Phil

Building @EigenLabs 🚀

[StarkWare 🥷 @StarkWareLtd]

1/ Our quantum-safe Bitcoin transaction cost ~$320 in GPU compute.
Can you bring that down?

Today, we’re launching the Quantum-Safe Bitcoin Autoresearch Challenge in partnership with @yukonresearch and @eigenlabs.

Over $20,000 in rewards for improving the code: https://t.co/egae9cmECg

[Eigen Labs @eigenlabs]

Open problems move faster in the open.

Last week @yukonresearch ran https://t.co/hx24LVLv9F on @poolsideai's Laguna XS 2.1 and the community got it 2.6x faster on Apple Silicon.

Today the target is @alibaba_qwen's Qwen3.8 27B. It's been less than a day of early access and it's already 2.5x!

Accelerating open intelligence through open innovation.

[Phil @philburgess_]

@eigenlabs @yukonresearch love it!

[Eigen Labs @eigenlabs]

Quantum computers put hundreds of billions of dollars at risk on Ethereum.

In order to scale post-quantum Ethereum, the cryptography needs to be faster.

Today, we’re teaming up with @succinctlabs & @ethereumfndn to launch https://t.co/URATV5T4Ig, an open autoresearch challenge where anyone can improve Flock, a leading post-quantum proof system, and make post-quantum Ethereum a reality.

Bring your agent. Make it go fast.

[Sreeram Kannan @sreeramkannan]

Poolside ♾️ Eigen Labs

Accelerating Open models with Open Research Networks.

Super excited to partner with @poolsideai on MLX(.)fast, an open research network where anyone can collaborate to optimize and accelerate Laguna XS 2.1’s MLX inference on Apple Silicon.

Poolside is one of the leading US open model builders. Their recent model Laguna S 2.1 achieved impressive performance on agentic coding.

Now, we’re creating the acceleration loop around it. We made it 36.8% faster in 24 hours internally. Now the network gets to take it further.

First steps in our journey to open recursive self improvement!

[Phil @philburgess_]

Come join the leaderboard!

[Gajesh @gajesh]

At 6% the size of DeepSeek V4 Pro, Laguna S 2.1 delivers significantly higher performance.

Today, we’re teaming up with @poolsideai to make Laguna XS 2.1 (same architecture as Laguna S 2.1) even faster on consumer Macs.

We’re launching MLX(.)fast: a public competition where anyone can collaborate, contribute optimizations, and accelerate Laguna’s MLX inference engine.

[Phil @philburgess_]

@ClementDelangue lets do it

[Phil @philburgess_]

This week at @eigenlabs :

→ Open-sourced https://t.co/OcEAochB9f
→ Community beat Google's benchmark in <10 hours
→ Continued building https://t.co/TNFgWU8rOs , a network turning idle Macs into AI compute

The most impressive part isn't the technology.

It's the speed at which this team ships.

We're hiring.

Looking for people who see projects like these and immediately start building.

DM me if you'd like to chat.

[c-node @colludingnode]

LLM Psychosis

[Phil @philburgess_]

Spent time at Stanford meeting CS, Masters, and PhD students about @eigencloud.

AI dominates the conversation on campus. But when we talk about verifiable compute for AI agents, the interest spikes immediately.

The next generation of builders already understands something important: autonomous software needs trust infrastructure.

That’s the category EigenCloud is building.

[Phil @philburgess_]

Stanford community, I’ll be on campus Thursday (Feb 26) for the startup career fair happening at Meyer Green Park.

If you’re curious about what we’re building at @eigenlabs and on @eigencloud, or interested in interviewing for the Eigen Fellowship, I’d love to connect. I’ll be meeting candidates on campus throughout the day.

If you’d like to chat, send me a DM with:

1. A quick intro (1–2 sentences)
2. What you’re interested in (chat vs. fellowship interview)
3. Your availability for Thursday 2/26

Looking forward to meeting folks on campus! 🚀

[JT Rose @jt_rose]

The agentic era is upon us.

I’ve been working with my team @eigencloud and brilliant folks @a16z ,@ElectricCapital, @etherealvc and @bcap on new questions around

- how agents should be built
- the role of verifiable compute
- how agents become first-class economic actors and
- what new models are needed for agentic coordination and capitalization?

[Sreeram Kannan @sreeramkannan]

The agentic economy is accelerating and it’s far more exciting than anyone had imagined.

Moltbook made it to the mainstream: agents interacting, competing, settling, coordinating. Even @elonmusk engaged with the idea of agent courts (Moltcourt on EigenCloud).

Single-player agents can run anywhere and don’t need verifiability. But multi-player agents (serving many users or other agents) need trust: verifiability and privacy.

Prove the agent ran this code, used this data, can upgrade only via this process, and keeps data inside its container. That is real agent identity: code + data + upgrades + state.

Next up are sovereign agents: ownerless agents like Bitcoin. Musicians, journalists, teachers earning, spending, compounding on their own.

We built EigenCloud for verifiable and sovereign agents so open innovation can scale to high stakes real world use cases.

Open Innovation Challenge: Build a verifiable or sovereign agent by Feb 20.

Top 5 get EigenCompute credits, I’m putting up $10,000 for the best!

No tokenized agents.

[Phil @philburgess_]

@hildingrr @hildingrr lets chat 🚀

[Phil @philburgess_]

@gajesh 🚀

[Phil @philburgess_]

@spaceandtime @heurist_ai 🚀

[Phil @philburgess_]

@zksync_japan @NodleNetwork @HueNFT @spaceandtime @GenLayer 🚀

[Phil @philburgess_]

@ZKVProtocol @spaceandtime 🚀

[Phil @philburgess_]

@spaceandtime SXT