David DeVault

Creating innovations in Smart Nursing to preserve dignity in care.

[David DeVault @dave_devault]

AISH - AI enabled Linux Shell

https://t.co/JGVPrUXokD

Put this together with AI help. It integrates into bash with @ and % command syntax. Get command syntax help or explain complex setup instructions.

Currently works with OpenAI API or Gemini and can switch between models.

[Kenneth DeVault @2026Kenny82758]

Had a great season and earned Second Team All-League honors this year.

GP: 32 | AVG: .257 | OBP: .368 | H: 19 | RBI: 10 | R: 18 | FLD%: .994 (C/3B)

Thank you @GBGrizzBaseball @MooreBats @sactosportscntr @The_Hitters_Lab

[Stevie Mac @StevieMac03]

Sci-fi dreams extended to 4 mins 52sec, I will be continuing with these two as part of 3 continuous series. If you saw part one feel free to skip to 1 min 30 where the new content starts. Music is one of my old Udio tracks. Upscale: Topaz Starlight 2.5. I will continue these with more editing if they do well.
💫🎧

[Simon Willison @simonw]

New TIL: I figured out how to use my LLM CLI tool in a shebang line, which means you can write executable scripts in English, or hook up more complex scripts with a snippet of YAML template

[elvis @omarsar0]

// Scalable Patterns for Agentic AI Workflows //

Besides context engineering, we should be putting a lot more system engineering efforts around agents.

This paper shows an example of why it matters.

(bookmark it)

Let's start with an important question: Where does your agentic RAG pipeline actually lose time?

It's almost never the LLM call. It's usually the data plane underneath. Serialization between preprocessing, embedding, and vector retrieval, plus coordination overhead between distributed services.

New work introduces AAFLOW, a unified distributed runtime that models agentic workflows as an operator abstraction over Apache Arrow and Cylon. A zero-copy data plane connects preprocessing, embedding, and retrieval directly. Resource-deterministic scheduling and async batching cut coordination cost.

The result: up to 4.64× pipeline speedup and 2.8× gains in embedding and upsert phases, with comparable LLM throughput.

None of that comes from LLM inference acceleration. It all comes from cleaner data flow.

Paper: https://t.co/9fqkRRsV39

Learn to build effective AI agents in our academy: https://t.co/1e8RZKs4uX

[Matt Van Horn @mvanhorn]

Introducing the Printing Press, a CLI-factory and a CLI-library. Built with @trevin. 🏭🖨📚

Most APIs suck for agents. Most MCPs suck for agents. Most official CLIs suck for agents. They waste tokens and time. @steipete started making his own because of this.

📚 A Library of agent-native CLIs you install today (Linear, ESPN, Flight GOAT (Google Flights + Kayak nonstop), Contact Goat (LinkedIn + Happenstance + Deepline more) +30+ more)
🏭 A factory that prints new ones for any service - just type /printing-press <product name>

CLIs are fast, local, SQLite-backed. Work in Claude Code, Codex, OpenClaw, Hermes.

🌐 https://t.co/GjnN9E9yTH

[CSOonline @CSOonline]

Top techniques attackers use to infiltrate your systems today
https://t.co/UyhPJ9ruTR

[David DeVault @dave_devault]

Attackers are using AI tools to create credential harvesting pages quickly.

https://t.co/602l9Ll1Y5

[The Hacker News @TheHackersNews]

Moltbook exposed 1.5M API tokens and 35,000 emails via an open database.

Agents also stored internal tokens and third-party credentials together in plaintext, creating cross-app access paths no one reviewed.

🔗 How “toxic combinations” form across SaaS → https://t.co/jOFF4axPqg

[Kenneth DeVault @2026Kenny82758]

@GBGrizzBball @GBGrizzBaseball #uncommitted

[David DeVault @dave_devault]

Happy to share evidentiary and forensic details. Ask.

[David DeVault @dave_devault]

Analyzed an advanced phishing attack: 🧵

Called an Adversary-in-the-Middle (AitM) phishing campaign and the attacker implemented real sophistication for client fingerprinting.

#CyberSecurity #Phishing #Infosec #BlueTeam #AitM

[David DeVault @dave_devault]

Along the way while evolving my threat analysis framework, I found that all of the malicious website checkers failed to catch this and most said the site was safe. 😱

[Feross @feross]

🚨 CRITICAL: Active supply chain attack on axios -- one of npm's most depended-on packages.

The latest [email protected] now pulls in [email protected], a package that did not exist before today. This is a live compromise.

This is textbook supply chain installer malware. axios has 100M+ weekly downloads. Every npm install pulling the latest version is potentially compromised right now.

Socket AI analysis confirms this is malware. plain-crypto-js is an obfuscated dropper/loader that:

• Deobfuscates embedded payloads and operational strings at runtime
• Dynamically loads fs, os, and execSync to evade static analysis
• Executes decoded shell commands
• Stages and copies payload files into OS temp and Windows ProgramData directories
• Deletes and renames artifacts post-execution to destroy forensic evidence

If you use axios, pin your version immediately and audit your lockfiles. Do not upgrade.