this guy literally created a Kebab benchmark for LLMs ♨️♨️♨️ pic.twitter.com/9vY9zLdqBe
— Charly Wargnier (@DataChaz) 25 juin 2026
this guy literally created a Kebab benchmark for LLMs
@datachaz
-
Man creates Kebab benchmark for LLMs
By
–
-
Anthropic accuses Chinese tech giants of record AI heist
By
–
🚨 Anthropic is accusing Alibaba, DeepSeek, and other Chinese tech giants of orchestrating the largest AI heist in history.
— Charly Wargnier (@DataChaz) 25 juin 2026
Over 45 days, these companies allegedly bypassed geo-blocks to launch a massive "distillation attack",
using 25,000 fake accounts and 28.8 million… https://t.co/N6MWQILdzs pic.twitter.com/HmBkKKlx5cAnthropic is accusing Alibaba, DeepSeek, and other Chinese tech giants of orchestrating the largest AI heist in history. Over 45 days, these companies allegedly bypassed geo-blocks to launch a massive "distillation attack", using 25,000 fake accounts and 28.8 million
-
User praises moxt.ai after trying impressive demo
By
–
Just tried this out, it is pretty impressive. great job, @moxt_ai > https://
moxt.ai -
Agent teams replace small SaaS with custom-built workflows
By
–
The replacement for small SaaS isn't more software.
— Charly Wargnier (@DataChaz) 24 juin 2026
It’s an agent team building it for you!
Watching @moxt_ai's Mini Apps run specialized agents makes this clear.
If a workflow can just deliver the exact output you need, the subscription model for internal tools will break 👀 https://t.co/lSY3IDcdaW pic.twitter.com/0C2LnJVfsrThe replacement for small SaaS isn't more software. It’s an agent team building it for you! Watching @moxt_ai
's Mini Apps run specialized agents makes this clear. If a workflow can just deliver the exact output you need, the subscription model for internal tools will break -
Dev tools evolution: Graftcode turns public methods into MCP tools
By
–
this is one of those things that makes you realize how far dev tools have come.
— Charly Wargnier (@DataChaz) 24 juin 2026
❌ before: hours of AI integration glue code
✅ now: expose the methods already living in your codebase@Graftcode turns ordinary public class methods into MCP tools through its gateway.
slick. https://t.co/WPJnHivZ5j pic.twitter.com/3ezRxRZ0Lhthis is one of those things that makes you realize how far dev tools have come. before: hours of AI integration glue code now: expose the methods already living in your codebase @Graftcode turns ordinary public class methods into MCP tools through its gateway. slick.
-
@datachaz — 2026-06-24
By
–
* TEXT VERSION * SESSION CONTROL
/clear → Wipes the slate clean for a fresh context window.
/rename [name] → Renames your session (leave blank to let Claude name it!).
/rewind → Undoes recent steps by rolling back to a checkpoint.
/resume [session] → Jumps back into an -
26 slash commands every power user needs to know
By
–
Want to master Claude Code? Here are 26 slash commands every power user needs to know. Save this list to supercharge your AI coding workflow ↓
-
Give AI Agents Persistent Memory with LangGraph and MongoDB
By
–
3/ Last → users HATE forgetful chatbots. You must give your agents a persistent brain. The 'Memory for AI Apps' module teaches you to use LangGraph and MongoDB to build stateful AI apps with isolated, long-term memory across sessions. Sweet. > https://
fandf.co/4uY0nN3 -
Vector Search Perf module for slow AI retrieval diagnosis
By
–
2/ Next problem → sluggish AI retrieval. Scaling it up is notoriously difficult. This Vector Search Perf module walks you through diagnosing slow queries with Atlas Metrics. PLUS actually managing memory sizing and quantization in full production > https://
fandf.co/4b6Q3uW -
Unify vector search with Voyage AI retrieval pipelines
By
–
1/ First: aren't you tired of juggling a separate vector DB just to make semantic search work? You can keep it all unified. The Voyage AI course shows exactly how to build advanced two-step retrieval pipelines where your original data already lives. > https://
fandf.co/3SmvV1z