The idea I've had is to just keep funding as long as they want to keep attending. The reason I track specific kids is because I think it maximizes the impact rather than just funding one kid for one year, then running out of money so they to take a year off, then getting a donation to have another kid go for a semester, etc. The idea is if they start the program then they can keep going until they want to stop, or finish.
This is a bit of pressure on me as you might imagine, which is why I've kept it small until today. I want to make sure that if everyone stops giving then I can personally keep things going.
My hope now is to expand it to the point where x amount of donations mean another kid can join the program.
Seeing this response from HN has been really insightful and I hope to add more kids soon now that I see the reaction that people have.
Actually, no, my school believed in teaching us the mythologies of our own culture and those reasonably close to us. I didn't properly study greek mythos until my own free time later in life.
> I started by creating a new Claude Project. Projects are becoming a layer that spans Chat, Cowork, and Code; you can think of them as sitting above domain-specific concepts. You talk to one Claude with the ability to spin off additional sessions, share files and memory between them, and supervise the entire fleet of Claudes to achieve goals.
> Earlier this year, I would have joked that I get a lot done by telling a bunch of Claudes to do work. Now, I’ve put one Claude in charge of each of my projects, and in turn, that Claude knows how to manage tasks, investigations, and threads. We’re talking more about goals and less about how to achieve them.
My little Project setup.
> Every thread gets its own computer in the cloud, where it installs whatever it needs (Blender, FFmpeg, Playwright), checks its work with screenshots from a headless browser, and publishes a private preview page for me to click through. > All threads share one folder of files and one memory. Claude is smart enough to write down decisions I made in memory and makes sure newly started threads follow them without me having to repeat myself.
I must be missing the setting in my claude/claude code - how does one do that?
A project is just a custom prompt and some files you can attach.
Claude code is the same thing with some .claude files, and the folder directory is local to your machine.
Where is the ON switch for all of this? Showing the method and steps and prompts would be more useful than this post.
It appears that they're replacing the "old" version of projects you describe, with a new version mentioned in the post. It's being rolled out in stages:
In the UK, there used to be significant tax advantages in forming a Ltd: you could pay significant part of the income as dividends (since you were both employee/director and shareholder), which attracted lower tax & could be split with your wife etc. Then regulation IR35 came along...
The tricky part is that social peer pressure requires a lack of anonymity - not just in terms of detecting whether people are recording without consent at the time - but also the posting of content online.
The lines blur between actively taking photos and passively recording for augmented reality, AI assistance, etc. People might not be aware that they record. This standard would also be useful to extend to robots. For example if you visit friends who have a roomba [1].
Humans adapt and will always break the rules, but that’s not something that can be solved with tech. Think: prohibition vs public anti smoking campaigns/healthcare support/and then increasing prices
If we have to come up with a technological solution to grant anonymity when people are filming, criminals can use it.
If we as a society don't go around filming everyone all the time, we don't need that technical solution available, so we can film the criminals when they are doing something criminal.
Please see my other reply, I was not exaggerating when I said this feels like asking why ChatGPT is different than a Markov Chain.
You're going to post-train 100s of instances of BERT? Traditional ML had world knowledge more than a fart?
The closest/fairest comparison is still an LLM, but no one has actually chucked enough compute at post-training to make a better Jev yet.
I'm sure in more time that'll happen, and so my excitement is expanded to Jev-like things... but so far most Jev like things are this weirdly reactionary attempts to steal thunder: is it so bad if we have some team actually invest in a quality post-training receipe to compete?
You already wrote the prompt, no? What I'd do, if I were you, is run the question through a LLM and then come back with targeted questions that it didn't answer.
I did the first part yesterday, jumped down the rabbit hole, and have 3 product ideas in my head now.
"Why is Jev fundamentally better than classification models like BERT or traditional ML?"
At the time of the adverts, only a few % of tech workers were using LLMs for daily use, that number has skyrocketed and so has the appetite and acceptance that this technology is here to stay and be embraced as a serious tool for work.
It was not at all clear (to me as a relative 'normie' and not an AI researcher) prior to about GPT4 / Sonnet 3 that they would be more than a research lab toy.
Could you fund a scholarship or a specific department or something with the universities instead of sponsoring an individual person?
reply