Are you picking the right AI engine or just the popular one?
In this clip,
@goinggo.net breaks down vLLM vs Kronk 👇
youtu.be/baSi1Vv37hY
The shift:
There’s no “best” engine, only the right fit.
→ vLLM = scale (thousands of users)
→ Kronk = speed (single-user apps)
→ Edge AI with Arduino + TinyGo
If you’ve ever built something solid… & then got blocked by someone else’s abstraction, @goinggo.net knows the feeling.
Watch the Short 👇
youtube.com/shorts/95GtF...
⚠️Because handing off too much control? That’s how you end up debugging someone else’s problems.
No livestream today, but keep us on your radar.
Stay tuned for what’s coming next.
In the meantime, catch up on previous sessions here:
👉 www.youtube.com/watch?v=vzoa...
The LiteLLM incident wasn’t a model problem. It was a supply chain problem.
AI systems are not single services anymore. They’re stacks of dependencies, & every layer assumes trust by default.
That’s the real vulnerability.
📰Read the full article here: www.ardanlabs.com/news/2026/ai...
Your Go + LLM app is already an attack surface.
The breach won’t come from your infra.
It’ll come from how the models are used.
Florin Pățan breaks it down 👇
📅 April 29th | 12pm - 1pm EST
Register now👉 www.eventbrite.com/e/security-i...
#golang #LLMSecurity
Lost in the 147,000+ GGUF models on Hugging Face?
We spent the last few months building Kronk, a Go SDK & server for local AI inference
@goinggo.net breaks down how to help you find the right model for your hardware!
Stop guessing which model to download. Read now: www.kronkai.com/blog/navigat...
Our YouTube short of the week is here!💻
This week revolves around “AI Agents: Beyond the Hype” from @goinggo.net ’s podcast episode with featured guest Hartley Moy! 🤓
🎥: youtube.com/shorts/bBGh0...
#ArdanLabsPodcast #Shorts #YouTube #SoftwareEngineering
No livestream today, but don’t go far 👀
Catch up on previous sessions here:
👉 www.youtube.com/watch?v=vzoa...
You didn’t ship a vulnerability…
your dependencies did. 😮
Today’s stacks are built on layers of APIs, SDKs, and orchestration tools you don’t fully control. When something breaks upstream it doesn’t stay there, it reaches production.
AI security is no longer local. It’s a supply chain problem.
Ult. Software Design LIVE Schedule📅
Join @goinggo.net & @kenriquezcodes.bsky.social in this week's stream:
Tues. 4/14 & Thu. 4/16 from 11am-1pm EST
Stay tuned 1 hour before the LIVE show for the stream link!😎
📽️Rewatch the last 72 EPs here: www.youtube.com/live/9zNp69_...
Your LLM app just executed a command it wasn't supposed to. How did that happen?
Join us April 29th (12-1pm EST) to explore some design patterns to secure your Go - LLM apps against a range of attacks.
FREE webinar with Florin Pățan:
www.eventbrite.com/e/security-i...
#golang #LLMSecurity
Our YouTube short of the week is here!💻
This week revolves around “Keeping Systems Simple and Maintainable” from @goinggo.net ’s podcast episode with featured guest Ryan Ryke! 🤓
🎥: youtube.com/shorts/T2vjs...
#ArdanLabsPodcast #Shorts #YouTube #SoftwareEngineering
❌Stop assuming your AI model’s context will “just work”!
In this clip, @goinggo.net explains what happens when your context window hits its limit and how to find your model’s specific context length on Hugging Face.
🎥 Watch now: youtu.be/E3aUk3vZrSA
Go + LLM apps are growing fast. Security risks are growing faster.
Join us Apr. 29th (12–1pm EST) for a FREE Webinar:
Security in Go LLM-Based Apps led by Florin Pățan
👉 Sign up & save your spot: www.eventbrite.com/e/security-i...
📢 UPDATE: Ult. Software Design Stream Schedule
There will be NO livestream tomorrow with @goinggo.net & @kenriquezcodes.bsky.social
In the meantime, you can catch up on previous episodes here
👉 www.youtube.com/watch?v=vzoa...
We’ll share updates as soon as the next streams are scheduled.
The question isn’t: “Can we add AI?”
It’s: How much infrastructure do we need to support it?
More layers ≠ Better systems
Less infrastructure. More control.
Read the full article to learn more about Kronk AI: www.ardanlabs.com/news/2026/kr...
🚨The fastest way to kill momentum? Pivoting too soon.
If you’ve ever started seeing progress & then second-guessed everything because of the competition… @goinggo.net can relate!
Watch the Short 👇
youtube.com/shorts/8CaNO...
It always starts simple.
One prompt.
One model.
Everything works..
Then comes the “just one more thing” phase, model servers, vector DBs, orchestration ...
Before long, you’re managing infrastructure, not improving AI.
Are we overbuilding by default? www.kronkai.com
Gophers, 1-hour countdown for stream #72! 😎
Join @goinggo.net & @kenriquezcodes.bsky.social as they go live at 11 am EST!
📽️ Today's stream link: youtube.com/live/GoT-FUz...
#golang #Livestream #SoftwareDesign
🚀 Tebeka Shorts #54!
In this episode, @tebeka.bsky.social shows a cleaner, more maintainable way to work with regular expressions in #golang, by naming your capture groups instead of relying on positions.
📺Watch now to simplify how you extract data from complex strings:
youtu.be/GOXpxIvfUCE
We are back!
Ult. Software Design LIVE Schedule📅
Join @goinggo.net & @kenriquezcodes.bsky.social in this week's stream:
Tues. 4/7 & Thu. 4/9 from 11am-1pm EST
Stay tuned 1 hour before the LIVE show for the stream link!😎
📽️Rewatch the last 71 EPs here: www.youtube.com/live/9zNp69_...
Stop obsessing over Tokens Per Second (TPS) for your local AI models!❌
TPS is often a false metric; a high TPS might just mean your model is "spinning its wheels faster" if your tooling is inefficient.
In this clip, @goinggo.net explains what actually matters.
🎥Watch now: youtu.be/aJiw2oFXOBc
Most teams don’t fail from lack of talent. They fail from choosing the wrong model.
Staff Aug ≠ Outsourcing ≠ Hiring
Each solves a different problem.
Use the wrong one → friction, delays, misalignment
If you're deciding, it’s worth getting it right.
Read more → www.ardanlabs.com/news/2026/st...
Waiting for the next model drop like it’s the “holy grail”…
only to spend hours trying to make it work on your setup… @goinggo.net can relate!
Sometimes you just wish the AI world would pause for a day so you can actually get some work done. 😂
Watch the Short 👇
youtube.com/shorts/vNSud...
Our YouTube short of the week is here!💻
This week revolves around “Making Mistakes and Fixing Them” from @goinggo.net podcast episode with featured guest Ryan Henrich! 🤓
🎥: youtube.com/shorts/VxyHS...
#ArdanLabsPodcast #Shorts #YouTube #SoftwareEngineering
Scaling does not fail in execution. It fails in the decision
Hiring. Outsourcing. Staff augmentation
All work, just not in the same conditions
That is where teams get stuck
We help teams make the right scaling decision and execute it with confidence. Get started: www.ardanlabs.com/staff-augmen...
Two workshops at GopherCon UK 🚀
📍 London
📅 August 11th
With:
@goinggo.net — AI in Go
Florin Pățan — Production Go systems
Limited seats. Secure your tickets now!
👉 www.gophercon.co.uk/workshops
Our YouTube short of the week is here!💻
This week revolves around “Overcoming Shyness with Confidence” from @goinggo.net podcast episode with featured guest Kacie Bail! 🤓
🎥: youtube.com/shorts/rOxDv...
#ArdanLabsPodcast #Shorts #YouTube #SoftwareEngineering
Most staff augmentation fails because it stops at placement.
That’s the mistake
At Ardan Labs, we don’t just place engineers.
We prepare them, integrate them, & support them throughout the engagement. That’s how you get consistent outcomes
We broke it down here👉 www.ardanlabs.com/news/2026/ho...
Most AI systems treat the model as a black box.
But what if you could see what’s happening under the hood? 👀
In this clip from @goinggo.net ’s Ultimate AI Workshop, hear from Bill how Kronk AI integrates with Llama CPP & the mental model behind modern AI systems.
🎥 : youtu.be/hph2iQuOKwU