Your curated collection of saved posts and media
https://t.co/Mdtyy1y2Ip
BREAKING: SpaceX has announced that @Starlink now has over 9 million customers, up from 8M in November and 7M in August 2025. Starlink added a record 21,275 new customers on average per day since they hit 8M, smashing their previous record of 14,250. That growth rate is a whopping 49.3% higher than it was just last month! 🤯
Portraits of Iryna Zarutska went up in D.C., NYC, Miami, and Venice, Ca after Elon Musk and Eoghan McCabe pledged to fund the murals. Promises made, promises kept. Thank you @elonmusk and @eoghan. America will never forget you, Iryna. ❤️ https://t.co/ZYEPxMhIUi
ACLU attorney in press release: “Children will die without sex-rejecting procedures!” ACLU attorney before SCOTUS, where she could get in trouble for lying: “Yeah, there is no evidence these procedures save lives.” https://t.co/9luvBNwin0
dear santa, define good 💭 https://t.co/jXZyxdIVGz
dear santa, define good 💭 https://t.co/jXZyxdIVGz
🇺🇸 BANS NEW CHINA 🇨🇳 MADE DRONES The FCC today banned all drones and critical components made in a foreign country, and all communications and video-surveillance equipment from major Chinese drone manufacturers SZ DJI Technology and Autel Robotics. The designation means the companies, their subsidiaries and partners won’t be able to import, market or sell new drone equipment in the U.S. DJI accounts for around 70% to 90% of commercial, local-government and hobbyist drones in the U.S. (Source WSJ)
Gravitational field layers/fabric visualization. https://t.co/XdKOxR6ox5
Artificial Organisms. 2021. An algorithmic study of behavioral patterns. By translating fauna into digital environments, I discovered a lot of similarities between simulated motion and organic life. Working with complex simulations feels like deciphering the source code of nature.
🧊 now you can see both: > dynamic 2D + 3D space-time 'fabric'. https://t.co/JQxk4lkmMT
https://t.co/JV6TrLIg8B
https://t.co/6omxRKKfpO
wow @joannejang i made it so you can really chat with the files https://t.co/CjGYha3PBV
NVIDIA made a beginner's guide to fine-tuning LLMs with Unsloth! 💚 You'll learn about: - Training methods: LoRA, FFT, RL - When to fine-tune and why + use-cases - Amount of data and VRAM needed - How to train locally on DGX Spark, RTX GPUs & more Guide: https://t.co/ajwL99Bug7 https://t.co/D0vyJkza0B
📢vLLM v0.13.0 is now available. Huge thanks to the community. Highlights: Engine core: compile_ranges for selective kernel compilation, PrefixLM support for FlexAttention + TritonAttention, and CUDA graphs for 3D Triton attention. Plus: xxHash option for prefix caching, chunked prefill for ALL pooling tasks, and Model Runner V2 updates (min-p sampling, logits NaN detection).
🚀Our Free LongCat API’s Backend Model Gets Updated! LongCat-Flash-Chat New Update is arriving! Building on "extreme efficiency" & "lightning-fast response", this upgrade reinforces long-context capability and real-task performance. 🔺 256K Context: Doubled from previous 128K, with top-tier info capture accuracy. 🤖 Agentic coding: Built for developers who actually ship. Full-stack apps across mobile, desktop, and cross-platform. ⚙️ SOTA Tool Use: High precision and robust execution even in non-thinking modes. 🌏 Multilingual Support: Enhanced support for 9 new languages (ES, FR, AR, PT, RU, ID, DE, KO, JA). 💭 Enhanced Reasoning: Significant improvements in Math and Complex Instruction Following. ✅ Good News: LongCat-Flash API is Fully Updated Now! 🔗 Check API Docs & Get Started (up to 5M free tokens/day): https://t.co/7TlSHfiCyp
I’m excited to share a new repo: Agent Skills for Context Engineering Instead of just offering a library of black-box tools, it acts as a "Meta-Agent" knowledge base. It provides a standard set of skills, written in markdown and code, that you can feed to an agent so it understands how to manage its own cognitive resources. https://t.co/vWwrYPAd8k Most agent failures are not model failures; they are context failures. This is still an experimental project. The goal is to establish a platform-agnostic standard for context engineering that can be used in Cursor, Claude Code, Copilot or Codex. skills/ context-fundamentals: What context is, why it matters context-degradation: How context fails (lost-in-middle, poisoning) context-optimization: Compaction, masking, caching multi-agent-patterns: Orchestrator, swarm, hierarchical memory-systems: Vector RAG, knowledge graphs, Zep tool-design: Building tools agents can use evaluation: Testing and measuring agent systems I believe this is a good start, showing developers how to approach context engineering rather than relying on ready-made tools. You will also find the aggregated research documents I used to build these skills in the repo. The skills are synthesized from technical blogs on context and prompt engineering that I bookmarked, AI Labs' documentations, and Anthropic Skills examples. Try the 7 Skills, created using Antrhopic's Skills template format. Experiment with the provided scripts and references, and feel free to contribute to the repo.
It’s actually a good question; the difference is subtle but structural. I usually frame it like this: AGENTS[.]md acts as the declarative context. You write this for every repo (and nested directories) to define the project structure, persona, and coding rules. Skills are the
Had my first successful experience using a browser agent to solve a real problem - in this case I had the Claude in Chrome extension help me find some configuration I had lost deep within the Cloudflare control panel https://t.co/fpgx8hpnce
OpenAI and Anthropic engineers don't prompt like everyone else. I've been reverse-engineering their techniques for 2.5 years across all AI models. Here are 5 prompting methods that get you AI engineer-level results: https://t.co/9k64cbQ5I4
New York’s New AI Law Creates Oversight Office, Standards https://t.co/TwOFyrn7wt @govtechnews
Splat's app uses AI to turn your photos into coloring pages for kids https://t.co/TJTDgCWE9h @SarahPerezTC @techcrunch
We have a new best open source model to close out 2025: GLM 4.7! It's been ~6mos since the first closed source model, Opus 4, broke 73% on SWE-Bench and GLM does 73.8%! It's fantastic at math and coding and beats DeepSeek / Kimi. Very cheap at $0.6/M in, $2.2/M out, 200k context, and fast too: 70tok/s! The bigger story here is how the gap between closed and open source models has evolved. This time last year, OpenAI launched o1-preview and the closest OSS thing we had was DeepSeek R1-lite. We're still ~6mos off but there are at least 4 close open-source competitors.
Woah, SAM3 just reached 1 million downloads on HuggingFace! https://t.co/zcIBDPWPOI
Woah, SAM3 just reached 1 million downloads on HuggingFace! https://t.co/zcIBDPWPOI
"May my heart be kind, my mind fierce, and my spirit brave.” ~K. Forsyth https://t.co/vWMZ7ItNkA
From complex customer feedback, @SurveySparrow is enabling real-time insights. Using robust, compliant AWS infrastructure & genAI solutions, the startup is helping marketers get value from data & scale with confidence. https://t.co/GINfqOZeLD
Experts say that a fraud that has long existed has now become both easier and faster. https://t.co/VPyLolODNd @CSOonline
AI translation is replacing interpreters in GP care here’s why that’s troubling https://t.co/VV71XxDurD @ConversationUS @ConversationUK
AI 'friend' could help you plan your next vacation https://t.co/EqK69XGfiY @FuturityNews
The World is Your Canvas Painting Promptable Events with Reference Images, Trajectories, and Text https://t.co/MAsRMGjV1R
discuss: https://t.co/uefcEJi9cw
nice https://t.co/WbiKCQ8UAg
