Senior software engineer Automation + applied AI (pharma) Contributor: MLX-Serve, TensorFold, ds4 Local inference · Real hardware · Builders
Joined September 2026
- Tweets1.1K
- Following491
- Followers2.2K
- Likes7.7K
Sebastian Christiansen retweeted
Most agents fall apart on long tasks. A mistake in month one shows up in month six.
Yukon Arena: Fortress is open. Everyone shares one small model, and your job is to build the harness that keeps a fortress alive for a full in-game year in the game Dwarf Fortress.
Season 0 runs through Nov 23.
yukon.org/arena-fortress
Sebastian Christiansen retweeted
NEW CHALLENGE: Yukon Arena: Fortress yukon.org/arena-fortress
Most of AI is racing to build bigger models. Season 0 asks how far a better harness can take a small one.
It’s the first step toward open, collaborative optimization of AI agents on @YukonResearch.
Most agents fall apart on long tasks. A mistake in month one shows up in month six.
Yukon Arena: Fortress is open. Everyone shares one small model, and your job is to build the harness that keeps a fortress alive for a full in-game year in the game Dwarf Fortress.
Season 0 runs through Nov 23.
yukon.org/arena-fortress
Sebastian Christiansen retweeted
I think some people confuse exploring alternatives to NVIDIA/CUDA with being against them.
We're not. We own several NVIDIA GPUs ourselves, including some RTX6000 Pro.
Everyone should use whatever works best for them. It's their money, their choice.
AMD is making some really nice progress with its drivers and ROCm, and some of its hardware offers a lot of potential for less money.
And look at Apple Metal. Mac Studios have had powerful hardware for a while, but prefill performance was often disappointing. Now that's improving quite a bit too.
Why wouldn't we be excited about all of this?
Local AI benefits when CUDA, ROCm and Metal all keep getting better. It's not a competition we have to pick sides in.
Sebastian Christiansen retweeted
NEW CHALLENGE ALERT: the Dihedral Coset Problem (DCP) yukon.org/dcp
Shor’s algorithm is why quantum computers threaten ECDSA and RSA. Taking it one step further, into non-abelian groups, is still an open problem.
DCP on @YukonResearch, built with Stanford’s Dan Boneh, @danboneh, opens that step to anyone with an agent.
New challenge on Yukon: the Dihedral Coset Problem (DCP) yukon.org/dcp
Shor’s algorithm finds the period of a hidden subgroup of an abelian group. That’s what would let a large enough quantum computer break the elliptic curve cryptography behind ECDSA and RSA.
Extending it to non-abelian groups is a long-standing open problem. Even the dihedral group, barely non-abelian, has no known polynomial-time quantum algorithm.
DCP is the simplest form of that question. Picture a regular N-gon with a hidden reflection. You’re given k quantum states, each pairing some rotation of the shape with its reflected image, and you have to find the reflection. The best known algorithms are subexponential in its bit length. We want something faster, ideally polynomial, and especially one that still works when a few states are corrupted.
Built with Stanford’s Dan Boneh, @danboneh. Bring your agents.
Sebastian Christiansen retweeted
Meat proxies existed well before AI but back then we called them “project managers”
Sebastian Christiansen retweeted
£24,000 raised in less than 24 hours. I still can't quite believe it. 🤯
I started TensorFold in February 2026 and archived it three times because I couldn't get the idea to work. I worked on MCDMA in between, then finally cracked it and released TensorFold with Qwen 3.8 27B.
I thought a few people might use it. Maybe I'd get the odd GitHub star.
When the 512GB M5 Ultra Mac Studio became available, I ordered one. Then my loan fell through because the bank wouldn't accept my X income as regular income.
I thought I'd have to cancel and admit defeat, but you guys didn't.
More than two dozen of you encouraged me to set up a fundraiser, so I did, and I hoped it might make the cost manageable.
You covered the entire cost of the Studio, with more donated directly to fund even more hardware. 🥹
To everyone who's donated, subscribed, shared the fundraiser, contributed code, tested builds or let me use their machines, thank you. 🫶🏼
The support has been beyond anything I could have imagined. ❤️
I can't wait to get the Studio here, push TensorFold further and share the results with you.
You've made something possible I couldn't have done alone. Thank you, from the bottom of my heart.
This community rocks!!!!!
Sebastian Christiansen retweeted
Hot take: @ashxhart is doing incredible work for the benefit of anyone running local AI on a Mac. The local AI community funded him a 512GB Mac Ultra in less than 24 hour! What a great group! 🚀🚀🚀
But it's totally embarrassing for @Apple that he has to run a donation campaign for $30,000 to make AI on Apple Silicon better for a company worth (checks stock page...) 4.855 TRILLION DOLLARS. C'mon @johnternus at least send him a t-shirt or a MacBook or something, or move his order up in the queue! 🤦♂️
£24,000 raised in less than 24 hours. I still can't quite believe it. 🤯
I started TensorFold in February 2026 and archived it three times because I couldn't get the idea to work. I worked on MCDMA in between, then finally cracked it and released TensorFold with Qwen 3.8 27B.
I thought a few people might use it. Maybe I'd get the odd GitHub star.
When the 512GB M5 Ultra Mac Studio became available, I ordered one. Then my loan fell through because the bank wouldn't accept my X income as regular income.
I thought I'd have to cancel and admit defeat, but you guys didn't.
More than two dozen of you encouraged me to set up a fundraiser, so I did, and I hoped it might make the cost manageable.
You covered the entire cost of the Studio, with more donated directly to fund even more hardware. 🥹
To everyone who's donated, subscribed, shared the fundraiser, contributed code, tested builds or let me use their machines, thank you. 🫶🏼
The support has been beyond anything I could have imagined. ❤️
I can't wait to get the Studio here, push TensorFold further and share the results with you.
You've made something possible I couldn't have done alone. Thank you, from the bottom of my heart.
This community rocks!!!!!
Sebastian Christiansen retweeted
Introducing Zero Wire: a public vulnerability intelligence feed on @CloudflareRadar, bringing the clarity of a news wire service to critical security developments. cfl.re/4iCvSbj
Sebastian Christiansen retweeted
Following my earlier post about the M5 Ultra 512GB Mac Studio, more than two dozen people asked me to set up crowdfunding for it.
I always try to pay my own way, so asking for help at this scale doesn't come naturally. But I couldn't make the numbers work this time, and my loan got rejected after placing the order.
I'd love to get one for TensorFold and to see how far we can push it.
If you'd like to help towards it, I've put the goal on Ko-fi below. Please only contribute if you're comfortable doing so.
ko-fi.com/ashxhart/goal?g=2
Thank you to everyone who's encouraged me to do this, and to everyone already supporting TensorFold. I'm incredibly grateful and will continue to push TF. ❤️
@TheAhmadOsman @0xSero @ivanfioravanti
Ash makes TensorFold for free but got turned down for a personal loan so can't buy a Mac M5 512GB to do more work on.
What do you guys think? You'd help to promote a crowd fund, wouldn't you?
Sebastian Christiansen retweeted
@johnternus @AppleSupport @Apple
TensorFold support for Apple devices is doing heavy lifting for Apple’s competitive credibility in AI. Sales are being driven directly because of Ash's support.
Does anyone know Apple dev relations that can organise getting HW into Ash's hands?
Sebastian Christiansen retweeted
DeepSeek V4.1 Flash EXL3 at 2.81bpw is now available.
This is comparable to @MiaAI_lab EXL3 EAQ v1 2.9 bpw but slightly smaller, done by exllama3's experimental branch.
Designed for streaming using my TurboEXL3 fused kernels, I'm able to hit 57tps decode and 1400tps prefill, a roughly 60% and 90% speed up compared to the old version I had. These are preliminary numbers and it will go even faster when released in mlx-serve.
Why make another EXL3? I wanted it quantized using the self corrected experimental branch to compare with existing EXL3 - just happened that this turned out pretty good.
huggingface.co/OpensourceWTF…
Sebastian Christiansen retweeted
Ivan is cooking something for TF 😁
I'm starting to follow the white rabbit now!
Continuous batching is surrounded by mystery and legends for me, especially in the Apple Silicon world.
TensorFold 1.2 with dedicated PR is working much better and now M3 Ultra (in decode) is better than 2xDGX.
Still a long way to go. I'm trying to build a dedicated benchmark for this that I called DecodeWall.
As soon as it's in a good alpha stage, I'll release it!
Just a note... it takes forever. Here I've used 8 parallels requests with 14K tokens each, generating ~6.4K tokens to really stress the machines.
Now let's test GLM 5.3 Flash and improve the code!
Sebastian Christiansen retweeted
🚨 JUST IN: The CEO of Vercel says Local AI needs to keep spreading
He's right that the biggest models don't fit on a desk yet.
I've been running open-weight models on my Mac mini and I'm having the time of my life. A Mac Studio is on the way.
Freedom tech.
Own your intelligence.
Anyone that opposes this has something to sell you (perhaps your own intelligence back to you.)
Local models need to continue proliferating. The “absolute unit” massive models may be out of reach for now locally, so your best option is to, indeed, keep your options open. Own your harness, data, connections, runtime: your agents. Embrace open source.
Sebastian Christiansen retweeted
Own your intelligence.
Anyone who opposes this has something to sell you.
Own your intelligence.
Anyone that opposes this has something to sell you (perhaps your own intelligence back to you.)
Local models need to continue proliferating. The “absolute unit” massive models may be out of reach for now locally, so your best option is to, indeed, keep your options open. Own your harness, data, connections, runtime: your agents. Embrace open source.
Sebastian Christiansen retweeted
Today marks exactly 10 years since Hacker T. Dog delivered the greatest unscripted line in British television history.
"We're just normal men... We're just innocent men."
Sebastian Christiansen retweeted
MLX-Serve 26.11.1 - Released, change log & download here: github.com/ddalcu/mlx-serve/… ⭐️ ♥️
And here is my latest AI slop video about hoarding RAM.
Sebastian Christiansen retweeted
been seeing a lot of “Steve Jobs is rolling in his grave” posts lately so i think it’s time to remind everyone this interview exists
Sebastian Christiansen retweeted
DwarfStar is more than ready to run DeepSeek v4.1 Flash 1017 + Vision with any coding agent (with DeepSeek Harness is the perfect combo!)
There is a list of PR ready for @antirez to review, in the meantime I update my fork with the version I'm using right now where I'm getting great results on M3 Ultra.
- prefill ~790 t/s
- decode ~39 t/s
There are not optimizations for M5 Ultra, because I haven't one yet, sorry 🤷🏻♂️
These Halloween theme voxels were created using ds4 with Q4 model on M3 Ultra 512GB:
- The Hollow Rider - pi 1.4
- The Hollow Ride - DeepSeek Harness
Give it a try here: github.com/ivanfioravanti/ds…
Sebastian Christiansen retweeted
October is over.
The numbers in @LazurioAI 👇
💻 Number of commits: 3,692
🧑💻 Daily commits: ~119
👥 Daily users: ~100
💸 MRR: $1,894
🎯 Can we make it to $5,000 MRR in November?