THE GUY WHO BUILT GITHUB JUST WALKED AWAY FROM A $7.5 BILLION MICROSOFT ACQUISITION TO REBUILD GIT FROM SCRATCH
A 42-min keynote from Scott Chacon himself - the co-founder who wrote the book every Git tutorial on the internet quietly steals from.
-> The moment you watch it, you realize why GitHub has been hiding the actual complexity of Git from you for the last decade.
He spent 10 years selling Git to developers through GitHub. Now he's saying the GUI was the lie. The tool only works if you understand what's actually happening underneath.
GitHub isn't Git -> it's a UI layer covering for the fact that 90% of developers never learned the engine.
If the man who co-founded the platform left it to build a better one, that should tell you what he thinks of your current Git skills.
Don't forget to bookmark & watch it today.
Okay.. @akshay_pachaar’s Hermes article was already top-tier, but his new 47-minute walkthrough is INSANE 🤯
Skip Netflix, grab a coffee, and watch this masterclass on how to build self-improving, 24/7 autonomous agents locally on your machine 👀↓
Hermes agent masterclass.
In this video, I cover everything you need to understand and customize Hermes Agent. Self-evolving skills, three-tier memory, GEPA optimization, and going from 1 to 10 agents that work for you 24/7.
Enjoy!
Chapters:
00:00 - Intro
02:03 - How to get the most out of this video
02:32 - What we're building (and why it's wild)
07:11 - How the whole thing works under the hood
09:27 - The SOUL.md: your agent's personality file
11:15 - The 3-tier memory system that keeps it all together
14:16 - Skills: what your agent can actually do
16:49 - The self-evolving loop (agents that improve themselves)
19:58 - The curator: Hermes' built-in garbage collector
22:56 - GEPA optimization: making your agent sharper
25:08 - Installation and setup
27:38 - Connecting your agent to Telegram
30:36 - Configuring programmer with Claude Code
31:53 - Adding new skills (from a hub of ready-made skills)
34:59 - Going from 1 to 10 agent profiles
36:49 - Building a custom designer from scratch
40:42 - Anatomy of the .hermes folder (where everything lives)
45:05 - Skill taps: sharing skills via a GitHub repo
45:59 - Skill bundles: stacking skills for workflows
47:19 - Hermes Kanban (coming soon)
48:05 Outro
Cheers! :)
instead of watching 2 hours of Netflix tonight, watch this Stanford lecture
it's the clearest explanation I've seen of how ChatGPT and Claude actually work
useful whether you've never touched AI in your life or have been using it every day for the past year
I took the key ideas and turned them into a practical guide on how to actually get 100% out of Claude
find it below
BREAKING: We just gave Claude access to the entire options and stock market.
It's the Unusual Whales MCP Server. It plugs directly into any AI assistant and gives it live, structured data on demand.
Build a trading bot. Build a finance dashboard. Build whatever you want.
FWIW, so far @grok has been doing way better job on graphics for me than the others (google's, claude's, etc) For banners/flyers/text heavy cards for example. But the downside is that the UX sucks ass. If they nail the Ui/UX it'll be a winner.
@grok@rkcpa192@rejectklaus@ConorLawrence When is this happening and where can I find more info about this?
I'd like to integrate this into my payment systems in the wild now or ASAP. I presume we'll be able to use it like we use other payment processors, etc.
Make me an amazing banner for my twitter page. -- my username is @notagrouch on instagram as well, my name across the web is the same.
Can you autonomously do some recon on me, and then generate a banner based on what you think would be the best portrayal of me, "my brand" if such a thing exists, my interests, my "me" basically in a modern design that showcases clean, uncluttered, contemporary, yet timeless design elements.
And please no "AI Slop" -- I presume I don't need to tell you the parameters on dimensions and resolution and stuff, given that it's "your" platform. Correct? Feel free to ask for anything that would clarify my reqeust.
You need to run uncensored AI Models, trust me.
With GEMMA 4 26B UNCENSORED, you can ask your AI Model literally anything.
Watch this 22 min video to set this up yourself:
Google Cloud AI engineer just showed how they go from idea to deployed app at Google in 30-minutes using Claude.
26-minutes. free. by Google AI team.
one person + Claude + Google Cloud = a full engineering org running on a laptop.
worth more than any $500 vibe-coding course.