Anthropic just dropped 5 workshops on building self-improving agentic systems from scratch:
@0xMovez50K followers
935,649 views
44 Comments
Comments from the original post on X (Twitter)

@MichaelWaitze
Love it. But here's what I realized: knowing how to use one model really well matters less than knowing which model to use for which problem. That's where the real value is.
10 likes

@0xMovez
Yeah, this is true. I mostly use Sonnet for coding, Opus for orchestrating, Fable for planning and goal setup.
10 likes

@MichaelWaitze
I think a lot of people are doing that. The model choices may be different for each task, but I do think most are splitting their loyalties.
1 like

@im_harish_hari
cool now watch everyone build the same todo app agent
4 likes

@0xMovez
It's not just about building agents, it's about agentic self-improving systems bro. That's what this series of workshops is about.

@0xRicker
2 hours of clean alpha, its will be nice evening
2 likes

@0xMovez
Yeah bro, one watch will replace 10 paid courses. Defo worth giving it some time.
3 likes

@0xCapx
Memory layers require scalable persistent storage infra.
2 likes

@gippp69
the memory segment at 36:44 caught my attention, that sounds super useful
2 likes

@0xMovez
Yeah, memory layer is the basis of every agentic system, that's for sure. Btw, have you built memory for your agents before?
1 like

@sayanchaudhury
Thanks for sharing this!
1 like

@itsthedonhashim
@0xMovez wow, this is gonna be a game changer for my side projects. especially pumped about the self-improving part. gotta dive into these workshops asap!
1 like

@undefinedKi
thanks for sharing and for timecodes
1 like

@0xMovez
You're welcome mate. Btw, what timecode caught your attention the most?
1 like

@undefinedKi
just started watching
1 like

@pawzzard
bro made a self-improving agent and it immediately optimized away the need for him 💀
1 like

@0xAthan
Ahh!! that's pure alpha
1 like

@0xMovez
Thx bro ! Happy its catched your feed
1 like

@0xAthan
Your posts are outstanding!

@memorilab
's new masterclass workshops are a blueprint for self-improving agents, but they highlight a massive hurdle: how do you share these memories across a multi-model ecosystem? If you deploy a fleet where Claude handles reasoning but passes tasks to specialized @GeminiApp or @OpenAI models, trapping user state in model specific, ephemeral wrappers is why production systems break. True cross model autonomy requires a model agnostic infrastructure that treats agent memory not as isolated vendor logs, but as a core, unified, queryable data layer. #AgenticAI #AIMemory #AIInfrastructure #AIAgents
1 like




















