WOW I didn't see this one coming. Enterprise AI teams are spending months building internal infrastructure that Santander just open-sourced FOR FREE The @Santander_es AI Lab just dropped 11 repos under Apache-2.0. And you don't have to be a bank to use these. They released
@datachaz
-
Anthropic engineer urges shift from manual prompts to self-prompting systems
By
–
STOP TYPING MANUAL PROMPTS INTO CLAUDE.
— Charly Wargnier (@DataChaz) 22 juin 2026
In a new 26-minute breakdown, this Anthropic engineer shares a massive shift in how we should be thinking about AI:
"Don’t prompt models. Build systems that prompt themselves."
The problem?
95% of builders are completely missing the… https://t.co/SzKUoDqK7h pic.twitter.com/dyotIgdJJsSTOP TYPING MANUAL PROMPTS INTO CLAUDE. In a new 26-minute breakdown, this Anthropic engineer shares a massive shift in how we should be thinking about AI: "Don’t prompt models. Build systems that prompt themselves." The problem? 95% of builders are completely missing the
-
Google Crushed by Open-Source Chinese Models Despite Infinite Resources
By
–
Google: Infinite data. Unlimited compute. Still crushed by open-source Chinese models
-
Guide to building an AI second brain with Claude and Obsidian
By
–
🚨 Yarchi just published an awesome guide on building an AI "second brain" using Claude and Obsidian
— Charly Wargnier (@DataChaz) 22 juin 2026
Based on @karpathy's LLM Wiki concept, the idea is to stop starting from a blank chat window and start building a compounding knowledge graph.
Obsidian handles the local… https://t.co/Jl8sflLBuH pic.twitter.com/kbXaJaD0gwYarchi just published an awesome guide on building an AI "second brain" using Claude and Obsidian Based on @karpathy
's LLM Wiki concept, the idea is to stop starting from a blank chat window and start building a compounding knowledge graph. Obsidian handles the local -
Educational purposes excuse still bypasses AI guardrails
By
–
funny how “don t worry it's for educational purposes” still works against most AI guardrails
-
Vercel CEO’s comment on GLM 5.2 urges attention
By
–
When even @Vercel
's CEO says this about GLM 5.2, people should probably take notice -
PixelRAG: skip HTML parsing, screenshot for RAG
By
–
STOP PARSING HTML FOR RAG. JUST SCREENSHOT IT Researchers from UC Berkeley just released PixelRAG, an open-source system that skips HTML parsing entirely. Why is it changing web scraping for good? Well, instead of scraping a page into text and embedding chunks: #1 it
-
Up to 95% Token Reduction Without Code Changes
By
–
UP TO 95% TOKEN REDUCTION WITHOUT CHANGING THE CODE A Netflix engineer just open-sourced Headroom, and it’s one of the smartest ways I’ve seen to cut LLM costs. It wraps Cursor or Claude in a local proxy to compress your payload before it hits the LLM: → Intelligently shrinks
-
Claude AI Agent Integration Turns Jira into the Ultimate Source of Truth
By
–
THEY FINALLY DID IT. THEY PUT CLAUDE INTO JIRA. @Jira isn’t the shiny new thing. but that’s exactly why this matters. Millions of devs live in Jira every day because it’s the ultimate source of truth. The new @ClaudeAI Agent integration turns Jira from the place where work
-
Atomic_Mail lets AI agents have autonomous email inboxes without humans
By
–
HOLY F*CK, YOUR AGENT LITERALLY GOT ITS OWN PERSONAL EMAIL 🤯@Atomic_Mail just dropped, and it lets your AI agents register their own autonomous inboxes *without* needing a human in the loop.
— Charly Wargnier (@DataChaz) 19 juin 2026
If you build agentic workflows, you know that connecting them to traditional email… https://t.co/tNv6uMztcWHOLY F*CK, YOUR AGENT LITERALLY GOT ITS OWN PERSONAL EMAIL @Atomic_Mail just dropped, and it lets your AI agents register their own autonomous inboxes *without* needing a human in the loop. If you build agentic workflows, you know that connecting them to traditional email