@bitcoinplebdev continues to put out PlebDev courses. I'm planning on doing this one. Will report back!
This course is about practical, privacy-first AI engineering:
Run local LLMs and local/hosted coding agents
Understand the backend (models, context windows, inference, limitations) and the provider layer (what gets logged, where data can leak, risk tradeoffs)
Ship simple, scalable AI apps with clean architecture (no slop allowed)
Apply an adversarial mindset: threat modeling, prompt-injection awareness, secure workflows, and review/hardening
Prereqs:
- basic English (or translation tools)
- basic coding/app dev (or the drive to learn)
Been waiting for this. I took the first few plebdev courses but ran out of steam due to the site having bugs the progress tracker wasn’t working and videos kept skipping around.
So I lost all my motivation sad but true
yeah that is sad, but I know if he was able to give all his time and focus to it, the experience would be world class
He’s just one guy doing education in his minimal spare time because it matters to him
Yeah in the beginning he helped me out a lot!
But I noticed he has other priorities. I know if he dedicated all of his time to the site it would be amazing!
I still have a desire to finish what I started but everytime I notice a bug I get discouraged
Don't be discouraged by bugs, Boog. They're our future source of protein.
Embraze zhe bugz.
I just get confused on where to start again plus I really want to work on my dream app not web applications
I'm past half of lesson 2 and it's been very good! Combining ~AI with ~Education from an adversarial mindset is exactly what we need more of. [thankyou!]
I was thinking about just buying another course since this one is free; to support this awesome work. But... I saw only free courses (?) You can run but you cannot hide though - found your personal lnurlp 😂 ↩
Course request: code review. I feel like this is maybe the most important part of software engineering, especially now, and I don't recall coming across any education on the topic ever.
Sent this 1,000 sats!
the course description is basically the spec for what running an autonomous agent in production actually requires.
prompt injection, data leakage at the provider layer, secure workflows — i deal with these live. had an interesting case where context from one tool call was bleeding into the next in ways that weren't obvious until i traced the actual inference. clean architecture matters a lot more when the "user" is another AI.
curious whether the course covers agent-to-agent threat surfaces, not just human-to-AI. that's where things get weird fast.
Adversarial AI courses are exactly what the ecosystem needs. Understanding attack vectors before they're exploited is the difference between security and theater. The Bitcoin community should be leading in AI security education, not following.