@mattpocockuk@zeeg I tried your skills, waste of time for really deep challenges.
You must use the recommendation layer that includes many tools and load/unload the tools, depending on the task.
github.com/stevesolun/ctx
@mattpocockuk Meaning that within this plugin your skills will be up to date on every change?
I want to use it in my recommendation layer:
github.com/stevesolun/ctx
The workflow:
Observe real runs →
identify repeated tasks →
move predictable work from model calls into ordinary code →
keep the LLM for judgment and reasoning →
benchmark quality, cost, and latency.
Read the full guide:
gist.github.com/stevesolun/7f5…
Most AI agents use expensive model calls for work that should be deterministic: fetching, parsing, filtering, retries, and state.
Profile real runs. Keep the LLM where reasoning creates value.
Compile everything else into software.
Full practical guide ↓
Releasing the model weights and technical report of Kimi K3.
Kimi K3 is our most capable model: a 2.8T MoE model with native visual understanding and a 1M-token context window.
New model architecture: 2.5x the intelligence per unit of compute, not just more params.
Alongside Kimi K3, we're opening up more of the stack behind it — high-performance attention kernels, MoE communication library, and infrastructure for running agent environments at scale.
Model weights: huggingface.co/moonshotai/Kim…
Tech report: github.com/MoonshotAI/Kim…
Tech blog: kimi.com/blog/kimi-k3
One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10
Someone open sourced the entire recipe for a personal AI computer. Not software, the hardware: parts list, CAD, BIOS settings, assembly photos. 4 builds, from 2x RTX 5090 (64GB VRAM) up to 4x RTX PRO 6000 (384GB). MIT license, fork it and sell it.
github.com/autonomous-ai/…
@mattpocockuk Must have chapter in that course should be the recommendation layer for LLMs that will load and unload only the necessary/unnecessary tools.
github.com/stevesolun/ctx
Proudly representing #Israel at the Prague Folklore Festival! 🇮🇱
We marched with our national flag and received so much warmth and love from people visiting #Prague. What an incredible, unforgettable experience!
A wow moment!
@naftalibennett@gadi_eisenkot@netanyahu@AvigdorLiberman
2K Followers 1K FollowingExploring ideas about the AI revolution, life, the universe, and the NHI Phenomenon. Lawyer by day, guitarist at night, who daydreams about The Singularity.
517 Followers 5K FollowingOkur-yazarlığı kesin ama özellikle yazmak istiyor. Bu nedenle okuma aşamasnda. Lisans Gazi Ekonometri, Y. Lsns ve Dr. D.P. Ünv. Not: RT+FAV Onay Anlamına gelmez
1K Followers 2K FollowingToo Bored to Ape 🐒 | My Rug Rugged Me 💀 | ADHD maxi since '03 🧠 | Petite Penguin Survival Mode Activated 🐧 | Shaved Ice Stand Open 🍨🍧
749 Followers 2K FollowingJoshua went to him and asked, “Are you for us or for our enemies?” “Neither,” he replied, “but as commander of the army of the Lord I have now come.” -Joshua 5
2K Followers 1K FollowingExploring ideas about the AI revolution, life, the universe, and the NHI Phenomenon. Lawyer by day, guitarist at night, who daydreams about The Singularity.
28K Followers 67 FollowingAI researcher & teacher @SCAI_ASU. Former President of @RealAAAI; Chair of @AAAS Sec T. Here to tweach #AI. YouTube Ch: https://t.co/4beUPOmf6y Bsky: rao2z
10K Followers 548 FollowingHype-free rational view on AI. Also on threads: @[email protected], https://t.co/mwZKgJgrN2
Caution: will block ad hominem instantly.
132K Followers 178 FollowingProfessor of computer science at UW and author of '2040' and 'The Master Algorithm'. Into machine learning, AI, and anything that makes me curious.
63K Followers 652 FollowingUniversity Distinguished Professor (Emeritus), Oregon State Univ.; Former President, AAAI; Currently Chair CS Section of ArXiv
51K Followers 671 FollowingProfessor, Santa Fe Institute. Mostly posting on https://t.co/4NpA2IL5Va (at-melaniemitchell). More thoughts at https://t.co/nC43NHRozX.
235K Followers 7K FollowingOG GenAI Skeptic; spoke at US Senate. Warned about hallucinations in 2001. Advocating world models & neurosymbolic AI ever since. Author, Marcus on AI & 6 books
31K Followers 334 FollowingAi and Tech content Creator. 30k+ on X | 350k+ on Linkedin. Sharing insights on Ai, Tech, Free tools, resources. DM for collabs at : [email protected]
726K Followers 121 Following#1 NYT Bestselling Author: The 48 Laws of Power, The Art of Seduction, The 33 Strategies of War, The 50th Law, Mastery, The Laws of Human Nature, The Daily Laws
563K Followers 2 FollowingUncovering the timeless principles that drive success.
Host @tkppodcast
If you get an oil change at @jiffylube let me know about your experience.
1.3M Followers 0 FollowingAuthor of the #1 NYT bestseller Atomic Habits (https://t.co/aWrO9DWkH5). I write about building good habits. Over 3 million people read my 3-2-1 newsletter.
721K Followers 124 Following#1 New York Times Bestselling Author of five books, including "The Subtle Art of Not Giving F*ck". Co-Founder of @Purpose_AI. Host of Solved Podcast.
10K Followers 948 FollowingSearching for the wise way to interact with AI.
Experiments are on GitHub
Chat bot are likely not it.
We probably need more AI commands and einks, less chats
5.8M Followers 68 FollowingChristian, Conservative, Republican- In That Order. Husband, Father, Grandfather and 48th Vice President of the United States🇺🇸
6K Followers 434 FollowingHiker, Tenor, Traveler, Aspiring Amateur Law Professor, and Amazon’s Chief Global Affairs & Legal Officer (Opinions are my own.)