pranavm27
pranavm27 on Hacker News
That's exactly what Sidney Farber did in Boston Children's Hospital btw in late 1940. One of his tests fast forwarded cancer.
I think its practical to solve cancer on a war footing where we would expect people to die.
And Farber's methods were pretty fast for his time - lol Farber would be a perfect name for this AI that wants to solve cancer knowing what's at risk.
From my last month's clauding experience, these agents now understand what needs to remain sequential and just wait for the other agents to get done.
Hey HN, built Pitch Like This so I could generate personalized pitches for job applications.
The platform allows you to add all your career experiences once and then reuse them for every pitch you generate. The shared pitches are then tracked for engagement.
The platform is free to use. I would like to know if such a product would be useful for you folks. I was planning to add more AI optimizations like compare JD to Resume and suggest experiences.
Longterm I see this product as a single place that knows every bit of your career on granular levels and helps you get opportunities without making job search a full time task as it is today.
Posted by
pranavm27 on Tuesday June 16, 2026 @06:18AM
from the show-hn dept.
And this is HN, its acting as its meant to xD
I had this idea in the beginning of last year and since I wanted to somehow get into space infra started doing some calculations - the area of arrays required kinda made me scrap the whole thing. But kinda curious since this is back as a mainstream topic.
ain't got energy left to go into another AI rabbit hole haha
Whenever I play Uno - the rules always change based on the group I am playing with. This is a layer higher saying that card creation and in game rule change.
I wonder if someone has already created an app to assist card creations and make it easy to onboard people onto the game.
Made a decision on not to upgrade midway installation. Feels like it payed off. And I am on M2 256 GBs so it would have been worst for me.
There is one part of the world where nothing movies without rules. And then there's another where rules are joke and everyone optimises for personal efficiency.
What should be the sweet spot?
Posted by
pranavm27 on Monday December 29, 2025 @10:53AM
from the garden.pranavmandhare.com dept.
Its good that way right? Let me as a human do the interesting thinking for which my brains are meant while you AI do what they chips were built for.
I am happy as is tbh, not even looking for AGI and all. Just that the LLM be close enough to my thinking scale so that it does not feel "why am I talking with this robot".
I feel ya but it didn't get me on this one for some reason. But it gets me a lot on Linkedin - due to which I lost control and blasted off a post yesterday.
I think it some kind of value - vibe dynamics that play in making the brain conscious about it being written with AI or otherwise.
Reminds me of Ken Miles saying 7000 rpm quote. At what size do you think this happens? Whatever is the most relevant metric of size for this context.
Love it, only issue on my mobile is the scroll surface overlaps. I would want that shelf to be perfect fitting on my screen before I start scrolling.
Vibe coded a library last month for my website however its much simpler and has Antilibrary section for all the stuff I have not read.
I rabbitholed into that another essay of buying domain names. The author juggles ideas by domain name. I have one called Banadana Girl .in and I was like sell bandanas lol - gotta check now the TAM for bandanas in india with women as TM. Give me ideas folks. Do you know of a bandana expert?
Miss anna, next time please scale down image dimensions so that us on mobile can read properly haha
Jokes aside, I always thought the best way to deal with piracy was to understand or convince the demand not to do it over dealing with the supply.
Posted by
pranavm27 on Monday December 22, 2025 @05:09PM
from the garden.pranavmandhare.com dept.
Isn't Supabase anon key actually a publishable one? What's voila about finding it. RLS disabled is a more of a voila here.
I think for cities with more than 5mil population, the best way to avoid road accident would be to restrict human driving in cities and allow only autopilots.
Might be more impactful and faster than infra. Though infra has to improve as well atleast on major roads.
From my perspective, the moat in such cases would be how many users impressed (based on accuracy, specific pain point) and how fast were they impressed.
Part of "how fast" equation is the UX - build with zero friction - every second they gonna churn unless impressed.
Do you think this will work as effectively with Google or Social Media review and rating datasets? As every country may not have a LeFooding.com
Would like to here everyone's thoughts