@waveofdavee He was great for Barcelona and won a title with them. Don’t get this weird rashford hate the reason Man U are struggling is their midfield mainly.
I still don't understand why everyone is not using this yet. Thanks to it, a year ago I increased my income to 17,000 dollars a month
Andrey Karpathy, co-founder of OpenAI, published a simple idea that got 16 million views: stop using AI to write code, use it to build a second brain
You point Claude Code to a folder, drop any source in there (an article, transcript, PDF) and Claude reads it, links it, and saves it into a living wiki of everything you know. It compounds like interest: the more you feed it, the smarter it gets
Here is the gist:
Install Obsidian, create a vault, open it in Claude Code
Paste the file with Karpathy's wiki idea and tell Claude to build it
Claude creates three folders: raw for sources, wiki for its pages, CLAUDE
which runs everything
Drop any source into raw and say "ingest this"
Ask questions across everything, forever
Five minutes to set up, and you never start with an empty chat again
The full step-by-step guide is in the article. Save to bookmarks
GRAPH ENGINEERING FULL COURSE — 2 HOURS
This is the most detailed Graph Engineering guide I've seen online.
Bookmark this video so you don't lose it
> build your first agent from scratch
> why single-agent loops fall apart
> turn those loops into a graph
> architect a multi-agent system on top
> the full build, start to finish
Agent → Loops → Graphs → Multi-Agent Systems → Money
then read how I ran it all on Kimi K3 below ↓
😰Two Anthropic engineers just spent 24 minutes showing Claude features most daily users have never opened once...
and the uncomfortable part is not how impressive the features are.
It is realizing how long you have been doing manually what those features were built to handle automatically.
My article covers the 25 hidden Claude features most people miss even after they know to look and it covers the ones the engineers did not show. Full guide below.
They built a billion dollar business on 10 AI agents in one week - and came to Stanford to share how:
00:22 - how the first agent launches the entire business automatically
28:34 - how to reach $100k from scratch with 10 agents
39:47 - they shared million dollar ideas that can be built in 24 hours
after watching I took one of their million dollar ideas - the next day the agent was already building the business and in the first month 400+ clients.
Save & watch - the article below shows how to take their million dollar idea and launch a business in 24 hours.
call me crazy but the first AI agent most companies should build is an autonomous analyst.
you can build one using Kimi K3.
it watches your competitors while you sleep, remembers every move, and wakes your team with the launches, pricing changes, and positioning shifts they need to act on.
don't bookmark this if it crosses your timeline.
paste the full article into Kimi and tell it to build the first version for your market.
if i were you... i'd spend a day or two building a simple Hermes setup right now
this is probably the highest leverage play you can make with AI agents
i don't think any other project is as impactful for your work
in just a few days they shipped "bot mode", which is basically an UI improvement for ppl who loved Grok Bot
now we have 900k context using GPT models (what works best with Hermes for me)
every single week your agent is improving via updates only, this is awesome
A Chinese developer just explained the shift from Loop Engineering to Graph Engineering better than anyone.
most people are still building agents the way that's about to be obsolete.
> why single-agent loops break and go "goal blind"
> the 4 parts of a graph: nodes, edges, state, policy
> 3 topologies that run everything: diamond, supervisor, pipeline
> Anthropic's 5 official workflow patterns
the punchline: it's not how many agents you run. it's the determinism you build with verifiers, code fallbacks, and reality anchors.
I broke the same architecture down with Kimi K3. Full A-Z guide below.
i met a woman at the airport yesterday
she runs a consulting business doing $8k a month
smart, polished and clearly knows her stuff
we got talking and she told me she'd been on 6 sales calls that week
closed zero of them
i asked her how she was closing clients
she pulled out her phone and showed me her calendly link
i told her that was the problem
here's the exact system i walked her through at gate 14 before her flight boarded:
the sales call is not closing your deals. it's killing them
think about what actually happens on most calls
you get on nervous. they're already skeptical. 45 minutes later they say "let me think about it" and disappear
they didn't decide after the call
they decided during it
the moment the price landed before the trust did, the deal was gone
she looked at me and said "that's exactly what keeps happening"
here's what i told her to do instead:
step 1: stop sending calendly links. start sending a google doc
one document that does the following:
- opens with their exact problem in their own words
- shows them what that problem is costing them per month in real numbers
- presents your mechanism as the only logical bridge between where they are and where they want to be
- includes a result from someone who looked exactly like them 90 days ago
- lays out the investment and what happens the moment they say yes
that doc is now your sales call
it doesn't get nervous
it doesn't ramble
it says the same thing perfectly every single time
i closed a $2,000,000 startup off the back of one of these with no call required
step 2: stop trying to build an audience. steal one
she told me she'd been posting on linkedin for 8 months
i asked how many clients it had brought in
she laughed
here's the thing nobody tells you
there are people in your space who already spent 3-4 years building an audience full of your exact buyers
coaches. consultants. agency owners. B2B founders
warm. engaged. already aware the problem exists
and not one of your competitors is contacting those followers directly
find 2-3 accounts in your niche whose audience overlaps with your ideal client
reach out to their followers with something like this:
"noticed you follow [account]. we just helped [similar client] get [result] in [timeframe]. want to see how?"
you're not cold. you're already in the same world
it lands completely differently
i do this with under 3,000 followers across all platforms and close companies doing millions
step 3: stop leading with the big retainer
she told me she'd been opening with a $5k/month package
i told her that was like proposing on the first date
a $5k retainer cold creates more hesitation than it's worth
too much money. too much risk. too much to think about before you've proven anything
lead with something stupidly easy to say yes to
$250 to $2,000 to start. clear deliverable. fast win. small upfront
get them in. get them a result. let the $6k conversation happen naturally once the trust is already there
3 out of every 10 people who pay me $300 to start wire $7,000+ within 45 days
the low friction offer doesn't just close more deals
it builds a pipeline of warm buyers 30-45 days away from a much bigger check
by the time her gate opened she had three things to do when she landed:
one: write the google doc
two: find two competitor accounts and start contacting their followers
three: build a low friction offer to lead with
she said "i've spent 8 months doing this completely wrong"
i told her most people do
the ones who figure this out early are the ones doing $40k, $60k, $100k months without a single sales call on the calendar
the ones who don't are still sending calendly links to people who ghost them
you now have the whole system
if you want me to help you build this inside your business - the doc, the siphon system, the offer... dm me "airport" and i'll walk you through exactly how we'd install it
@5thOfSanogo@Rory_Talks_Ball He proved he could play In the middle as he helped us win the prem buddy. Being asked to be a sole dm without help from the rest of the midfield is always a tough ask. Zubi, Rice, Bruno would also struggle.