sahilagarwal

Not really different. They would need to report CSAM if it is ever uploaded by a user.

Any website that allows user to upload videos needs some sort of service that can identify and report CSAM.

I generally don't have as much time (or patience / fucks) anymore in my day. So, I use AI 3 days a week. On the other two days, I don't use assistants to code, just ask them to review my work after its done.

Helps me keep sane tbh. And keeps the edge sharp.

Better management?? Easier processing for residential solar panels? How about government subsidies on solar panels for lower income homes?

Hell, maybe create a unified portal when companies buy energy - show the cost difference side by side.

I like to write them on my own in every company Im in using bash. So I have a local set of bash commands to help me figure out logs and colorize the items I want to.

Takes some time and its a pain in the ass initially, but once I've matured them - work becomes so much more easy. Reduces dependability on other people / teams / access as well.

Edit: Thinking about this, they wont work in other use cases. Im a data engineer so my jobs are mostly sequential.

Hi Boris,

If you wouldn't mind answering a question for me, it's one of the main things that has made me not add claude in vscode.

I have a custom 'code style' system prompt that I want claude to use, and I have been able to add it when using claude in browser -

``` Beautiful is better than ugly. Explicit is better than implicit. Simple is better than complex. Complex is better than complicated. Readability counts. Special cases aren't special enough to break the rules. Although practicality beats purity. If the implementation is hard to explain, it's a bad idea. If the implementation is easy to explain, it may be a good idea.

Trust the context you're given. Don't defend against problems the human didn't ask you to solve. ```

How can I add it as a system prompt (or if its called something else) in vscode so LLMs adhere to it?

Same. AI is a good tool to use as a sounding board and conversation partner.

I only access claude and others using my browser - I give it a snippet of my code, tell it what exactly I want to do and what my general goal is, then ask it to give me approaches, and their pros and cons.

Even if someone wants to use AI to code for them, its still better to do the above as a first step imo. A sort of human in the loop system.

> It adds velocity but velocity early on always steals speed from the future. That's been the case for languages, for frameworks, for libraries, it's no different for AI.

Completely agree. I'm seeing this in my circle and workplace. My velocity might be a tad bit slower than the rest of my peers when you compare it per ticket. But my long tern output hasn't changed and interestingly, neither has anyone else's.

As an aside, I like your system of completely removing autocomplete unless you need it - may be something like that would finally get me to enable AI in my IDE.

A playground for the zon format is great, but it would be amazing to see a few examples where zon has already been integrated into the LLM and see its responses to user queries. It doesn't even need to be a playground (as that becomes costly quickly), just some examples for the user to see how the black box will work when zon is integrated.

I kind of wonder how far would 200 dollars would go. Would it be enough to start a local campaign in a town of 100,000 people?

I just created separate profiles for different stuff. Work is all on chrome anyways due to google integration, so all thats left in my random browsing.

Ordered in what I use the most - Fanfics, novels - profile 1. Netflix, others - profile 2. General browsing - profile 3.

Somehow this became one of favorite posts ever shared on this website.

Its give a view into one of the most common thing used for entertainment in households worldwide now (specially if you consider phones and tablets a part of this). As a guy born in 1990s, I have never even made the connection - television itself is so ingrained into nearly all households.

I kind of like how good storytelling also relates to the article. A black person showing all the stereotyped black mannerisms in media is fine, but great storytelling builds a character whole. Adding a small thing like liking spicy indian food adds so much to the character.

Yeah. I'm all for sprints to start focusing on optimizations and bug smashing instead of just barreling down the road of profitability while the middle managers hold a gun to your head.

Do you have any insight on when these will be generally available?

I would go against the grain and say that LLMs take power away from incredibly rich people to shape mass preferences and give to the masses.

Bot armies previously needed an army of humans to give responses on social media, which is incredibly tough to scale unless you have money and power. Now, that part is automated and scalable.

So instead of only billionaires, someone with a 100K dollars could launch a small scale "campaign".

I guess my non-management / non-business side is show here, but how can it be that much?? I still remember I designed a fairly simple cron job that took database backups when I was a junior developer.

It gets even easier now that you have cheap s3 - just upload the dump to s3 every day and set the s3 deletion policy to whatever is feasible for you.

Time and physical labor are an amazing way to process grief.

There is a hindu ceremony in India where we build a funeral pyre and light it. Before that, there are prayer ceremonies that happen over a few days (I think). I've always felt that it was designed this way (way back when) to give time and space to the family to grieve. The lighting of the funeral pyre seems like letting go somewhat.

Isn't that true for every piece of software you use? Reflections on trusting trust (https://www.cs.cmu.edu/~rdriley/487/papers/Thompson_1984_Ref...) was one of the formative papers of my software engineering career.

Me too! I am a data engineer so whenever I have pipeline jobs running, I have a script that monitors them. When the jobs finish, an audio plays stating the job has finished and its status. Thats just one convenient script out of dozens.

Makes life much more easier when I can play video games or read books without having to check status every 20 mins.

Though I haven't created as many as you have. Would you mind sharing some of them??

I try not to think about it, but HZD (game) had the most believable take on the future.

AI war machines apocalypse - War machines that consume earth's sources to build drones and other war machines. There are autonomous supply chain of these to the war front, all managed by the AI.

They're unhackable, with the newest encryption that would take years to decrypt. Unfortunately, there is a bug in the production code that causes the AI to start targeting everything. AI starts killing all humans instead of the filters it was given.

How do you defeat an autonomous self-replenishing robot army that consumes the earth for energy and grows in size each day? You can't.

This perfectly illustrates why I've always preferred working at startups over major corps including FAANG / MANGA.

There is a top down culture of not embracing mediocrity that genuinely makes me thrive at work. My current company has a good work life balance and if I make a point that some part of the system needs improvement, my voice actually gets heard. Only place I've seen where sprint retros actually made impact. Most of my friends have no work life balance and also don't have a voice when they see half-assed work.

The numbers showcase the effect of this as well. The startup has thrived even when VC's have tightened their purses.

Its a bit of nostalgia for me. It took a bit of work to understand ipython when I first started as a programmer, but that effort helped me in the long run. Using ipdb for breakpoints was a game changer in my first job.

And it also was a good way to get comfortable with using terminal.

Using notebooks removes all these learnings. I dislike it because it makes for less confident programmers in the long run.

In case you missed it, there's a comment parallel to yours by the founder of the company. They also provide their email in a child comment to that. Link: https://news.ycombinator.com/item?id=43804502

There are also historical examples of nations where nothing was done to reign in the chaos and that led to far worse long term consequences for the people.

The best tech stack I have ever worked on was in an adtech company. The code was beautiful and the utility functions to interface with various AWS services were really really neat. I built a near real time estimator using Theta Sketches.

While job searching, I have tried to use techs like Sketches in my filters but it mostly draws up a blank. Would love to work on genuinely interesting stuff like that again.

It honestly did leave a bad taste in my mouth whenever I thought what the end goal of it all was.

You reminded me of one of my favorite piece of media in gaming (HZD). It feels especially relevant in the current times, with how war and AI is progressing in tandem with geopolitical unrest.

Its an old recording that the main character listens to in the end cutscene while visiting Elisabet's grave, and (spoilers) the main character was created as a clone of Elisabet. It's very hard hitting after the whole experience.

> GAIA: Query: What did she say?

Elisabet Sobeck: She said I had to care. She said, "Elisabet, being smart will count for nothing if you don't make the world better. You have to use your smarts to count for something, to serve life, not death."

GAIA: You often tell stories of your mother. But you are childless.

Elisabet Sobeck: I never had time. I guess it was for the best.

GAIA: If you had had a child, Elisabet, what would you have wished for him or her?

Elisabet Sobeck: I guess... I would have wanted her to be... curious. And willful - unstoppable, even... but with enough compassion to... heal the world... just a little bit.