Your curated collection of saved posts and media
You guys sure had fun this day. https://t.co/MfELwKSxgn
art not made with ai https://t.co/buZmvqz14C
art not made with ai https://t.co/buZmvqz14C
Phil Hartman as the Grinch, from a 1994 Behind the Scenes special on TNT. Not directly related to The Simpsons, but this clip was too good to not share, since Phil was a regular Simpsons guest star during this time. https://t.co/Uu82eT1E89
https://t.co/MFMONRsUVM
This is Judge Joy Kennedy Earlier this month, she lowered the bail for a repeat violent offender to $5k in Cleveland 5 days later, he kiIIed Ben McComas https://t.co/bSDadGElI1
🇺🇸 SEATTLE WOMAN BLINDED BY CAREER CRIMINAL WHO HAD 8 ARRESTS THIS YEAR ALONE This is what “criminal justice reform” looks like in Seattle: On Dec 5, 2025, 42-year-old Fale Vaigalepa Pea attacked Jeanette Marken, a completely innocent elderly woman, outside the King County Courthouse. Marken was standing near the courthouse earlier this month, waiting to cross the street, when Pea allegedly approached her from behind and struck her in the head with a wooden board. She’s now permanently blind in one eye, with a shattered cheekbone and broken nose. And the kicker? Her attacker had eight prior arrests in 2025 alone, all for violent and criminal behavior… and he still kept getting released. He’s been on law enforcement’s radar since 2011 and been through the system repeatedly. And yet, somehow, he was walking around free, ready to ruin another life. Marken’s son, Andrius Dyrikis, is demanding to know why the system protected him instead of the public, and honestly, we all should be. Now Pea is finally being held on $1M bail for first-degree assault, but it took a brutal, life-altering attack to get there. How many more innocent people have to suffer before cities like Seattle admit that “restorative justice” is just a PR slogan, not public safety? Source: IJR, The New York Post, @AmericaPapaBear
Leftists use pathos to override logos in order to push their activism. The “pity play” is a common form of this. It disarms you by flooding you with pity, guilt, & moral urgency so your judgment and discernment never gets a chance. Cue the crying child, or the one-sided history. Then comes the demand: accept the leftist moral frame and the activism that follows. If you resist, the label is not just an insult. It’s a social activation switch, greenlighting attacks on you: “racist,” “hateful.” The point is to mobilize bystanders, raise the social cost of saying no, and make you the example so others learn that compliance is the price of staying “decent.”
Still can’t believe this happened … ❤️🖤🩶🤍 https://t.co/XuK3YTyLlo
Starlink's high-speed, low-latency internet is now available in the Cayman Islands! 🛰️🇰🇾❤️ → https://t.co/ebhreaCiw5 https://t.co/OshXvW7kv6
ELON MUSK: WE WANT TO HAVE EMPATHY THAT IS DEEP, NOT SHALLOW we want to have empathy for our fellow humans. I strongly believe we should care about humanity and we should care about the future. But we need to have empathy that is deep, not shallow Shallow empathy is caring about criminals, but deep empathy is caring about the victims of the criminals. Why do we have repeat violent offenders released on the streets, often with no bail? It's crazy. And they prey upon innocent people. Then our streets are not safe
Custom instructions, https://t.co/OxVZGa4DEg files, rules, and now skills… when to use what or all: best breakdown so far: https://t.co/UOqLkeeAOW #vscode #githubcopilot
Custom instructions, https://t.co/OxVZGa4DEg files, rules, and now skills… when to use what or all: best breakdown so far: https://t.co/UOqLkeeAOW #vscode #githubcopilot
Timothée Chalamet has become the first person to appear on top of The Sphere in Las Vegas https://t.co/W9pwhKzlR4
Wild. By far the most complete Claude Skills repo yet 🤯 @Composio’s Awesome-Claude-Skills packs 100`s of ready-to-use workflows: ↳ PDF tools, changelog generation ↳ Playwright automation ↳ AWS/CDK tools, MCP builders ... and much more! Free and open-source. Repo in 🧵↓ https://t.co/kJhZHLU5OA
How to inject Higher Order Instructions for Claude Code: - Allows for Agent Personas (Planner, Build, QA etc) - Allows for Partner Agent approach that can think on higher level - System instructions have stronger adherence For injecting the instructions at runtime, use this command: claude --append-system-prompt "$(cat ./PARTNER.md)" The Claude .md files is passed as a user message with <system-reminder> tags and is re-injected after compaction, which overall allows drift in my experience I have seen huge performance improvements in instruction following by using the Higher Order approach - just make sure to keep it lean and following the prompting guidelines for Opus 4.5
I wrote about how I've been having a ton of fun cooking with LLMs recently - including having Claude take a photo of two recipe cards and vibe-code me up a custom timer application to help me prepare two meals at once https://t.co/qK5fvtF9FG
Claude Code plugins now support LSP servers. LSP (Language Server Protocol) gives Claude real-time code intelligence while working on your codebase. Before: Claude had to read files, run type checkers, and piece together error messages to understand what's broken. Now with LSP: Claude gets instant diagnostics, knows exactly where errors are, can jump to definitions, and sees type information in real-time. For teams: Package your LSP configs in a plugin and publish to your internal marketplace. Your team gets the same code intelligence setup without individual configuration. One person sets it up, everyone benefits.
🚀 42.55x Speedup! LightX2V delivers Day 0 support for @Alibaba_Qwen new Qwen-Image-Edit-2511! 🔥 47% framework speedup ⚡️ CFG+4-step distillation (↓25x compute) 📈 42.55x total acceleration Repo: https://t.co/SATQr3KA7m Model: https://t.co/ik3MVMnrQK https://t.co/4jqPXaao9F
How can you tell if the stated caffeine dose on an energy drink is right? I made a video showing how I measured the concentration myself at home! And for this test beverage, the estimate (144.1 += 19.6mg) lines up perfectly with the label's 150mg 😀 https://t.co/FK83gKhwfE https://t.co/TqrfsqouWu
Are LLMs any good for web API integrations? While we see a lot of fancy demos, the reality is that LLMs still largely struggle with web API integrations. The default assumption is that code models can handle API calls reliably. After all, they excel at general code completion tasks. But web APIs have unique challenges that break this assumption. This new research introduces WAPIIBench, a benchmark for evaluating LLM-generated web API invocation code across four real-world APIs: Asana, Google Calendar, Google Sheets, and Slack. None of the evaluated open-source models solved more than 40% of tasks. Even when given the correct endpoint, models still generated 6-31% illegal arguments. URLs get hallucinated 14-39% of the time. Why is this so hard? Web API invocations differ from regular function calls in critical ways. Operations are identified by HTTP method plus long URL strings, not simple function names. Multiple argument lists exist across body, header, and query locations. Parameters have complex nested data types. And API specifications are documented externally, limiting what models can memorize. The researchers propose a solution: constrained decoding. They automatically translate OpenAPI specifications into regex-based constraints that filter token predictions during generation. The constraints enforce compliance with API specs without requiring model modifications or prompt adjustments. Constrained decoding improves correctness by 90% on average for full completion and 135% for argument completion. Illegal URLs, methods, and arguments drop to zero. Models that previously generated zero executable code now achieve similar rates to other models. Great read for AI devs. Paper: https://t.co/OXFKJRMmJc Learn to build effective AI agents in our academy: https://t.co/zQXQt0PMbG
Santa receives thousands of letters every year—Processing these manually takes a lot of time, so this year, we're helping him out 👇 We built an agent to automate extracting wish-list items from letters 🎅 📤 Upload to LlamaCloud ✂️ LlamaSplit categorizes pages into logical segments (letters vs. index pages) using AI-powered document understanding 📋 LlamaExtract extracts structured data from each child's letter—name, age, wishlist items, address, and whether they've been good or bad (using Pydantic schemas for type-safe extraction) 🔄 LlamaAgent Workflows orchestrates the process with a fan-in pattern: split the document into segments, then extract data from each letter segment in parallel The result? Transform a messy multi-page PDF into clean, structured JSON for every child's wishlist—automatically handling document segmentation, parallel extraction, and data validation. Try it yourself in this Colab notebook: https://t.co/TbLLah1BV5
MiniMax M2.1 is a SoTA 10B-activated OSS coding & agent model, scoring 72.5% on SWE-multilingual and 88.6% on our newly open-sourced VIBE-bench, exceeding leading closed-source models like Gemini 3 Pro and Claude 4.5 Sonnet. https://t.co/3mFEc57V6S
The secret sauce to get the most out of MiniMax M2.1 for complex agentic tasks is the interleaved thinking. It excels at integrating composite instruction constraints (as seen in OctoCodingBench), ready for office automation tasks. https://t.co/UxAEzfvRan
I was also testing it for designing websites. The aesthetics are much nicer than what I get with Gemini 3 Pro. More examples of this soon. Stay tuned! M2.1 docs here: https://t.co/YdCOkaAbo2 Check out my deep research agent here: https://t.co/6oCi8ig6At
DataFlow An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI https://t.co/SbPUMOIvnA
The Prism Hypothesis Harmonizing Semantic and Pixel Representations via Unified Autoencoding https://t.co/iNjvF1Z41i
Region-Constraint In-Context Generation for Instructional Video Editing https://t.co/T0Th0WTaCp
Qwen-Image-Edit-2511 is out on Hugging Face https://t.co/rKveDT8bfk
app: https://t.co/C3eUAPqaGR
