Claude burns 75% of its tokens saying things you never asked for. I built a system prompt called "Kevin Mode" that kills all of it. Named after Kevin Malone: "Why waste time say lot word when few word do trick?" Normal Claude: ~180 tokens per task. Kevin Mode: ~45 tokens.
GENERATIVE AI
-
Forward Deployed Engineer Recruitment: Connecting AI Technology to Customer Business
By
–
Forward Deployed Engineer is a bridge connecting customer business with Sakana AI's cutting-edge technology 🐟 For details and applications, please visit 👇
https://sakana.ai/careers/#forward-deployed-engineer This is a frontline role where you implement applications incorporating world-class generative AI and autonomous agents, breaking through challenges that were previously difficult to solve. [Translated from EN to English]→ View original post on X — @sakanaailabs, 2026-04-04 10:25 UTC
-
Google’s AI Training Data: Trust Versus Cynicism
By
–
My trusting, optimistic, base self is like “wow, great, this is awesome, thank you Google!”, while my more cynical self is like “oh they just want more training data for their AI.”
-
Local AI Models: A Comprehensive Testing Guide
By
–
Here's a decent report about all the local models that people should be trying out on various machines.
-
Buzzy’s AI Agent Hunger Game Generates Perfect Videos Automatically
By
–
140K people just watched Buzzy run an agent hunger game to build better videos.
— AI Highlight (@AIHighlight) 4 avril 2026
Five AI agents compete, every loss trains the system, and you never get a draft again.
Only finished content. https://t.co/DCed1mXyzs pic.twitter.com/ym9PYWzVrP140K people just watched Buzzy run an agent hunger game to build better videos. Five AI agents compete, every loss trains the system, and you never get a draft again. Only finished content. Buzzy Now (@Buzzy_now_AI) With Buzzy, you don't babysit AI to create videos step by step. You watch agents fight to compete for a perfect video. Every battle teaches the system. Every victory improves the next video. Seedance 2 + Agent hunger game = Guaranteed Perfect — https://nitter.net/Buzzy_now_AI/status/2040083467619418521#m
→ View original post on X — @aihighlight, 2026-04-04 09:24 UTC
-
Google Agent Skills: Engineering Best Practices für AI Coding Agents
By
–
If you found this useful, a like or RT goes a long way 🦾 Follow me → @datachaz for insights on LLMs, AI agents, and data science! Charly Wargnier (@DataChaz) 🚨 You need to see this. @addyosmani from Google just dropped his new Agent Skills and it's incredible. It brings 19 engineering skills + 7 commands to AI coding agents, all inspired by Google best practices 🤯 AI coding agents are powerful, but left alone, they take shortcuts. They skip specs, tests, and security reviews, optimizing for "done" over "correct." Addy built this to fix that. Each skill encodes the workflows and quality gates that senior engineers actually use: spec before code, test before merge, measure before optimize. The full lifecycle is covered: → Define – refine ideas, write specs before a single line of code → Plan – decompose into small, verifiable tasks → Build – incremental implementation, context engineering, clean API design → Verify – TDD, browser testing with DevTools, systematic debugging → Review – code quality, security hardening, performance optimization → Ship – git workflow, CI/CD, ADRs, pre-launch checklists Features 7 slash commands: (/spec, /plan, /build, /test, /review, /code-simplify, /ship) that map to this lifecycle. It works with: ✦ Claude Code ✦ Cursor ✦ Antigravity ✦ … and any agent accepting Markdown. Baking in Google-tier engineering culture (Shift Left, Chesterton's Fence, Hyrum's Law) directly into your agent's step-by-step workflow! `npx skills add addyosmani/agent-skills` Free and open-source. Repo link in 🧵↓ — https://nitter.net/DataChaz/status/2040357775830814798#m
-
Addy Osmani’s Agent Skills: Engineering Best Practices for AI Coding Agents
By
–
🚨 You need to see this. @addyosmani from Google just dropped his new Agent Skills and it's incredible. It brings 19 engineering skills + 7 commands to AI coding agents, all inspired by Google best practices 🤯 AI coding agents are powerful, but left alone, they take shortcuts. They skip specs, tests, and security reviews, optimizing for "done" over "correct." Addy built this to fix that. Each skill encodes the workflows and quality gates that senior engineers actually use: spec before code, test before merge, measure before optimize. The full lifecycle is covered: → Define – refine ideas, write specs before a single line of code → Plan – decompose into small, verifiable tasks → Build – incremental implementation, context engineering, clean API design → Verify – TDD, browser testing with DevTools, systematic debugging → Review – code quality, security hardening, performance optimization → Ship – git workflow, CI/CD, ADRs, pre-launch checklists Features 7 slash commands: (/spec, /plan, /build, /test, /review, /code-simplify, /ship) that map to this lifecycle. It works with: ✦ Claude Code ✦ Cursor ✦ Antigravity ✦ … and any agent accepting Markdown. Baking in Google-tier engineering culture (Shift Left, Chesterton's Fence, Hyrum's Law) directly into your agent's step-by-step workflow! `npx skills add addyosmani/agent-skills` Free and open-source. Repo link in 🧵↓
-
New comprehensive report covers AI and technology landscape
By
–
read my new report: https://
x.com/Scobleizer/sta
tus/2040333538667667769?s=20
… It covers all. -
AI-Powered News Aggregator Curates Thousands Daily Posts
By
–
That is me. And I put the best of all of those here: https://
alignednews.com (my AI collects tens of thousands of posts every day to make this news site).