aster0id

Recently I vibe coded a couple of scripts invoked by cron to do the same thing for a few services running on a single node for me. Works beautifully.

How many false positives did the AI throw up?

This is incredible research. So much harm can be prevented if this makes it into law. I hope it does. Kudos to the anthropic team for making this public.

I had a similar problem this year after having moved to a new country, working a remote job and separated from my partner. Having had a terrible social life since I was a kid, I knew it in my bones that I'd have to find myself new friends or else. So I did - I renewed my relationship with old friends, joined a book club (was a big reader as a kid), and my dog helped me make friends at the dog park.

I find it interesting that I've thought about the exact social mechanics of making friends before as well - low stakes in person common context where you meet on a regular basis is key.

Yeah but work isn't all there is to life, at least for me. There are way more fulfilling things. If you like your work more than anything else in life, good for you. Different strokes for different folks.

A demo video would've been nice

I agree with the premise but take issue with the measure for "success": do you feel excited to get up and work on Monday?

We're humans and no matter what you're pursuing, you'll hit a point where your brain will adjust to the new reality and things will start feeling mundane. This is called the hedonic treadmill.

To me, what has helped is developing hobbies and relationships outside of work. We're social animals and need connection with others to feel fulfilled. Personally, my own life feels way more fulfilled right now than when I was just working on interesting projects at work or on my startup (that went nowhere).

> Code is so cheap it’s practically free. Code that works continues to carry a cost, but that cost has plummeted now that coding agents can check their work as they go.

I personally think that even before LLMs, the cost of code wasn't necessarily the cost of typing out the characters in the right order, but having a human actually understand it to the extent that changes can be made. This continues to be true for the most part. You can vibe code your way into a lot of working code, but you'll inevitably hit a hairy bug or a real world context dependency that the LLM just cannot solve, and that is when you need a human to actually understand everything inside out and step in to fix the problem.

Be careful with sharing this URL in your Instagram DMs. I built something similar a few weeks ago for watching Instagram reels, shared a link to it with someone on Instagram, and my account instantly got suspended because this type of stuff violates Instagram's TOS and they crack down really hard on it.

Dog enrichment calendar - I have a lot of different types of treats, toys and activities that I'd like to do with my dog but I fell into routines and just gave him two or three toys and treats on repeat. So I'm building an app where I'd be able to configure an inventory of all the treats and toys I own and the app would remind me to use a new toy or treat every day, to minimize repetition. You'll also be reminded ahead of time for toys and treats that require preparation

I relate to this. I started building side projects last year, and being used to all the bells and whistles of CI/CD, serverless/containers and amazing monitoring and dashboarding tooling, I defaulted to those patterns even for my tiny projects. To make matters worse, I tried building everything on top of free tiers of various services, which made configuration and setup even harder as I was trying to glue things together in non standard ways just to make free stuff look like the stuff I have at my job.

I quickly learned that I needed none of that crap. Now I usually just have one dev environment (my local machine) and one prod, usually a free cloudflare worker. DB is almost always a free tier postgres instance. Testing and prod deployment happens on git precommit and postcommit hooks instead of inside a CI pipeline. No docker is usually necessary as I just build typescript services which have native support on most platforms. DB migrations are run directly from my local machine when I need them to run, instead of having specialized config in a CI pipeline.

I doubt that the product folks over at Google overseeing an experimental project like this have such outsized influence over something core like the ads engine

I'm an individual, experienced FAANG software engineer looking to build something in this space. Lmk if you want to chat about building something together

This could become the missing piece for RAG with LLMs for company data. Every query that requires a lookup can use this model and then an agentic LLM can crawl through the hierarchy of results to extract the relevant information for the user's query. I suspect that'll work much better than the current methods of chunking and storing data with metadata like title and author in a vector database and then performing a hybrid search

So the solution to all of the world's problems is to move everyone to the Arctic/Antarctic regions! Got it

What's the end game? Make people write more high quality, high complexity code with less time?

I don't think that's how it works. You can try to juice the rock as much as you want, but you can only choose any two of the three IMO. It's a structural constraint of making humans write code. If they end up creating code generating machines that can do this, good for them. But until then it'd serve everyone better if people just accepted reality.

It's a dumb game, sure. But I'd say it arises from opposing incentives, not necessarily from a real desire on the company's part to screw you over.

How important is feeling "not screwed over" at the beginning of an employment important for you? Does it trump a great work environment and interesting things to work on? How sure are you that your subjective feelings during negotiations match how the employer actually is objectively?

It would seem intuitively obvious that there must be correlations between being screwed over in the beginning and then having a bad experience later on during the actual job as well. But I'm personally wary of blindly following intuitions in matters that relate to money.

Being able to just "walk away" from decidedly some of the highest paying jobs in the world (irrespective of the feeling of being low balled) is a privilege too.

Anyway, in my own personal experience, I was screwed over during the offer phase of a previous job, and the job was not great either - terrible wlb and politics, but I did learn a lot and became very efficient at my work. As a bonus I stopped caring about my work outside of being necessary for paying my bills, while still maintaining decently high quality output.

I had the opposite experience with my latest job - the recruiter was professional and empathetic, and I had a great offer experience. The job itself is great as well.

So yeah, maybe there are correlations, but I'm still just one data point and so I'm not keen to generalize yet.

Because the authors are likely non native English speakers. I'm one myself and it is hard to write for a primarily native English speaking audience without linguistic artifacts that give you away, or worse, are ridiculed for.

It's interesting to see that extraversion actually seems to hurt founders

The more I learn about the world the more I learn that I don't have any control over much of what will happen to it, and by extension to me.

So my choice is to live my life and enjoy it as much as I can.

In which case there will be massive social upheaval, which won't be good for the newly minted god-CEOs. They are incentivized to share the spoils of infinite productivity. What good is being a god of a world in flames?

If AI agents do get better than human SWEs, they'll also get better than their human counterparts at other jobs - including being an entrepreneur.

When people call out the doom of SWE careers at the hands of AI, they seem to think that only SWE careers will be affected, which seems weirdly biased to me. If AI comes for our jobs, it'll come for everyone's jobs. And if that is the case, economics/capitalism as it exists today doesn't make any sense anymore.

I've interviewed for Coinbase and it was a shit show. The recruiter initially said my interviews went well but then never got back to me, even after me reaching out multiple times. Plus there are lots of reports from people working there that things are held together by strings and glue, and the work life balance is terrible.

Late millenial. I agree with everything you said.

I use various models through Openrouter API + Open WebUI with a custom step by step prompt. Here's the output using the Qwen2.5 72B model:

To determine the output of the given `fizzbuzz` function for an input of 3, let's break down the code step by step:

1. *Function Definition*: ```javascript function fizzbuzz(n) { return (["Fizz","Buzz","FizzBuzz"])[ (n % 3 === 0) + (n % 5 === 0) ]; } ```

2. *Input*: - The input `n` is 3.

3. *Evaluate the Conditions*: - `n % 3 === 0`: This checks if `n` is divisible by 3. - For `n = 3`, `3 % 3 === 0` is `true`. - Therefore, `(n % 3 === 0)` evaluates to `1` (since `true` is treated as `1` in arithmetic operations). - `n % 5 === 0`: This checks if `n` is divisible by 5. - For `n = 3`, `3 % 5 === 0` is `false`. - Therefore, `(n % 5 === 0)` evaluates to `0` (since `false` is treated as `0` in arithmetic operations).

4. *Sum the Results*: - The expression `(n % 3 === 0) + (n % 5 === 0)` becomes `1 + 0`, which equals `1`.

5. *Array Indexing*: - The array `["Fizz", "Buzz", "FizzBuzz"]` is indexed by the result of the sum. - The index `1` corresponds to the second element of the array, which is `"Buzz"`.

6. *Return Value*: - The function returns `"Buzz"`.

Therefore, the output of the function `fizzbuzz(3)` is `"Buzz"`.

### Reflection and Error Checking - *Step-by-Step Verification*: - The conditions `n % 3 === 0` and `n % 5 === 0` are correctly evaluated. - The sum of the boolean results is correctly calculated. - The array indexing is correctly performed. - *Logical and Factual Accuracy*: - The logic and arithmetic operations are correct. - The array indexing is consistent with the conditions.

No errors were found in the reasoning or the final answer. The output of the function `fizzbuzz(3)` is indeed `"Buzz"`.

Everything is getting en-shittified, even YC itself.

This has been a trend for my cohort of college graduates. Graduated right in time for a housing crisis, inflation, layoffs, etc. Can't help but feel at least a little bitter about folks who pulled the ladder up behind them.