looks like today's going to be a great day for vibe-coding
@datachaz
-
Testing a 100% SMS-native AI assistant
By
–
Been testing this, seriously cool launch 👀
— Charly Wargnier (@DataChaz) 19 mars 2026
Email is async. Slack is real-time. @HeyNoahAI is preemptive!
Zero apps to install.
it's a 100% SMS-native assistant that texts you vital context BEFORE your meetings begin.
Want to bypass the waitlist?
Use my VIP link in this 🧵↓ https://t.co/lvBpvgXbPMBeen testing this, seriously cool launch Email is async. Slack is real-time. @HeyNoahAI is preemptive! Zero apps to install. it's a 100% SMS-native assistant that texts you vital context BEFORE your meetings begin. Want to bypass the waitlist? Use my VIP link in this ↓
-
Dispatch research preview for mobile AI interaction
By
–
🚨 Anthropic just dropped its 🦞 @OpenClaw competitor
— Charly Wargnier (@DataChaz) 18 mars 2026
Meet Dispatch.
A new research preview in Claude Cowork that completely changes how you interact with AI.
Here’s how it works:
1️⃣ Pairs your phone to a persistent Claude session on your desktop
2️⃣ Message tasks on the go,… pic.twitter.com/HkTnNpYp0JAnthropic just dropped its @OpenClaw competitor Meet Dispatch. A new research preview in Claude Cowork that completely changes how you interact with AI. Here’s how it works: Pairs your phone to a persistent Claude session on your desktop Message tasks on the go,
-
MiniMax-M2.7 model hits SWE-Pro SOTA at 56.22%
By
–
MiniMax-M2.7 is here. → matching Sonnet 4.6 as an agent
→ recovering live incidents in just 3 minutes
→ hitting SOTA in SWE-Pro (56.22%) It even edits your Office files -
Which LLM excels at persuasive copywriting?
By
–
Let's settle this. if we're talking purely about persuasive copywriting quality, which LLM takes the crown?
-
Deeplake AI memory economics for agent workflows
By
–
Agent usage is spiky so stop paying for 24/7 databases. @Activeloop just dropped Deeplake to fix AI memory economics: → Instant sandboxed Postgres
→ Built for agent workflows
→ Handles text/vectors/video natively Only pay for the compute your agent swarm actually uses -
Technical Overview of MCP Client ID Authentication Model
By
–
3/
— Charly Wargnier (@DataChaz) 18 mars 2026
Now here's the best part → CIMD 🔥
Under the new MCP auth model, a client hosts a metadata.json file over HTTPS and uses that exact URL as its Client ID.
This means significantly less pre-registration and a fundamentally cleaner trust model. pic.twitter.com/OK3rkF1SKY3/ Now here's the best part → CIMD Under the new MCP auth model, a client hosts a metadata.json file over HTTPS and uses that exact URL as its Client ID. This means significantly less pre-registration and a fundamentally cleaner trust model.
-
Securing AI Agent MCP Server Integrations
By
–
1/
— Charly Wargnier (@DataChaz) 18 mars 2026
First, let's look at Descope's MCP integration.
When giving AI agents access to external tools, securing that connection is critical.
Descope handles this using:
→ Full MCP server auth
→ OAuth 2.1 support
→ PKCE validation
Your agents only operate within strict,… pic.twitter.com/cS6ivvB4Sl1/ First, let's look at Descope's MCP integration. When giving AI agents access to external tools, securing that connection is critical. Descope handles this using:
→ Full MCP server auth
→ OAuth 2.1 support
→ PKCE validation Your agents only operate within strict, -
Descope Introduces Agentic Identity Hub for AI Agent Security
By
–
Looking for bulletproof security for AI agent access?@DescopeINC just changed the game with their Agentic Identity Hub 🔥
— Charly Wargnier (@DataChaz) 18 mars 2026
→ MCP server authentication backing OAuth 2.1, PKCE, DCR, and CIMD
→ A secure vault stocked with 50+ templates and short-lived tokens
→ Strictly scoped,… pic.twitter.com/hLcg0mIibrLooking for bulletproof security for AI agent access? @DescopeINC just changed the game with their Agentic Identity Hub → MCP server authentication backing OAuth 2.1, PKCE, DCR, and CIMD
→ A secure vault stocked with 50+ templates and short-lived tokens
→ Strictly scoped,