Hacker News
X / Twitter
Create a tiny script that can do most of what chrome-devtools mcp can, based on @badlogicgames 's blog post, added to my collection: https://t.co/XAN8htljcN
Getting protein into young children
Pro tip for Cursor/Claude Code:
In a PostToolUse hook, add the tool call to your bash history (I prefer atuin).
Now your terminal has a nice, searchable history of everything your AI has actually done.
Interesting read on @AmpCode does context engineering to optimize the Coding Agent.
- Embeds file content via @-mentions, limited to 500 lines.
- Shell Mode captures command output and exit status code.
- Handoff feature extracts relevant data for new, focused threads.
- Uses read_thread tool to pull context from other conversations.
https://t.co/Roh73zwXIS
People often ask me how to get good at Twitter
I start by pointing them back to this old essay by my friend @danshipper, "Selling Umbrellas in a Synagogue"
The css on his old site seems broken, so I'll repost the relevant part of it here:
The way people interact with Twitter is fundamentally different from the way people interact with Google. And so measuring things like CTR and conversion rate on Twitter is completely missing the point.
Let me give you an example.
If you’re ever in New York and it begins to rain, a stunning and incredible ritual occurs. As soon as the clouds begin to form, a bunch of guys suddenly materialize toting umbrellas. They walk around the whole time it’s raining selling them for 5 bucks a pop.
I’ve been in at least a few rainstorms and have thought to myself “hey, what the hell?” and just bought one. After the rain goes away, the vendors just disappear into thin air.
The guys selling the umbrellas are filling an expressed need. When it’s raining out and people are walking around and getting wet, they need umbrellas. The vendors conveniently swoop in because they see that need and fill it.
The same thing happens on Google: people are already searching for things that they want. They’re like people getting wet in a rainstorm. They’ve expressed need, and they have the oft-quoted “purchase intent”. So putting an ad next to search results makes perfect sense. The ad is just like the guy hawking umbrellas.
But Twitter is not like Google. And selling things on Twitter is not like selling things on Google. Twitter is not like a rainy Manhattan avenue.
Twitter is like a synagogue.
Every Saturday at a synagogue a bunch of people get together. The relationship is social, and it’s communal. They go to synagogue for the services and then the schmoozing afterward.
Twitter is similar. Their tagline is, “Find out what’s happening, right now, with the people and organizations you care about.” Twitter is social. Twitter is communal.
And so, selling things on Twitter is like taking our Manhattan umbrella vendor, and having him go try to sell umbrellas in synagogue.
Imagine the scene. A bunch of hungry people are eating bagels and lox after services and chatting amongst themselves. Suddenly some guy comes up toting a bunch of umbrellas.
“Hey I know you’re busy talking with your friends but can I interest you in an umbrella? It only costs $5. It’s a great deal!”
I shiver even thinking of having to do something like that. It’s grotesque. And most importantly, it’s very unlikely to work.
What’s interesting to note is that the people that the vendor is talking to are the same people that minutes earlier may have bought an umbrella from him on the street on their way to temple. But now that the context is shifted, it completely changes the way the sales pitch is perceived.
In advertising, context is everything. And an umbrella vendor in a synagogue misses that entirely. As Gary Vaynerchuk might say, he’s like a teenage boy with his first girlfriend. He’s trying to close too fast!
So how you sell umbrellas in a synagogue?
Well, let’s say you’re Moses Goldstein of Goldstein Umbrellas. You go to services every Saturday. And then you go eat with the community. You share advice, and expertise. You trade stories with people in other industries.
It may seem like you’re just idly wasting your time. If you go and measure the ROI of what you’re doing it will stand at zero. It looks like it’s a very bad idea for you to pay your yearly dues at the synagogue.
But what you’re really doing is a primitive non-scalable version of content marketing. With every person you talk to, and every story you swap you’re establishing yourself as a trustworthy, reliable and well-liked authority on umbrellas.
Still, you won’t see any ROI.
Then one day a member of congregation comes up to you and says, “Hey Moses, my company is looking for an umbrella vendor. Of course the first person I thought of is you!”
And you suddenly have a new customer.
What this says to me is that there are a lot of companies that are going to get on to Twitter’s advertising platform, throw a few thousands dollars at it, see a low conversion rate and conclude “This sucks!” These are the guys that are selling umbrellas in a synagogue.
But as people understand the social web more they’ll begin to realize that on social sites the advertising context is shifted in much the same as the context is shifted between the street and the synagogue. In the street, the relationship is all about immediate need. You have a need, I’m the most convenient way to fill it.
By contrast, in a synagogue, the relationship is all about connection. It’s about developing and cultivating bonds between people in a genuine fashion. And then once those bonds have been formed, they’ll be utilized when need arises i.e. when someone is looking for an umbrella vendor. The arc on the relationship is many times longer than the arc on the relationship with a street vendor. The upshot of it is that Twitter allows you to build those relationships in a scalable way.
So am I going to continue using Promoted Tweets? Nah, but I do have a startup called Firefly. If you’re interested in doing better customer support I’d love to talk to you about it some time.
Gave this little list its own URL:
https://t.co/agvahJN0Si https://t.co/GguoJ6WrWE