fLLMen retweeted
Friendly reminder once aganin that Russia is still bombing civilians in Ukraine. 18 people lost their lives tonight, including three children.
fLLMen retweeted
For my friends who are still using UV and might be a little weary about recent compromises to PyPi packages, stick this in your pyproject.toml.
You can let all of those pip users find and report the compromises...
ZK is the way to scale AI agents. Devs, now you can plug your agents or @openclaw directly into Zeko today with our growing library of demos, tools, & skills.
Zeko + o1js are a fast & low cost way to settle AI agent zkProofs: for full privacy, verification, autonomy & micropayments.
zkACP ex1: github.com/zeko-labs/develop…
zkVerify ex2: github.com/zeko-labs/zk-veri…
fLLMen retweeted
1/ Introducing Sentio Network: The Decentralized Data and Compute Layer
We are thrilled to unveil the Sentio Network, evolving our production-grade observability platform into the world’s first decentralized, AI-native data infrastructure.
Sentio is moving from a unified platform to an open, incentive-aligned network. Here is everything you need to know about the Sentio Litepaper:
fLLMen retweeted
Opinion × Binance Wallet Booster Campaign is now live.
Let’s unlock collective intelligence and shape the next-generation multi-player internet.
Repost this post to join now.
Get ready to join the Booster Program with @opinionlabsxyz on #BinanceWallet !
📅 Booster Program Start Time: February 6, 2026 03:00 UTC
🎯 Eligible users need sufficient Binance Alpha Points to participate
🎁 5,000,000 OPN will be available in Booster Program
⚠️ Important Note: Tokens from the Booster Program are subject to a lock-up period set by the project team. Please make sure you understand the risks before participating.
👉Check for details: binance.com/en/support/annou…
fLLMen retweeted
🚩
Those who still don’t understand what’s happening with Mina or think it’s just another random project have no clue what’s really being built. What @o1_labs and the devs are doing is pure genius.
Ceux qui ne comprennent toujours pas ce qui se passe avec Mina,
ou qui pensent que c’est juste un projet ordinaire,
n’ont aucune idée de ce qui est réellement en train d’être construit.
Ce que font o1Labs et les développeurs, c’est du pur génie.
那些还不明白 Mina 现在正在发生什么的人，
或者以为它只是一个普通项目，
根本不知道正在构建的东西有多么惊人。
o1Labs 和开发者正在做的，是纯粹的天才之作。
اللي للحين ما استوعب شنو قاعد يصير في مينا أو يظنها مشروع عابر، ما يدري شنو قاعد يُبنى فعلاً. اللي تسويه o1Labs والمطورين عبقرية حقيقية.
#ZKProofs #BTC
fLLMen retweeted
We’re open-sourcing MiniMax M2 — Agent & Code Native, at 8% Claude Sonnet price, ~2x faster
⚡ Global FREE for a limited time via MiniMax Agent & API
- Advanced Coding Capability: Engineered for end-to-end developer workflows. Strong capability on a wide-range of applications (Claude Code, Cursor, Cline, Kilo Code, Droid, etc)
- High Agentic Performance: Robust handling of long-horizon toolchains (mcp, shell, browser, retrieval, code).
- Smarter, Faster, Cheaper with efficient parameter activation
fLLMen retweeted
Zeko explainer 🫡🫡🫡
What happens when you combine the world’s lightest blockchain with a ZK rollup designed for performance? ⚡️
Let's dig deeper into Zeko’s design with @ZekoLabs CTO, Martin Ondejka.
Timestamps:
00:00 Zeko optimizations
00:27 How are optimizations achieved?
00:56 What influenced Zeko’s design?
02:21 What does Zeko make easier?
02:59 Tradeoff space
03:36 Mina + Zeko combined benefits
fLLMen retweeted
🕹️ ZK Arcade is coming soon — and we’re giving the Mina community early access!
We’ve teamed up with @alignedlayer + @Nori_ZK to reward early zk builders + testers.
If you joined Nori’s first ETH→Mina bridge testnet, this one’s for you 💫
Like & RT this post, then register 👇
fLLMen retweeted
The Slot Reduction MIP is now in Finalization ✅
Community feedback has been addressed, and it’s ready for inclusion in the upcoming Mesa Upgrade, pending the community's on-chain vote 🗳️
The first MIP for the Mesa Upgrade proposes to:
🔹 Cut slot time from 180s → 90s
🔹 Roughly doubles the network’s potential throughput
🔹 Faster tx inclusions
🔹 Cutting confirmation latency, making the network feel more responsive for everyday usage!
o1labs.org/blog/road-to-mesa
fLLMen retweeted
The Toad Report #1 is out.
Going to try and do these more regularly. Please share!
willmcgugan.github.io/toad-r…
fLLMen retweeted
1h40 youtube video: Prompt Engineering in Python | Automatic and Programmatic Prompt Optimization | Complete Course
How to code, your own, automatic prompt optimizer.
How the most advanced prompt optimization tool, DSPy, works and how to fully leverage its capabilities.
How to perform prompt engineering programmatically in Python, efficiently manipulating prompts with code to create powerful, maintainable, and composable AI programs.
As a practical example, this AI tutorial demonstrates how to optimize the extraction of structured data from receipts, improving accuracy from 20% to 100%.
fLLMen retweeted
Introducing DeepConf: Deep Think with Confidence
🚀 First method to achieve 99.9% on AIME 2025 with open-source models! Using GPT-OSS-120B even without tools, we reached this almost-perfect accuracy while saving up to 85% generated tokens.
It also delivers many strong advantages for parallel thinking:
🔥 Performance boost: ~10% accuracy across models & datasets
⚡ Ultra-efficient: Up to 85% fewer tokens generated
🔧 Plug & play: Works with ANY existing model - zero training needed (no hyperparameter tuning as well!)
⭐ Easy to deploy: Just ~50 lines of code in vLLM (see PR below)
📚 Paper: arxiv.org/pdf/2508.15260
🌐 Project: jiaweizzhao.github.io/deepco…
joint work with: @FuYichao123 , xuewei_wang, @tydsh
(see details in the comments below)
fLLMen retweeted
Well, in the most lowkey way possible, and on a random Tue afternoon, @DSPyOSS 3.0 is out of beta.
pip install -U dspy
So many amazing people contributed to this. Thank you all!
(Release notes below. Stay tuned for a ton of stuff over the next few weeks!!)
