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) 🚨 ICYMI @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/2043246635996807300#m
LLMS
-
Claude AI Performance Decline: Reliability Issues and User Frustration
By
–
this guy just explained why @claudeai feels worse despite more updates: > Core reliability dropped to 98.73% uptime, hurting devs who need stability > Strained compute is wasted on fluff features like the /buddy terminal pet > Severe GPU constraints lead to tight usage limits and forced context clearing > Many cancelling Pro tiers to force Anthropic to listen > Even enterprise users report major regressions, confirming the OP's exact issues
-
Google’s AI Watermark Cracked by One Person
By
–
BREAKING: GOOGLE’S “UNBREAKABLE” AI WATERMARK JUST GOT JAILBROKEN BY ONE GUY WITH A LAPTOP. I don’t think people understand the gravity of what just happened. Every single image Nano Banana has ever generated carries SynthID, an invisible watermark baked into every pixel.
-
Where to Look for Generative AI Risks – MIT Sloan
By
–
Where to look for #GenerativeAI risks by Beth Stackpole @MITSloan Learn more: bit.ly/4uybBsA #LLM #GenAI #ArtificialIntelligence #MachineLearning
→ View original post on X — @ronald_vanloon, 2026-04-12 07:48 UTC
-
Scobleizer Praises Hermes Agent as Best Open-Source AI Tool
By
–
I'm frequently using Claude Code and i love @openclaw. But i would say Hermes Agent from @NousResearch is the best open-source agent I’ve ever used, especially given that it comes from an independent startup rather than a major LLM giant.
→ View original post on X — @scobleizer, 2026-04-12 07:45 UTC
-
Comparing LangGraph, AutoGen, and CrewAI for Full Stack AI
By
–
One person running this full stack is ambitious. Curious how you pick between options like LangGraph, autogen and CrewAI for a given use case George 🙂
-
Verso AI launches engine to simplify slide editing for LLMs
By
–
Today we launch Verso AI: the mission is to solve PowerPoint!
— m_ric (@AymericRoucher) 12 avril 2026
In short, we've made an engine to represent slides (horrible OOXML language) into one language that's easier for LLMs to edit ; that was a long work, but now it's paying off, because on our benchmark, Verso beats… pic.twitter.com/21l1zWYYt7Today we launch Verso AI: the mission is to solve PowerPoint! In short, we've made an engine to represent slides (horrible OOXML language) into one language that's easier for LLMs to edit ; that was a long work, but now it's paying off, because on our benchmark, Verso beats
-
Memory Importance in Viral Blog Discourse
By
–
This blog made the rounds for a reason. Memory isn't optional!
-
High-Signal Trajectories and DPO for Agent Optimization
By
–
Good solution. Btw, Once you’ve identified the high-signal trajectories, you can also pair them with counterfactual continuations (what the agent should have done at the point of failure) to construct preference pairs for DPO. So the signals don't just act as a debugging tool
-
Muse Spark outperforms expectations after year without Meta models
By
–
I think Muse Spark came in far better than most were expecting as the first new model attempt from Meta, especially given the fact that it has been a year since Llama 4 with no models at all (and that Llama 4 was generally considered a dead end).