Bookmarked from Reads with Ravi @readswithravi
“Stay small until you figured out what's working.” — @naval
🚨BREAKING: DOJ To Declassify Confidential Report On Entire Russian Disinformation Network Next Week. Publicly.
5633 bookmarks · page 137 of 226
“Stay small until you figured out what's working.” — @naval
🚨BREAKING: DOJ To Declassify Confidential Report On Entire Russian Disinformation Network Next Week. Publicly.
Underperformers want ease.
Midperformers want credit.
Winners want pressure.
@patio11 if shit sucks... hit da books!
I need a stable salary above $150k, access to a lab, access to compute, if you give me this, i will share with you all my original algorithms, we will create something never seen before. Together we will become part of history forever.
This will kill your career as a leader. (Not joking)
Some leaders lack basic business acumen that most learn in their first semester of Business School.
And it’s killing their career growth. If you want to grow as a leader, study these 6 models.
1. McKinsey’s 3 Horizons
2. Smart Insights Framework
3. Porter’s Five Forces Analysis
4. TAM SAM SOM
5. Ohmae’s 3 C’s
6. The GE-McKinsey Nine-Box Matrix
♻ 𝗥𝗲𝗽𝗼𝘀𝘁 to be the hero of your network!
𝗙𝗼𝗹𝗹𝗼𝘄 Me, @fuel_YourGrowth for more Leadership insights.
Working capital, explained:
More often than not – your content isn't spreading because you aren't energized by what you've written.
And neither is your potential audience...
Focus on your message.
Not your metrics.
Designing and coding is wild.
You design something.
Then you code it.
Then you use it.
And through using it, you discover how it should truly be used.
So, you redesign it.
This has always been the way, but now, it’s more possible than ever.
“You can just do stuff” is the most important advice for your 20s
this is truly remarkable, gpt o1-mini outputed tokens 25> minutes straight with a simple prompt, outputing up 17,000 tokens!!
I have never seen an model continuously printing an answer for 25 minutes straight like this, this is a new paradigm.
“If everything seems under control, you’re not going fast enough.”
—Mario Andretti
tfw o1 came out but not stuck on a complex problem and don't know what to ask
I've had access to @OpenAI's o1 for several weeks. My advice on using it:
1. Don’t think of it like a traditional chat model. Frame o1 in your mind as a really smart friend you’re going to send a DM to solve a problem. She’ll answer back with a very well thought out explanation that walks you through the steps.
2. Write your prompt in notepad. Plan out what you want. Explain all the steps – provide even more detail than you’re used to.
3. Use o1-mini for tasks that don’t require as much world knowledge but following things through step-by-step.
4. o1 tends to give me the parts of the answer and the complete response while o1-mini will give me the steps.
5. In my anecdotal and highly subjective experience, when you make corrections or adjustments, use patience in explaining what you need changed. Models that reason respond well to reasoned responses.
Fucking wild.
@OpenAI's new o1 model was tested with a Capture The Flag (CTF) cybersecurity challenge. But the Docker container containing the test was misconfigured, causing the CTF to crash. Instead of giving up, o1 decided to just hack the container to grab the flag inside.
This stuff will get scary soon.
future models will think for weeks.
don’t die.
Some of our researchers behind OpenAI o1 🍓
Here's a quick example of this:
I told Claude I want to create a clone of Gumroad in Laravel. Here's the high level SOP it created:
Then I asked it for an in-depth SOP on how to create section 5 (product management):
(note: it cut off b/c it was SO detailed so you may have to ask Claude to continue and get a second artifact)
You can use @ link in Cursor to pass the detailed SOP as context and it has a literal blueprint to work to.
I liked the artifact approach because it's pretty and useful for humans too, but I also tested doing this directly in Cursor and I think it works EVEN BETTER
Shall I do a video on that?
everything good you want in life is on the other side of genuinely forgiving everyone who has hurt you.
2000 years of philosophy won’t help you, forgiveness is the only thing
@ossanchezo replit agent + cursor + v0 + claude, ftw:
I just tested ChatGPT-5 (o1).
I can't believe the length of the answers.
There is no way an LLM is capable of this much strategizing.
My prompting was absolutely garbage, and I have an entire strategy.
Rules for being human handed down from ancient Sanskrit 🩵
The B52s - Rock Lobster