Tweet Disematkan
plebdevs
273 posts
plebdevs
@pleb_devs
https://t.co/g7Ft0gBsmG FREE Adversarial AI Course out now (plebdevs dot com) 🤝👩💻🤝🧑💻🤝👨💻🤝
Bergabung Kasım 2023
124 Mengikuti326 Pengikut
Next PlebDevs AI course lesson drops tomorrow.
Until then: go watch Lesson 2. It’s free, it’s technical, and it covers the AI provider / trust / self-hosting side of this stuff that almost nobody talks about clearly.
We’re building the course we wish existed.
plebdevs@pleb_devs
Lesson 2 of the PlebDevs adversarial AI course is now live! Learn about AI model providers in depth and *importantly* how to be your OWN provider
English
You didn't hear?? You missed it???
PLEBDEVS ADVERSARIAL AI COURSE
We are mastering local and private AI in 2026 - time to level up!
plebdevs@pleb_devs
PlebDevs Adversarial AI course is ready to start! Lesson 1 is now released and live on the plebdevs platform! Rest of the course will be released over the coming weeks and yes it is all totally FREE
English
The gap between frontier cloud AI and local private AI is closing fast
We are on the best timeline
DHH@dhh
I got qwen3-coder-next running on my @Beelinkofficial AMD 395+ w/ 128GB. Spitting out at 35 tps, which is just OK, but seeing that fed into @opencode is still pretty damn neat. The local LLM story is only going to get better!
English
The most powerful local coding model I've ever used!
Things are too bullish for local / private AI
Accelerate!
Qwen@Alibaba_Qwen
🚀 Introducing Qwen3-Coder-Next, an open-weight LM built for coding agents & local development. What’s new: 🤖 Scaling agentic training: 800K verifiable tasks + executable envs 📈 Efficiency–Performance Tradeoff: achieves strong results on SWE-Bench Pro with 80B total params and 3B active ✨ Supports OpenClaw, Qwen Code, Claude Code, web dev, browser use, Cline, etc 🤗 Hugging Face: huggingface.co/collections/Qw… 🤖 ModelScope: modelscope.cn/collections/Qw… 📝 Blog: qwen.ai/blog?id=qwen3-… 📄 Tech report: github.com/QwenLM/Qwen3-C…
English
plebdevs me-retweet
The events happening all around the world can be difficult for everyone, and my thoughts and motivations are affected.
One way we stay connected is to be creatively productive. We process our thoughts through art, get togethers and writing.
We at Bitcoin Party KC have been actively updating our membership site to create a space for community. We want to provide education and a sense of being with our community. Bitcoin is a sovereign asset that allows you to create more value all over the world. Our hope is that we can catalyze a positive change in the world with bitcoin centric projects.
We’re building this space to support each other’s growth, especially when the world feels overwhelming.
In this picture I shared, I wanted to show real proof of work examples of community we have organized in 2025.
1. A project called @SeedSigner, building diy bitcoin hardware wallets from an event we organized in Kansas City w/ @KcBitcoiners
2. Austin @bitcoinplebdev from @pleb_devs and @PlebLab , talking about learning how to code from a Bitcoin Part KC export event we did in Austin, TX during SXSW, with help and support from @btcplusplus, @madelinevibes, @Blockstream, @ThrillerX_ , @unchained, @TedThayer_, @SuperTestnet, @btctechsupport, @niftynei @Airbtconline and @bitcoincommons
3. Chris from Bitcoin Party KC and @JondoMedia giving an educational talk about a recent bitcoin scam that happened to someone’s loved one and how to avoid it, picture by @bitcoinburnbabe
If you value creative connection and passionate community, the membership and support we offer could be a place where you belong.
In 2026, we’re looking for people who want to join the mission and be a catalyst for real change in the world.
Join us, join the community and support Bitcoin Party KC as we build and grow into the new year. You are a part of the team. We want to grow with you, here: bitcoinpartykc.com
English
Things getting more bullish or local AI every day...
ollama@ollama
ollama launch is a new command in Ollama 0.15 to run Claude Code, Codex, Droid and OpenCode with Ollama! GLM 4.7 Flash is now optimized to use much less memory for longer context lengths (64k+). Need additional hardware? Ollama's cloud offers GLM 4.7 with full precision and context length.
English
