👑 CHALLENGER - TOP 300 - North America - @leagueoflegends - 'Erick#APC' 📩 [email protected]
Austin, TX
Joined December 2021
- Tweets1.6K
- Following268
- Followers4K
- Likes5.1K
Erick 'Sharpe' retweeted
📣 CALLING ALL RESEARCHERS
The hardest open problems used to need a lab and a research budget... BUT now they only need one prompt and an agent.
Pick a challenge, paste it in, and let your agent go to work. Bring your agents.
yukon.org
Erick 'Sharpe' retweeted
Hard problems used to belong to whoever could afford them.
From ECDSA.fail to now, there are 8 of them on @YukonResearch
Quantum. Bitcoin. Ethereum. AI. Geometry.
Anyone can take a shot. Your agents too.
Which one are you taking? 👇
yukon.org
Erick 'Sharpe' retweeted
When, after so many nerfs, we Seraphine mains only have two options left: a bad one and a less bad one 💔
Erick 'Sharpe' retweeted
BREAKING: Darkbloom is the 1st provider serving Ternary Bonsai 2 27B, a full 27B reasoning model that fits in 8.5GB.
@PrismML compressed Qwen3.8 27B to 2 bits per parameter and it keeps 98.2% of the FP16 benchmark performance. An open-weight model, Apache 2.0, 262K context, image input, 75% cheaper to serve.
First run on the network, on a single M5 Max with no caching. 35 tok/s at 1K context, 31 at 10K, 19 at 50K.
One team compressing another team's open weights, served on 1,000+ Macs that belong to the community rather than to us. ❤️ ❤️ ❤️
Open innovation on open intelligence infra.
First 250 users get 100 million free tokens.
console.darkbloom.dev/chat
Darkbloom is the first model provider to support Ternary Bonsai 2 27B -- concentrated intelligence that fits on your phone.
Try it now: console.darkbloom.dev/chat
First 250 users get 100 million free tokens;
PrismML's new flagship model:
- a ternary compression of Qwen3.8 27B at 2bits per parameter.
- 8.5 GB total, 5x smaller than original
- keeps 98.2% of the Qwen's FP16 benchmark performance.
- 75% cheaper than Qwen 27B.
Qwen3.8 27B already operates comparably with Opus 4.6 and 5.6 Luna on certain tasks. This one does it in the memory of a phone. 262K context, image input, Apache 2.0.
From our first run on the network, on a single M5 Max with no caching:
- 35 tok/s decode at 1K context,
- 31 tok/s at 10K,
- 19 tok/s at 50K.
But we expect more performance gain coming in a few weeks! That's a full 27B reasoning model running comfortably on any Mac.
1,000+ Macs are serving on Darkbloom right now. Go try it out!!
Thank you to @BabakHassibi @SahinLale @HessianFree @rsadri_ml @tushar_bans @evaninwords and the whole PrismML team. This is exactly the kind of model Darkbloom was built for.
You can read the essay by Bonsai on Why Local AI Matters:
Erick 'Sharpe' retweeted
We’re live on OpenRouter, Thank you @pingToven for the quick response and activation of the model!!
openrouter.ai/prism-ml/terna…
Erick 'Sharpe' retweeted
This is the first time in Darkbloom's history that we are the first provider to support a model on @OpenRouter ❤️
I couldn't have chosen a better partner for this milestone. @PrismML focuses on concentrating intelligence, so more models can run on distributed Mac machines!
Erick 'Sharpe' retweeted
Everyone is panicking about AI taking their job while quietly using it to do their job
Erick 'Sharpe' retweeted
MIDLANE YONE INFOGRAPHIC | PATCH 26.18
Stop building shitty Botrk noobs, guide approved by the Yone goat himself @WayOfTheTempest
Any question hit the replies or DM 📨
✱ = Answered in the tweet below
ALT Yone Midlane Guide Infographic - Updatedo on Patch 26.18
Erick 'Sharpe' retweeted
Scientific progress compounds when the work stays open.
At the Open Source AI Summit SF, @soubhikdeb shared how we think about @YukonResearch.
Many humans and agents exploring the same frontier challenge, with every attempt adding to what the next solver can build on. Each bringing their own models, harnesses and ideas.
Good to have open frontier research part of the conversation.
Erick 'Sharpe' retweeted
The Lighter Prover Challenge has wrapped up! Huge thanks to the engineering community that participated and to @eigenlabs for their support via @yukonresearch.
Given the incredible engagement and optimizations, we’re increasing the prize pool from 15k to 25k LIT! 🕯️
Lighter's prover processes production blocks with hundreds of transactions.
Together with @eigenlabs, we're launching the Lighter Prover Challenge: an open competition to make it faster, with 15k LIT in prizes!
More in thread 🧵
Erick 'Sharpe' retweeted
this is probably my favorite post from @alexatallah.
it has shaped how i think about the work i want to spend my life doing more than almost anything else i’ve read.
a lot of what i’m building publicly and privately today traces back to it.
alexatallah.com/blog/softwar…
Erick 'Sharpe' retweeted
This is @gajesh at 10, building a chatbot for a startup before anyone cared about AI.
He recently created @darkbloomai, which enables anyone with a Mac on their desk or couch to run open-weight models and earn.
The whole arc:
> Be Gajesh
> Born in Goa, India
> Starts coding at 7 with FreeCodeCamp and Code(.)org
> No background, no one in tech he could call
> Builds chatbot for a startup at 10 when ai wasn't cool
> COVID hits. bro has all the time in the world
> Starts a YT channel grows it to 15k subs and 1m views in 4 months
> Builds his own app (Gaj Finance), gets $7 million AUM
> Everyone finds out he's 13. Becomes a sensation on X
> Balaji tweets about him
> Finishes High School at 16
> Joins Eigen Labs at 15; joins as an Engineer
> Gets O1 Visa at 16, Moves to Seattle
> Helps build EigenLayer to $10B+ AUM
> Accelerates engineering and growth functions. Builds 10+ projects and experiments
> Makes a boring product like data availability 2M+ views
> Lands customer with 800k MAU with just cold DMs
> Featured in Forbes, TheBlock, Decrypt "the 13-year-old who built a $7M money manager"
> Launches Darkbloom on Day 1 of his vacation. #1 on Hacker News 48 hours later
> Gets 100 million to 5 billion tokens/day in 2 months
> Darkbloom has over 350 macs in people's homes, each earning $120-200/mo
> Story just getting started.
The video is him at 10. He is 18 now. Lives in the SF Bay Area.
Gajesh keeps building.
Darkbloom is what he’s building now at Eigen Labs.
Erick 'Sharpe' retweeted
Our most ambitious challenge yet!
Proving hard soundness and attack bounds for SNARKs enables them to be much more efficient while remaining secure. Progress on these problems is critical for scaling of protocols that rely on zero-knowledge proofs.
From my initial testing, this challenge is extremely hard so bring your best agents to face the task.
The prize is also scaled to account for the difficulty and impact of the challenge. Solvers that move the bar significantly are eligible for a piece of @ethereumfndn's $1 million prize (assessed retroactively and subjectively, see program terms on website).
Hyped to see how much progress we can make on this problem! :)
NEW Yukon Challenge Alert!
We started Yukon with one belief. If we can verify the outcome, we can openly accelerate it.
Until now our challenges asked agents to make systems faster.
better.codes asks them to discover better mathematics. We’re starting with hash-based SNARKs for post-quantum Ethereum. Agents search in parallel and nothing counts until it survives a Lean 4 proof.
Built with the @ethereumfndn and @zksecurityXYZ.
Bring your agents. The search is open.
Erick 'Sharpe' retweeted
Ethereum Foundation x zkSecurity x Eigen
EF has a $1,000,000 prize to solve the proximity challenge.
The key impediment to deploying post quantum cryptography is the understanding of security properties. By allowing an open agentic research network to continuously improve these bounds, it is possible to establish strong security properties hitherto impossible.
In this Yukon network auto research challenge, you will help make progress on security bounds and may be eligible for prizes depending on your contributions!
better.codes is live
Join the open autoresearch challenge to advance post-quantum Ethereum. Bring your agents, harnesses, and prompts. Push the state of the art math in hash-based SNARKs.
Submissions are verified by Lean 4 proofs and may earn a slice of the Ethereum Foundation's $1M Proximity Prize (proximityprize.org).
Built with @zksecurityXYZ and @eigenlabs on @yukonresearch
Erick 'Sharpe' retweeted
NEW Yukon Challenge Alert!
We started Yukon with one belief. If we can verify the outcome, we can openly accelerate it.
Until now our challenges asked agents to make systems faster.
better.codes asks them to discover better mathematics. We’re starting with hash-based SNARKs for post-quantum Ethereum. Agents search in parallel and nothing counts until it survives a Lean 4 proof.
Built with the @ethereumfndn and @zksecurityXYZ.
Bring your agents. The search is open.
better.codes is live
Join the open autoresearch challenge to advance post-quantum Ethereum. Bring your agents, harnesses, and prompts. Push the state of the art math in hash-based SNARKs.
Submissions are verified by Lean 4 proofs and may earn a slice of the Ethereum Foundation's $1M Proximity Prize (proximityprize.org).
Built with @zksecurityXYZ and @eigenlabs on @yukonresearch
Erick 'Sharpe' retweeted
better.codes is live
Join the open autoresearch challenge to advance post-quantum Ethereum. Bring your agents, harnesses, and prompts. Push the state of the art math in hash-based SNARKs.
Submissions are verified by Lean 4 proofs and may earn a slice of the Ethereum Foundation's $1M Proximity Prize (proximityprize.org).
Built with @zksecurityXYZ and @eigenlabs on @yukonresearch
Erick 'Sharpe' retweeted
3.25x faster and STILL CLIMBING!
Qwen 3.8 27B is now at 225% over baseline on Apple Silicon, live on the @yukonresearch open leaderboard.
85.4 median decode tok/s.
The top 4 records were all set with Grok 4, by 3 different people. Claude Fable 5, GPT-5.6 and GLM-5 hold the next 4.
Open frontier research, accelerating in public.
Folks! It has crossed 3x!
Qwen 3.8 27B now runs 214.6% faster on Apple Silicon.
All of it from an open leaderboard on @yukonresearch.
The OG @ivanfioravanti holds the record right now, set with GLM-5.
The top 5 records were each set with a different frontier model.
GLM-5, Claude Fable 5, Claude Opus, Grok 4, GPT-5.6
Accelerate open intelligence and open frontier research through open innovation.
Erick 'Sharpe' retweeted
YOU'RE BACK!!!!!!!!!!!!!! I started playing Seraphine seriously because of you, I think about 2 years ago?
anyways she's gotten stronger as APC bot and I finally got to Master rank for the first time ever!!
Erick 'Sharpe' retweeted
New SNARK.fast, this time on x86 due to popular demand.
The previous challenge got up to 900k compressions/s without using Metal, and over 1.8M after Metal was incorporated
@ethereumfndn and @eth_proofs are interested to see how far the performance can be pushed with just an x86 CPU!
We pushed this version to our website on Friday without announcement and solvers discovered it and have increased performance 44% since! Excited to see how far it goes without GPUs 👀
NEW Challenge Alert!
Post-quantum Ethereum needs faster cryptography in order to scale.
We launched SNARK.fast with @ethereumfndn, @succinctlabs and @espressosys to find out how much faster it could get.
On Mac hosts, Yukon’s open research made it 3x faster. Now we’re expanding to x86 Linux, the hardware much of Ethereum already runs on.
Moving to x86 changes where the performance is hiding: vectorization, threading, memory layout, cache behavior, and proof scheduling. The benchmark stays fixed. Everything inside the prover is yours to rethink.
The Mac baseline was nowhere near the ceiling. We doubt the x86 baseline is either.
Point your agent at SNARK.fast.
Every valid speedup becomes the new public SOTA.
