Yansoki

Coalitional Game Theory, AI

[Yansoki @JustXTech]

@itsolelehmann I always wanted to build something similar just cuz of how much I like cooking/food

Layer this with cooking techniques and you have an private chef and cooking guide across different cultures...great for food tourism and chefs trying different things

Kudos

[Yansoki @JustXTech]

@scion_x_ 3.6T de trésorerie...faut lire avant de publier

[Yansoki @JustXTech]

I just watched "I swear", on John Davidson...a movie that had me crying, laughing, and ultimately feeling admiration for someone who has done so much, when life gave him so little...the power to move things, question yourself , and inspire...Great movie

[Ashutosh Maheshwari @asmah2107]

It is truly impressive that we have developed H100 GPUs capable of trillions of operations per second, just so we can use them to run a Python wrapper that waits 10 seconds for a JSON response from a LLM.

We have achieved the pinnacle of hardware efficiency and software laziness simultaneously.

[Yansoki @JustXTech]

@akashbitm787 @asmah2107 Try this out

https://t.co/v18FKygT1f

[Yansoki @JustXTech]

@asmah2107 https://t.co/v18FKygT1f

[Yansoki @JustXTech]

We just open-sourced Kuat beta.
It's a Rust-based DataLoader for PyTorch that achieves 4.6x faster throughput than ImageFolder on standard benchmarks.
If your H100s are sitting at 40% utilization because the CPU can't decode JPEGs fast enough, this is for you.
Repo + Benchmarks: https://t.co/gBh9btTzbx

#MachineLearning #PyTorch #RustLang #ComputerVision

[Yansoki @JustXTech]

>50,000 parameters on MNIST and barely 90% accuracy is signs of a very poor model....Higher performance is achievable with <10k parameters, this is nothing impressive or any significant breakthrough

[Brian Roemmele @BrianRoemmele]

Breakthrough: Game-Theoretic Pruning Slashes Neural Network Size by Up to 90% with Near-Zero Accuracy Loss: Unlocking Edge AI Revolution!

I am testing this now on local AI and it is astonishing!

introduced Pruning as a Game.

Equilibrium-Driven Sparsification of Neural Networks, a novel approach that treats parameter pruning as a strategic competition among weights. This method dynamically identifies and removes redundant connections through game-theoretic equilibrium, achieving massive compression while preserving – and sometimes even improving – model performance.

Published on arXiv just days ago (December 2025), the paper demonstrates staggering results: sparsity levels exceeding 90% in large-scale models with accuracy drops of less than 1% on benchmarks like ImageNet and CIFAR-10. For billion-parameter behemoths, this translates to drastic reductions in memory footprint (up to 10x smaller), inference speed (2-5x faster on standard hardware), and energy consumption – all without the retraining headaches of traditional methods.

Why This Changes Everything

Traditional pruning techniques – like magnitude-based or gradient-based removal – often struggle with “pruning regret,” where aggressive compression tanks performance, forcing costly fine-tuning cycles. But this new equilibrium-driven framework flips the script: parameters “compete” in a cooperative or non-cooperative game, where the Nash-like equilibrium reveals truly unimportant weights.

The result?

Cleaner, more stable sparsification that outperforms state-of-the-art baselines across vision transformers, convolutional nets, and even emerging multimodal architectures.

Key highlights from the experiments:

•90-95% sparsity on ResNet-50 with top-1 accuracy loss <0.5% (vs. 2-5% in prior SOTA).

•Up to 4x faster inference on mobile GPUs, making billion-parameter models viable for smartphones and IoT devices.

•Superior robustness: Sparse models maintain performance under distribution shifts and adversarial attacks better than dense counterparts.

This isn’t just incremental – it’s a paradigm shift. Imagine running GPT-scale reasoning on your phone, real-time video analysis on drones, or edge-based healthcare diagnostics without cloud dependency.

By reducing the environmental footprint of massive training and inference, it also tackles AI’s growing energy crisis head-on.

The implications ripple across industries:

•Mobile & Edge AI: Affordable on-device intelligence explodes.

•Green Computing: Lower power draw for data centers and devices.

•Democratized AI: Smaller models mean broader access for startups and developing regions.

As AI scales toward trillion-parameter frontiers, techniques like this are essential to keep progress practical and inclusive.

Pruning as a Game: Equilibrium-Driven Sparsification of Neural Networks
(PDF: https://t.co/OxRgcEqOue)

I will continue my testing but thus far results are robust!

[Yansoki @JustXTech]

@aj_agr @copyconstruct Yupp, we have a tool to help you search your logs while they are still compressed

[Yansoki @JustXTech]

@lucastech @LorenCharnley @DanielLockyer We have a tool that would help you store them in compressed form and still search/manipulate them...also support streaming merging so no in memory decompression...I think you need something like that

[Yansoki @JustXTech]

@davidgu @abdulkarim_me We've developed a general purpose tool that enables you to manipulate your logs while they are still compressed..could help you save some of that

[Yansoki @JustXTech]

Load balance on replicated containers, multiple read, single write DBs..for multi vps setup, cloudflare + nginx and arguably docker swarm...no need for k8 at 10RPS....adjust api endpoints to make requests cheap, use caching(client side) and redis...this would handle &gt; 10krps

[N.Kanali @NicKanali]

Safaricom is hoping to increase M-Pesa processing capacity to 10,000 transactions per second by January.

Currently, M-Pesa processes 6,000 per second.

[Yansoki @JustXTech]

@Ifenimiii 😭😭nooo...this is your internal chaos

[Satya Nadella @satyanadella]

I’ve been thinking a lot about what the net benefit of the AI platform wave is. The real question is how to empower every company out there to get more out of this platform shift and build their own AI native capabilities and enterprise value (vs inadvertently just transfer their unique value to the tech sector!!).

Bill famously said a platform is when the economic value of everybody that uses it exceeds the value of the company that creates it. That’s the essence of the positive-sum future.

Even in our somewhat zero-sum mindset industry, we can create partnerships that create value for all parties involved. Our partnership with OpenAI is a great example. Our investment helped them scale; their research accelerated our own innovation. That’s what healthy platforms and partners do—they catalyze and compound progress.

There’s no better proof than what we announced just this week. The world’s first AI superfactory was co-designed with OpenAI and informed by three generations of AI supercomputers we built for frontier model training and inference. It was also a result of working closely with Nvidia and getting better at the full stack optimization from model architecture to micro-architecture of the chip and everything between three companies!

We also did the work to bring AMD into the fleet doing inference of GPT models, which enabled them to get up to speed on their own software stack for AI.

And now all this infrastructure will scale to support every startup to enterprise doing their own training to inference.

You can see the same dynamic in coding. Thanks to AI, the category itself has expanded and may ultimately become one of the largest software categories. I don’t ever recall any analyst ever asking me about how much revenue Visual Studio makes! But now everyone is excited about AI coding tools. This is another aspect of positive sum, when the category itself is redefined and the pie becomes 10x what it was! With GitHub Copilot we compete for our share and with GitHub and Agent HQ we also provide a platform for others.

Of course, the real test of this era won’t be when another tech company breaks a valuation record. It will be when the overall economy and society themselves reach new heights.

When a pharma company uses AI in silico to bring a new therapy to market in one year instead of twelve. When a manufacturer uses AI to redesign a supply chain overnight. When a teacher personalizes lessons for every student. When a farmer predicts and prevents crop failure. That’s when we’ll know the system is working.

Let us move beyond zero-sum thinking and the winner-take-all hype and focus instead on building broad capabilities that harness the power of this technology to achieve local success in each firm, which then leads to broad economic growth and societal benefits. And every firm needs to make sure they have control of their own destiny and sovereignty vs just a press release with a Tech/AI company or worse leak all their value through what may seem like a partnership, except it's extractive in terms of value exchange in the long run.

We know that the Internet wave had tremendous positive sum impact in the world, and yet we also had some sectors that got hollowed out like local media. This time around we have the opportunity to ensure broad diffusion of this tech with choice and control that is distributed to ensure positive sum outcomes across the board.

At the end of the day, this new technological wave gives us the opportunity to dream bigger and set higher ambitions for what we can collectively achieve. Each of us will need to play our part!

[Yansoki @JustXTech]

@Ifenimiii Loving anyone, is also willing to let them go....Love in itself is not selfish imo...if MJ has decided to leave, then I'll cherish what we had, and let go of what I hoped we would have...its not easy, but loving someone selflessly, and loving yourself, makes it easier, for me🥲

[Yansoki @JustXTech]

@Ifenimiii Judge people by the way they treat someone they can't benefit from...never fails

[Yansoki @JustXTech]

@Ifenimiii 😂😂😂😂....would you rather people love your writing and only it , judging you by its quality....or love everything from the mind that gives them precious life lessons from time to time...God a beg

[Yansoki @JustXTech]

😭😭😭😭

[Slazac 🇪🇺🇺🇦🇹🇼🌐 @TrueSlazac]

college

[Yansoki @JustXTech]

Lost a crazy contract cuz my passport couldn't do on-boarding, screwed up an investment meeting over poor internet, lost a PhD offer 2 years ago over poor internet...smh , a hellhole 😑

[Ngong Oliver @NgongOliver]

I hate the fact that I live in Cameroon. This is the worst country to live in if you have a dream. Last year I lost a PhD offer due to poor connection. Today I had an interview, still MTN blackout the internet. I'm just so pissed..