Linda Vivah

Directions Website Contact the business

Linda Vivah Al/ML explained so it sticks⚡️
Al Engineer | Al Infra | 10+ yrs in tech | ex-AWS ☁️
singing-as-a-service 🎶 I mom x3 👶| 📍NYC

11/12/2026

AI Inference: a mini crash course … let’s go! ✨

Whether you run a business or build as an engineer, it’s one of the most important things to understand right now.

Training is how a model gets built. Inference is every time anyone uses it: every prompt, every agent call, every line of code.

Deloitte forecasts inference will be about two-thirds of all AI compute by 2026. With traditional software, one more user costs almost nothing. With AI, every request runs compute. More users, more compute, a bigger bill.

For LLM inference specifically, 4 common ways to bring that cost down:
🔹 KV caching: save earlier work so it isn’t redone
🔹 Continuous batching: keep the GPU busy
🔹 Quantization: smaller numbers, less memory
🔹 Right model, right job: easy requests go to smaller models

There are more too, like prompt caching, speculative decoding and distillation.

Save this for the next time someone asks what inference actually means.

Happy building 🤍

10/30/2026

7 core Claude Code features explained in 90 seconds.. let’s go! ⚡

To unlock Claude Code’s full potential you need to know what’s available to you. Here’s the TLDR:
🔷 CLAUDE.md → a markdown file Claude loads as context each session
🔷 Skills → packaged instructions Claude loads when the task matches
🔷 MCP → standard protocol for connecting Claude to external tools and data
🔷 Hooks → commands that run automatically at points in Claude’s lifecycle
🔷 Subagents → isolated Claude instances with their own context and tool access
🔷 Plugins → skills, hooks, and MCP configs bundled into one installable unit
🔷 Agent Teams → parallel Claude sessions with a lead, messaging each other directly

AI inference visual mini crash course: 40 must-know terms….let’s go! ✨Understanding AI inference is an important skill r...
10/28/2026

AI inference visual mini crash course: 40 must-know terms….let’s go! ✨

Understanding AI inference is an important skill right now whether you’re an engineer or you’re running a business.

Why? Unlike a training run, inference costs you money every time someone uses your product. It decides how fast the answer comes back, how many users you can serve, and what the bill looks like as usage grows. So it’s both a business challenge and an engineering challenge.

This is a visual crash course of the 40 core terms you need to know.

Comment ✨BLOG✨ and I’ll send you the written version with 50 must-know AI inference terms.

10/26/2026

LinkedIn just released its Top 50 Startups of 2026! I went through the list and here are my 4 takeaways ✨

🔗 If you would like the official blog search “Linkedln top 50 2026” or comment BLOG & I’ll DM you the link ✨

10/24/2026

How open-source AI helps doctors plan surgery on a child’s heart 🫀

At Children’s Hospital of Philadelphia (Children’s Hospital of Philadelphia Research Institute ), Dr. Matthew Jolley’s team models a child’s heart in 3D before surgery: in one case, two repairs had failed until the model clarified the anatomy.

💡 TLDR: open-source AI turns a child’s heart scan into a 3D model in seconds instead of hours, and because the tools are open, other children’s hospitals can use them and build on them.

How a scan becomes a 3D heart 👇
➡️ The team trains AI on scans where researchers already marked the anatomy
➡️ On a new scan it predicts which regions belong to which heart structure (that’s segmentation)
➡️ It runs on MONAI, an open-source medical imaging framework NVIDIA co-founded
➡️ Doctors explore that anatomy in 3D and plan around one specific child’s heart

A modeling step that took a skilled researcher about four hours now finishes in seconds.

Why does the open-source part matter?
Kids’ heart defects are too rare and too varied for traditional device companies to invest in. No single company has built these tools, and no single hospital could build them alone. So Dr. Jolley’s lab built them with the open-source community and made them free to use and build on. Stanford and Boston Children’s now contribute tools alongside CHOP, and more than 20 children’s hospitals in the US run cardiac modeling programs. Each team builds on the others’ progress.

Next: CHOP is working with NVIDIA on physics simulations of how a device will deploy inside a specific child’s heart, with the long-term goal of bringing real-time simulations into clinical workflows.

Follow for more AI for good stories 💙

NVIDIA

10/24/2026

How open source AI helps doctors plan surgery on a child’s heart 🫀

At Children’s Hospital of Philadelphia (Children’s Hospital of Philadelphia Research Institute ), Dr. Matthew Jolley’s team models a child’s heart in 3D before surgery: in one case, two repairs had failed until the model clarified the anatomy.

💡 TLDR: open-source AI turns a child’s heart scan into a 3D model in seconds instead of hours, and because the tools are open, other children’s hospitals can use them and build on them.

How a scan becomes a 3D heart 👇
➡️ The team trains AI on scans where researchers already marked the anatomy
➡️ On a new scan it predicts which regions belong to which heart structure (that’s segmentation)
➡️ It runs on MONAI, an open-source medical imaging framework NVIDIA co-founded
➡️ Doctors explore that anatomy in 3D and plan around one specific child’s heart

A modeling step that took a skilled researcher about four hours now finishes in seconds.

Why does the open-source part matter?
Kids’ heart defects are too rare and too varied for traditional device companies to invest in. No single company has built these tools, and no single hospital could build them alone. So Dr. Jolley’s lab built them with the open-source community and made them free to use and build on. Stanford and Boston Children’s now contribute tools alongside CHOP, and more than 20 children’s hospitals in the US run cardiac modeling programs. Each team builds on the others’ progress.

Next: CHOP is working with NVIDIA on physics simulations of how a device will deploy inside a specific child’s heart, with the long-term goal of bringing real-time simulations into clinical workflows.

Follow for more AI for good stories 💙

NVIDIA CHOP

10/23/2026

About 70% of websites run on PHP, & two critical flaws hiding in it for over a decade were just made public & patched 💻

💡They’re nicknamed PHP2Shell, & they’re in PHP itself, the language behind WordPress, Drupal, Joomla, Magento & a lot of the web. In vulnerable setups, someone can run code on a server with one web request, no login needed. So updating WordPress alone won’t fix it.

Here’s what to do:
➡️ Find your PHP version. On WordPress, go to Tools > Site Health. Otherwise, check your hosting dashboard under PHP settings
➡️ Fixed versions: 8.2.35, 8.3.36, 8.4.27, 8.5.12 or newer
➡️ On 8.1 or older: upgrade, or ask your host for a patched build
➡️ Run your own servers? Update, restart your PHP workers & rebuild Docker images with PHP inside. If it was online & unpatched, rotate its secrets too

And a good reminder for everyone:
🔹 Change any password you reuse & keep them in a password manager
🔹 Turn on 2FA (or passkeys) for your hosting, WordPress admin & email
🔹 Keep auto-updates on

The wild part: two separate teams found these bugs with AI. Attackers can use the same tools, & here attempts started before the patch was even out. Patch as soon as you can.

Comment ✨INFO✨ & I’ll DM you the links: the official PHP advisory + the exact question to send your host & the free tools that can check it for you.

I use voice AI 🎙️more than I type these days for a lot of reasons Well for one, as a mom I never have hands 😅 + I can ge...
10/21/2026

I use voice AI 🎙️more than I type these days for a lot of reasons

Well for one, as a mom I never have hands 😅 + I can get so much more nuance across & it’s wayyyyyy faster

💡 A 2016 Stanford study found speaking is about 3x faster than typing on your phone (161 words per minute vs 53), which tracks.

So these are the voice AI tools I’m using daily:

1️⃣ Wispr Flow
I have it installed everywhere & use it in so many apps, Claude a lot, most of my desktop apps & on my phone. I press Fn, start talking & it types into whatever app I’m in.

2️⃣ ChatGPT Voice
I think out loud with it. I can ramble, interrupt, change direction & it keeps up. I also use it a lot for translation, day to day stuff like at my parking garage & when I travel. Underrated.

3️⃣ Meta glasses + Muse
Directions when I’m with the kids, quick questions without pulling out my phone & I use Muse by voice too. Can’t wait for the new voice mode & Muse on the glasses.

What are your favorite voice AI tools these days? 👇

10/18/2026

Mini crash course: History of Chess AI by Nathaniel 😊

He is a way better yapper than me 🤣
Honestly, I had no idea he knew all of this. He plays a lot of chess, is a builder at heart, and just loves to learn and teach.

He has been asking me for a YouTube channel for the last 3 years (since he was 6)... so I finally created one for him today that will be managed by parents: ✨Nathaniels Amazing Universe✨ (can DM link)

Chess played a huge role in getting AI to where it is today: it started with Shannon mapping out computer chess in 1950, then Deep Blue beating Kasparov in 1997, and later AlphaZero learning the whole game from scratch just by playing itself.

Love his yaps 🥹 & shoutout to Levy Rozman who has been a huge chess influence and inspiration to him ♟️

10/14/2026

Address

3355 S Las Vegas Blvd
Las Vegas, NV
89109

Alerts

Be the first to know and let us send you an email when Linda Vivah posts news and promotions. Your email address will not be used for any other purpose, and you can unsubscribe at any time.

Contact The Business

Send a message to Linda Vivah:

Shortcuts

Share

Nearby engineering companies