David vonThenen

When token costs get expensive.... you gotta do, what you gotta do 🤣

LLMs don't run out of compute first… they run out of memory. 🤯🧠
KV cache, memory tiering, and shared storage are reshaping the economics of AI inference. I break down what's happening inside systems like vLLM + LMCache.

Read more: https://bit.ly/4bl87kn

#AIInference

People love AI demos… until production hits. 😅

On the Automate or Die Trying podcast, we break down the real challenges of enterprise AI: RAG accuracy, agent security, governance, and why "similarity" ≠ correctness in production.

Watch the episode: https://bit.ly/3PxRryI

Spent years chasing bigger models… turns out smarter engineering wins. 🚀
I joined the @_odsc AI X Podcast to talk about real-world production AI: RAG failures, quantization, SLMs, and building efficient systems that actually ship. 🎧

Listen here: https://bit.ly/4ssrdMm

#AI

@socallinuxexpo starts tomorrow!

I'll be presenting:
• A Practical Guide to Training a Small Language Model: https://bit.ly/3LkKjo0
• The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend: https://bit.ly/4rlTiEP

Sneak peek below 👇

Bigger models used to win headlines. Now they win power bills ⚡

On the @odsc.bsky.social blog, I break down how quantization and specialized SLMs are reshaping agentic AI around efficiency, not ego. It's about value per watt, not parameter count 🚀

Read here: https://bit.ly/4s6iKye

Excited to join @WDI_conference 2026 🎉 My VoD session, “Rethinking RAG: How MCP and Agent2Agent Will Transform the Future of Intelligent Search”, dives into governance, grounding & multi-agent design 🚀

Register: https://bit.ly/474WJrs
Code: WID26SP20 🎟️

#GenAI

1 week until @socallinuxexpo.bsky.social

Session: The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend
https://bit.ly/4rlTiEP

Session: A Practical Guide to Training a Small Language Model: Tokenizers, Training, and Real-World Pitfalls
https://bit.ly/3LkKjo0

Excited to share that my talk was accepted for @devoxx.fr. I'll be presenting "The Sound of Your Secrets: Teaching Your Model to Spy So You Can Learn to Defend," all about acoustic side-channel attacks and defenses.

More details: https://www.devoxx.fr/

NVIDIA's research backs it: Small Language Models > giant LLMs for agentic workflows 🔥 Focused SLMs = better control, lower cost, fewer "confident guesses."

Orchestrator-8B as a smart router? Game changer. I'll cover this at @odsc.bsky.social East! 🚀

More info: https://bit.ly/4aCsYPG

Recorded an episode of "Automate or Die Trying" Podcast with Wil Ramos! 🚀 We went deep on hardening RAG + agent workflows... grounded data, audit trails, guardrails, human-in-the-loop.

Teaser post on LinkedIn: https://bit.ly/4qQiyCo

Just listened to Lex Fridman w/OpenClaw's creator 🤯🤖 Self-modifying AI agents are here… and they're powerful.

But let's be real: security is a real concern 🔐⚠️ Privileged automation + access + personal info = serious risk.

I break it down here: https://bit.ly/4tTsmhJ 🚀

Excited to share that my talk was accepted for NDC Copenhagen! I'll be presenting The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend.

🗓️ Session Time/Date: Thurs, Jun 4 at 15:00
📍 Location: Room 4
📖 Session Link: https://bit.ly/4qvPWxT

Three weeks out and I can't wait to bring this one to @socallinuxexpo 23x in Pasadena, CA 🎧🔐

Check out my session: The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend

🗓️ Sat, March 7 @ 14:30
📍 Room 101
🔗 https://bit.ly/4rlTiEP

#SCaLE23x

Three weeks to go and I'm fired up to be speaking at @socallinuxexpo 23x in Pasadena 🎉🐧

Session: A Practical Guide to Training a Small Language Model: Tokenizers, Training, and Real-World Pitfalls

🗓️ Fri, Mar 6 @ 15:45
📍 Ballroom DE
🔗 https://bit.ly/3LkKjo0

#SCaLE23x

Happy Friday! Just obtained my latest certificate.

Just a reminder... if you deploy anything, deploy to a VM, cloud instance, etc in complete isolation.

🚨 Exposed DBs, leaked prompts, 91% injection success. Moltbook wasn't hacked by geniuses, it failed basic engineering 😬

Handing control and data to unproven AI agents isn't innovation, it's risk.

Read the full breakdown 👉 https://bit.ly/4qXmqlI

🔥 #AISecurity

Excited to share that my talk was accepted for @odsc.bsky.social East! I'll be presenting: "Less Compute, More Impact: How Model Quantization Fuels the Next Wave of Agentic AI."

Details here: https://odsc.ai/east/

The internet is biting back. Creators are deploying "tarpits" to trap AI scrapers in infinite mazes of gibberish data. This "data poisoning" spikes training costs and breaks the uncompensated data buffet. Be indigestible. Grow spikes.

Blog: https://bit.ly/4jvNTId

Teams are rethinking RAG 🔄🚀 BM25-based Hybrid RAG hits the sweet spot with clear observability, solid answer quality, and one OpenSearch stack to run 🤖✨ An alternative to Graph-based variations!

This is why it sticks... learn more 👉 https://bit.ly/4pz0D3b

AI isn't only optimizing search & ads, it's reshaping prices. 💸

This podcast exposes techflation: algorithms charging different people different prices to extract max value. Groceries cost more because AI knows what you'll tolerate. Dark precedent.

🎥 https://bit.ly/4jKdDkl

I'll be presenting at @devoxxgreece.bsky.social 🎉

Session 1: "The Sound of Your Secrets" will discuss acoustic side-channel attacks/defenses.

Session 2: "How Model Quantization Fuels the Next Wave of Agentic AI" will discuss efficient AI systems and models.

Info: https://devoxx.gr/

Pumped to share I'll be speaking at @DevoxxGR 🎉

I'm presenting 2 sessions:
1. The Sound of Your Secrets: Teaching A Model to Spy, So You Can Learn to Defend
2. Less Compute, More Impact: How Model Quantization Fuels the Next Wave of Agentic AI

👉 https://devoxx.gr/

I guess you can say I was pretty active with speaking sessions at conferences in 2025 🤣

🎉 Reading some eye-opening stuff over the break...

MIT just dropped a study showing AI can already replace 11.7% of U.S. jobs. Not hype. Real data. Worth a read if you care about work, skills, and what's next.

👉 https://bit.ly/3Y76fWg

New video is live! 🚀🔍 I break down how rethinking RAG with MCP + Agent2Agent unlocks more powerful, secure, agentic search. This is the same approach I shared at 3 conferences in late 2025.

Watch it now on the @Instaclustr YouTube! 🎥✨ https://bit.ly/3NiViPe

Hybrid RAG breaks the black box 🔍🚀 Combining Graphs or BM25, and vectors turns retrieval into something explainable, governable, and production-ready for real enterprise AI 🤖✨ Want agents you can trust?

Read the full breakdown here 👉 https://bit.ly/4pz0D3b

#HybridRAG

Got two talks accepted at SCaLE 23x! 🐧

1. A Practical Guide to Training a Small Language Model
2. The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend

One of the best conferences of the year! See you there!

Register: https://bit.ly/4aMlprJ 🚀

What did 2025 really change about AI, and what must 2026 fix to make it work in the real world? 🤖✨ Top builders and thinkers share bold predictions (including mine) on agents, context, and governance.

Read it here on the @_odsc blog 👉 https://bit.ly/3YdViSW

#AI #Governance