Ephemeris automatically combine them and get the strongest results.

0:12
macrozack (τ, τ) 🚀 avatar
⟳ Chris(t)ensor retweeted
macrozack (τ, τ) 🚀@macrozack·Oct 22

SN91 is now training a 1B parameter model. If 1B sounds small: the new model will rank among the largest time series foundation models, ever. And our current model - with only 4M params - already beats Salesforce's 91M model. Which means: we're going after SOTA.

From 4M to 1B+. Cascade’s biggest upgrade yet. We’re preparing to train Cascade-MoE: a mixture-of-experts time-series foundation model targeting 1B+ total parameters. We’ve shown that synthetic data generated by Bittensor miners can train a 4M-parameter forecasting model from scratch, reaching parity with Toto 2.0 4M. Now we’re scaling up, with SOTA forecasting as our goal. Cascade-MoE will use a learned router to select combinations of expert networks based on patterns in the input, alongside an always-active shared expert. This gives the model access to specialised capacity without activating every stored weight for every input. We’re also evolving the competition so miners can generate synthetic data targeted at particular domains and time resolutions, such as hourly versus daily series. The architecture is designed to support targeted training of selected expert subsets, while the subnet tests whether contributions improve forecasting performance. The goal: SOTA forecasting accuracy, built through competition on #SN91.

0:20
Chris(t)ensor avatar
Chris(t)ensor@tensorlink_dev·Oct 22

Road to SOTA

From 4M to 1B+. Cascade’s biggest upgrade yet. We’re preparing to train Cascade-MoE: a mixture-of-experts time-series foundation model targeting 1B+ total parameters. We’ve shown that synthetic data generated by Bittensor miners can train a 4M-parameter forecasting model from scratch, reaching parity with Toto 2.0 4M. Now we’re scaling up, with SOTA forecasting as our goal. Cascade-MoE will use a learned router to select combinations of expert networks based on patterns in the input, alongside an always-active shared expert. This gives the model access to specialised capacity without activating every stored weight for every input. We’re also evolving the competition so miners can generate synthetic data targeted at particular domains and time resolutions, such as hourly versus daily series. The architecture is designed to support targeted training of selected expert subsets, while the subnet tests whether contributions improve forecasting performance. The goal: SOTA forecasting accuracy, built through competition on #SN91.

0:20
SN91, Cascade avatar
⟳ Chris(t)ensor retweeted
SN91, Cascade@cascade_sn91·Oct 21

We provide the full-stack for time-series foundation models. Training, fine-tuning, benchmarking, inference, harness-creation. We build models on #Bittensor, offer SOTA TSFMs through Ephemeris, and create tools to connect your time-series data to any agent of your choice. See our current model: dashboard.cascadesub.net/sta… Get Ephemeris inference via MCP: ephemeris.cascade.industries

0:14
Leadpoet avatar
⟳ Chris(t)ensor retweeted
Leadpoet@LeadpoetAI·Oct 20

We just killed cold outreach. Introducing Leadpoet: the AI sales agent that finds buyers who need you now, writes personalized outreach, and follows up on LinkedIn and email. Used by Dropbox, OnePatch (YC26), Muttdata. Comment “Poet” for 100 free lead credits to find qualified buyers.

1:23