It's a bit scary to know they have conversation data from people even if their datasets are anonymized. They say they gather actual conversation data from "third party data sources". For obv reasons they won't cite where they got it from.
Rainy / cold days, busy families, and being able to access a greater variety of food in urban areas. These are scenarios with a high degree of pain that have not yet been solved by modern urban or surburban lives.
Watched your Youtube. I love this - will try it out and give it to our team. This is effectively the "full mode" version of the mode I currently use Cursor for.
Curious how this is going to affect Cursor - I'm assuming it'll just be a drop-in replacement and we can expect Cursor to get the same speed-up as VSCode.
Congrats on launching! Wish we had this years ago at Flexport for our ops / science teams. Traditional ML approaches are expensive, and the idea of defining your final shape of data and automating the ETL process is the best abstraction out there.
Curious - what do you guys use for the T step of your ELT? With nested blocks 12 layers deep, I can imagine it gets complicated to try to de-normalize using regular SQL.
Literally just had this idea 2 days ago - each TS agentic project feels like doing this stdlib work over and over again, but with a slightly differently architecture each time.
One question for our use case - what if a standard function requires bi-directional communication (as opposed to a single call to `generateText`)?
For one standard function, our envisioned interaction loop is:
Agent --> SSE to browser --> browser processes --> browser sends results back to server --> server sends to Agent --> Agent returns result
Used to use mint.com, have been looking for a decade for an alternative. But throwing in the AI-gen photos makes me rly distrustful of this type of service, esp one that requires you to link bank accounts.
Solve something you experienced as a college student. You're an expert in what it's like in 2024 to have gone thru such a crazy process. What would you have wished for?
Doesn't the movie example provide a counterpoint? Some human interactions do scale - townspeakers, specifically do on Twitter, on Instagram. 1-1 discussions don't.
Is the point more that social media is mixing various human interactions into the same bucket of "online discourse", and mixing the two (1-1's vs town halls) makes it "something perverse"? It's like accidentally handing your friend a mic during your walk back from the movies.
Thanks for summarizing! These points resonate with me bc I used to be an introvert, but found the extrovert inside of me a couple years ago (ironically, during pandemic).
A few additional points to make these macro data-based observations practical:
1. Saving your energy means ironically fewer convos.
2. A good proxy for "people who are most likely to be interesting" is the idea of reading their "energy". People whose energies are more similar to you are likely to resonate with you.
3. The article doesn't touch on follow-ups bc LinkedIn doesn't have that dataset. But follow-ups contain a wealth of information. For me currently they are the "breaking point" - most of my potential weak ties that could be strong ties remain at weak ties bc they descend into scheduling hell or lack of proactiveness (i usually follow up, and it's hard when i don't have time already as a founder).
4. This "sweet spot" is just in terms of LinkedIn mutual connections, which is weak bc LinkedIn connections are noisy. The real number is probably <10. Some say it's 6. I suspect it's actually 4 based on empirical evidence, where 3 of the 4 aren't captured on LinkedIn.
5. Try asking for their Instagram before LinkedIn next time. This might not be for the HackerNews crowd, but Instagram contains 2/4 or 3/4 of the missing signals that LinkedIn doesn't capture - what you do outside of work, where you are in your life journey / hero narrative, and what your life direction is.
6. Overcoming all your instincts in real world is tough. This takes a string of positive, warm, open interactions. Going to a few small, closed group events may help. Check out Saturday, Supermomos, or go to events at a private social club to "warm up" before going to larger tech events. Hopefully they cultivate a sense of "intimacy" in you, which is the energy you want to lead with from first interaction.
Hope this helps whoever bothered to read this from top down. If any of these points resonates, email me at [email protected]
Love your response to this :) came to the same conclusion. I do think friendships are getting "faster" and community "easier" to build - hopefully the next wave of friendships can be made faster & with fewer mental cycles.