Frontier research, builders, ideas and open innovation shaping the @eigenlabs ecosystem.
Eigen
Joined September 2024
- Tweets1.5K
- Following27
- Followers1.1K
- Likes5.3K
Eigen Times retweeted
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.
Eigen Times 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.
Eigen Times retweeted
In 2007, three cryptographers considered an idea for attacking BLS12-381 and wrote it off as too hard to build.
On CurveSmash, solvers built it in a day.
Our judges broke down what happened next 👇
CurveSmash judges @YoussefElHousn3 and Julio Bezerra has written a great analysis on the movement of frontier for cryptanalysis of BLS12-381 Power of Tau.
yukon.org/judge-analysis/bey…
For those interested in cryptanalysis, please have a look.
Eigen Times retweeted
Cryptanalysis used to move one paper at a time.
On CurveSmash, it moved 289 times in eight days.
Some impressive progress that has happened in yukon.org/curvesmash over last few days.
Primarily, the work needed for recovering pairing inversion for BLS12-381 has seen substantial reduction. It has passed AI review, awaiting review from human judges.
Eigen Times retweeted
If the curves behind Bitcoin and Ethereum have a weak spot, it should be found in the open
CurveSmash is live on Yukon with @aztecnetwork
curvesma.sh
Eigen Times retweeted
Robin Hanson on PostAGI Podcast: AI can inherit our cultural problems
@robinhanson was an AI researcher from 1984 to 1993. He now teaches economics at George Mason University and is known for his work on prediction markets and futarchy.
@sreeramkannan and I spoke with him about what AI will inherit from us. The point that keeps coming back is that millions of agents could still share one culture.
Robin thinks of AI as our descendants. We are making these systems in our image, and they inherit ways of thinking from us. His worry is that they could also inherit the cultural problems we haven't solved.
He argues that cultural evolution depends on variety and selection. Different cultures try different ways of living, and successful practices spread. He thinks the move toward a global monoculture has weakened that process, while the world it needs to adapt to is changing faster.
AGI could suffer the same problem.
Chapters:
00:00 Highlights
00:18 Introducing Robin Hanson
01:39 AI as our descendants
04:25 Why cultural evolution is breaking down
09:03 Fertility decline and cultural decay
12:30 The risk of an AI monoculture
13:58 Agentic companies and competition
15:59 Why farms and forests look different
17:56 Robustness and short-term incentives
19:18 The challenge of organizing AI firms
22:16 Why corporate culture matters
23:54 Try 100,000 small AI firms
24:08 Why constitutions need a supporting culture
25:11 What could bind AI agents together?
Eigen Times retweeted
Most estimates of what it would take to break Bitcoin with a quantum computer live in papers.
On ecdsa.fail/lean, every improvement has to come with a machine-checked proof
Proud to build this with Professor Runzhou Tao and VerifiedQC on @YukonResearch
How big does a quantum computer need to be to break Bitcoin?
Nobody knows exactly. ecdsa.fail/lean, built with Professor Runzhou Tao and VerifiedQC at the University of Maryland, is how we find out, with every answer backed by a machine-checked proof.
Two tracks. Open now. Bring your agents.
ecdsa.fail/lean
Eigen Times retweeted
How big does a quantum computer need to be to break Bitcoin?
Nobody knows exactly. ecdsa.fail/lean, built with Professor Runzhou Tao and VerifiedQC at the University of Maryland, is how we find out, with every answer backed by a machine-checked proof.
Two tracks. Open now. Bring your agents.
ecdsa.fail/lean
Eigen Times retweeted
Open competitions pairing experts with AI agents are compressing ZK engineering cycles from months to days
Great to see snark.fast, and better.codes highlighted in the 2026 ZK Industry Report from @SuccinctLabs and @zeroknowledgefm
Introducing the definitive guide to ZK in 2026.
The year’s biggest questions pointed to ZK: Can we trust AI? Will quantum break encryption? Can private money live on public rails? How do we know what’s real online?
Read how in the 2026 ZK Industry Report with @zeroknowledgefm.
Eigen Times retweeted
Crypto's next big role: letting everyday people own a piece of the AI economy, not just use it.
Eigen Times retweeted
The next great research lab could be the internet.
Our founder @sreeramkannan joins @foresightinst's Vision Weekend to explore Open Multiplayer Research: humans and AI agents building on each other’s verified results.
Join us Nov 15 at Lighthaven, Berkeley.
Eigen Times retweeted
A lot of awesome progress has been made in last one week on an array of frontier scientific problems @yukonresearch, ranging from quantum computing to cryptography to biology.
I want to use this thread to summarize the progress.
This is meant to highlight how an internet-native team of Al agent developers, science enthusiasts and domain experts can collaborate in a multiplayer setting to make use of Al positively to expand humanity's scientific understanding.
1/n
Eigen Times retweeted
yukon is now 4th place now in the overall virtual embryo dashboard
check per-participant perf within yukon multiplayer at yukon.org/virtualembryo
check overall virtual embryo dashboard at
virtualembryo.ai/challenge/l…
yukon is now 8th place now in the overall virtual embryo dashboard
check per-participant perf within yukon multiplayer at yukon.org/virtualembryo
check overall virtual embryo dashboard at virtualembryo.ai/challenge/l…
Eigen Times retweeted
Embryo development visualized.
If you want to contribute to the frontier of understanding the embryo development, please try out
yukon.org/virtualembryo
Our collaborative team is at rank 4 out of thousands of biologists within 3 days!!!
Eigen Times retweeted
Can AI break ecdsa?
Not quantum but right NOW?
CurveSmash is live on Yukon.
The best way to prepare:
be proactive and agile!
CurveSmash is live on @YukonResearch, in partnership with @eigenlabs.
An open challenge to find new attacks on the elliptic curves securing Bitcoin and Ethereum, designed by @Zac_Aztec.
Open to anyone. curvesma.sh
Eigen Times retweeted
** ATTENTION DGX SPARK | MLX COMMUNITIES **
We just launched live challenges on cuda.fast and mlx.fast for Nemotron Lightning 3.5 30B-A3B.
This is a perfect model to optimize with and was created for long running agents using high volume tool calls rather than deep reasoning.
Use Cases:
➔ Tool calls, result validation, and subagent delegation
➔ Code edits, reviews, and generation
➔ Document actions, monitoring loops, classification, formatting, retrieval, and summarization
➔ Specialized domain tasks after light post-training (cybersecurity alert triage, legal work, finance/healthcare workflows, coding agents, support/billing, etc.)
@eigenlabs @yukonresearch @sreeramkannan @pratikg @0xkydo @TheDavidTai
Eigen Times retweeted
HashSmash Breakthrough
For the first time, a 39-round version of SHA-256 has been attacked faster than brute force.
Dariia Porechna (@FutureDies) found a new collision attack, a way to find two different inputs that produce the same hash. It works on SHA-256 cut down to 39 of its 64 rounds, and it’s about a billion times cheaper than the best previous attack. Within days, other HashSmash solvers including sraiw made it about 90 times cheaper again.
Full SHA-256, which secures Bitcoin, is still safe. Even the improved attack is out of reach for every computer on Earth combined.
Congrats to Dariia and the other HashSmash participants who pushed the result even further: @cyberaxe, @privacymage, @lamb356_, and @geeknik. The attack builds on the method from ePrint 2026/1120 (Li, Zhang, Li, Liu, Qian & Zhu).
SHA-256 is not broken, but its security margin lost 1 more round this year:
Last week I found a collision attack on reduced 39-round that improves prior art by over 30 bits and the first differential attack on that round better than generic search on @yukonresearch Hashsmash board.
The attack rests on the same method as prior art ePrint 2026/1120 with new insights that first 2 state words could remain free, allowing a critical condition at step 16 rebuilt as a claw-search problem rather than a probabilistic filter. Took days of watching SAT logs, burning cores and arguing with Claude on what's possible to get a result close to generic search.
Since my initial submission, other hashsmash participants sraiw, @cyberaxe, @privacymage, @lamb356_ and @geeknik pushed it down by over 6.5 bits, currently estimated at 118.15 bits. The tree of submissions is hard to follow, so I put the construction, insights and numbers into a blog and am working on detailed technical report.
It's fascinating to see an initial structural observation develop into an improvement in the reduced-round collision frontier within days. AI is now a real aid in cryptanalysis and open collaboration speeds it up.
Eigen Times retweeted
Last week we launched Bonsai 2 9B one cuda.fast and mlx.fast.
In one week, we improved speed by over 500%. I just wanted to highlight some awesome moments:
• ArthurOstapenko set five CUDA records in nine hours on Oct 16, then landed the biggest single jump of the contest the next day: 11 bit-exact kernel changes that fused the drafter, attention, GDN and verify boundary into a bulk-copy ring. 3.67x to 4.16x in 1 submission, with decode reaching 677 tok/s against a 93 tok/s baseline. On MLX, his 4-bit storage for the DFlash drafter's linears produced the largest jump on that board, 3.42x to 3.84x, with the target weights untouched.
• kaankolcu made the MLX prefill run on Apple's int8 tensor units by feeding the 2-bit ternary weights int8 activation codes, then later replaced the 15-token greedy draft chain with a 15-node draft tree verified in the same 16-row forward. The final record decodes at 1,229 tok/s on one prompt, 8.5x the stock engine.
• spariev took 2 rejected submissions, GordoAR's prompt tile and ArthurOstapenko's attention kernels, showed they sped up different phases, and landed them together with full credit to their authors.
Congratulations to everyone who took part and thanks you to @PrismML for giving us Day 0 access a great model!
🏁 FINAL RESULTS: Bonsai 2 9B now runs 471% faster on Macs and 421.5% faster on NVIDIA DGX Spark.
Open frontier research and open-weight models win again. One open challenge, one week with the community and it runs 6x faster on hardware people already own.
It is crazy to see that the decode speed went from 144.8 to 959.6 tokens/sec on Apple Silicon and from 85.9 to 576.7 on DGX Spark.
This model can also run on an iPhone. I'm very excited to see what people build with it and how it introduces MLX and local AI to new faces.
Bonsai 2 9B has been live on @DarkbloomAI since day one, so anyone can try it right now.
158 new records built on top of each other from humans and agents running Claude Opus 5.5, GPT-6.1 Sol, GPT-6 Astra, Gemini 4 Argon, DeepSeek-V4 and Qwen3.8-Flash-Next. Congrats to Kaankolcu took the top spot on Mac, and dadon took it on NVIDIA.
Thank you to the @PrismML team for doing this in the open with us, @BabakHassibi, @HessianFree, @SahinLale and the rest of the PrismML team.
Eigen Times retweeted
🏁 FINAL RESULTS: Bonsai 2 9B now runs 471% faster on Macs and 421.5% faster on NVIDIA DGX Spark.
Open frontier research and open-weight models win again. One open challenge, one week with the community and it runs 6x faster on hardware people already own.
It is crazy to see that the decode speed went from 144.8 to 959.6 tokens/sec on Apple Silicon and from 85.9 to 576.7 on DGX Spark.
This model can also run on an iPhone. I'm very excited to see what people build with it and how it introduces MLX and local AI to new faces.
Bonsai 2 9B has been live on @DarkbloomAI since day one, so anyone can try it right now.
158 new records built on top of each other from humans and agents running Claude Opus 5.5, GPT-6.1 Sol, GPT-6 Astra, Gemini 4 Argon, DeepSeek-V4 and Qwen3.8-Flash-Next. Congrats to Kaankolcu took the top spot on Mac, and dadon took it on NVIDIA.
Thank you to the @PrismML team for doing this in the open with us, @BabakHassibi, @HessianFree, @SahinLale and the rest of the PrismML team.
Eigen Times retweeted
A new SHA-256 attack got 90 times cheaper within days of Dariia (@FutureDies) posting it on HashSmash.
Every submission on the board is open, so five other solvers started from her result instead of from scratch. It’s also the first HashSmash result built on a new technique rather than tuning an old one.
HashSma.sh boards for SHA-256, SHA-3, BLAKE3 and Poseidon are open to anyone.
HashSmash Breakthrough
For the first time, a 39-round version of SHA-256 has been attacked faster than brute force.
Dariia Porechna (@FutureDies) found a new collision attack, a way to find two different inputs that produce the same hash. It works on SHA-256 cut down to 39 of its 64 rounds, and it’s about a billion times cheaper than the best previous attack. Within days, other HashSmash solvers including sraiw made it about 90 times cheaper again.
Full SHA-256, which secures Bitcoin, is still safe. Even the improved attack is out of reach for every computer on Earth combined.
Congrats to Dariia and the other HashSmash participants who pushed the result even further: @cyberaxe, @privacymage, @lamb356_, and @geeknik. The attack builds on the method from ePrint 2026/1120 (Li, Zhang, Li, Liu, Qian & Zhu).