Founder & CEO, Continuous Intelligence. Building models that learn from the world as it unfolds in continuous time. Email: x@benwalker.co.uk
London
Joined February 2022
- Tweets187
- Following192
- Followers227
- Likes145
Pinned Tweet
Today we're launching ci-proto, @Continu_Intel's first time-series foundation model.
- #1 on fev-bench, ahead of Google, Amazon and Mistral
- 64× the context window of others
- Open weights and available for commercial use
Proud of the team. This is just the beginning.
Go try it on your own data now for free: github.com/continuousintelli…
1
10
334
If you work with time-series data and want early access to our next models as a design partner, visit our site: continuousintelligence.co.uk…
6
195
Maybe it is time to make these models a reality 👀
Delighted to share that I have passed my DPhil viva for my thesis, Advances in Neural Controlled Differential Equations.
This thesis lays the foundation for making continuous-time machine learning practical. Now it is time to make these models a reality.
Thank you to Terry Lyons for the unending guidance, support, and encouragement throughout my DPhil.
Many thanks to my examiners, Marc Deisenroth and Stephen Roberts, for the spirited discussion and invaluable advice on my work.
Our new paper Chess-World-Model has been accepted to NeurIPS 2026 Evaluations & Datasets!
The most interesting result?
Models that perform almost perfectly on real games fail badly when tested on games generated from random legal moves.
Same rules. Same legal moves. Wildly different performance.
🧵 1/5
1
1
174
Even after matching the random games to the human-game length distribution, the gap remains.
This shows that near-perfect held-out performance does not necessarily mean a model has learned the underlying state-transition rules.
4/5
1
13
Want to know more? The paper, code, and dataset are now all available publicly.
Paper:
arxiv.org/abs/2605.30100
Code:
github.com/Benjamin-Walker/C…
Dataset:
doi.org/10.7910/DVN/C8TEVB
5/5
1
29
Ben Walker retweeted
Six papers at NeurIPS 2026 from a team of four: that's 1.5 papers per person!
Among them is our inaugural Continuous Intelligence paper, Time Flies When You Parallelise.
Preprint coming soon. In the meantime, here is a brief intro to are all six papers!
Really enjoyed speaking at the SPRIN-D AI and Robotics conference about what we are building at @Continu_Intel !
Thank you to @IlirAliu_ for the great video!
@Continu_Intel
Most AI assumes nicely ordered tokens or regularly sampled data.
Reality isn't like that. @benjaminwalker and team are building models for irregular, asynchronous streams of events and measurements unfolding continuously through time.
Ben Walker retweeted
Two months into Continuous Intelligence, we shared our progress building foundation models for time-series data at SPRIND’s conference in Berlin!
Exciting to see so much frontier AI innovation beyond LLMs across the UK and Europe. Thank you SPRIND for bringing us together!
Ben Walker retweeted
Continuous Intelligence has been awarded up to €3 million through SPRIND’s Next Frontier AI Challenge.
We are one of ten teams selected from 500+ applications to enter Stage 1.
Read more
continuousintelligence.co.uk…
We’re hiring in London
continuousintelligence.co.uk…
Ben Walker retweeted
True sovereignty isn't copied. It's built. Here are the 10 teams we fund with €125M to create the next AI paradigm in Europe! Learn more about the teams and the @SPRIND Next Frontier AI Challenge 👇
1/
Earlier this week, I launched @Continu_Intel. Today, I can share what comes next.
We are one of ten teams entering Stage 1 of SPRIND’s €125m Next Frontier AI Challenge.
We are turning continuous-time ML research into models that learn from a continuously evolving world.
We are delighted to be one of ten teams entering Stage 1 of SPRIND’s €125m Next Frontier AI Challenge.
We are building AI that learns directly from irregular, asynchronous and multiscale streams of real-world data.
1
3
352
When I passed my DPhil viva, I wrote:
“This thesis lays the foundation for making continuous-time machine learning practical. Now it is time to make these models a reality.”
Today, that work enters its next phase with the launch of Continuous Intelligence Limited.
The real world does not arrive as tokens.
It arrives as irregular, asynchronous and multiscale streams of measurements, events and signals.
Continuous Intelligence is building stream-native AI for real-world time-series data.
2
294
Unless I’ve missed something, there are still no technical details on how they make the approach subquadratic. Anyone know how they choose which previous tokens a query should attend to without first looking at all previous tokens, or is the subquadratic claim just marketing?
The transformer architecture used for ChatGPT, Gemini, and Claude has defined the last decade of AI. It also introduced a fundamental constraint: compute scales quadratically as context grows.
Longer inputs, exponentially higher costs and accuracy that degrades well before the context window limit.
SubQ changes that.
It's the first LLM that breaks the quadratic scaling constraint delivering longer context, higher accuracy, and lower cost at the same time without tradeoffs.
Read more here.
subq.ai/introducing-subq
146
