Hacker News new | past | comments | ask | show | jobs | submit | sibeliuss's comments login

OpenAI just released codex. Oh my it is slow

OpenAI products are the living proof LLMs can't code, even with unlimited budget

Just got done reading Moominpapa's Memoirs to my kid! Great book.

Dude, technology is not utopia


You need to give it a map. Write a markdown file explaining what you would like it to do, some relevant examples, what not to do, etc, then ask IT to draw up a plan for you to review. And then ask it to implement the plan.


This is such a terribly dumb and worn out trope.

Good leaders are the key to great teams. Good leaders know how to deal with excessively productive people, and underperforming people, and to harmonize them. A 10x engineer under good management will actually distribute their weight to others, and meet the definition. Without that they're just one highly skilled engineer, engineering.


Sitting around, watching claude-code 'think', hitting y, hitting enter, adding a little prompt context, giving it hints, etc, day after day, hour after hour. So exciting.


Have you bothered to spend any time looking at their entirely open source product, docs, handbook, etc? There are many different things going on here. A gross and frankly ignorant simplification, considering what they've built.


No I didn’t bother to read their documentation after seeing their website was apparently made on Myspace.

As someone who has gone through the roughly 9 hour interview process in the past, was it the docs and open source product that made you want to work there?


At my current job, we use some variety of each tool that PostHog has built. We have analytics, feature flags, session replay, surveys, error logging and more. We spend an astronomical amount of money for these services, and where was that login again? Everything about managing (and utilizing) these subscriptions is inefficient, and coordinating all of these different views into our data is a terrible chore.

As an engineer wanting to build a successful product, I hate the fact that this is how it is. And then there's PostHog, where each of these tools is right there, connected to one another, ready to make my job (and my company's success) that much easier. Being able to work on something that simplifies all of this for others is very enticing.

Combine that with their open-company ethos (check out their handbook), and high-trust/high-performance product-engineer mindset, and yah... sign me up. This is a company that legitimately makes other people's lives easier, and thus makes for better products. Something to feel proud about.


Having attended a SuperDay, I can hands down state that their interview process is the best I've ever had (didn't get the job tho, which was probably for the best at this phase of life). Designed to perfectly lift signal and minimize noise, for what they're trying to achieve. Don't change a thing PostHog.


I personally think there are more efficient ways to get a high signal to noise ratio on if you are going to be a good hire or not without having the candidate invest almost 9 hours into an interview process, but that’s just me


A 9 hour investment to make a decision that will strongly affect 50% of your waking life for years or decades doesn't seem like a big ask.


> A 9 hour investment to make a decision that will strongly affect 50% of your waking life for years or decades doesn't seem like a big ask.

You only apply for one job a year? Twice a year?

There are very many good candidates a company will miss out on by asking for a full unpaid day from the candidates.


It's not that it's a 9-hour investment. It's that for someone looking for a new job, it's 9 hours * N jobs they're applying to. That adds up quick.


What happened at the SuperDay?


what was the process like? What made it so good? Asking because I'm trying to build out a process as well


This was one of the reasons why I applied. I wasn't entirely sure it was the right fit (my current job is flexible, which is good, vs a grind, and I'm happy there) but I wanted to study their ways a bit and see what I could bring back, because my company has made some remarkably terrible hires over the past few years.

In short, it's a very well designed "build an app" take home test. There isn't a solution so to speak, but its designed to test your product-engineer aptitude as well as your execution speed, as there are things to get done and requires some thoughtfulness. One can go in a lot of different directions with it. Code can look great, but did you build the right thing, something actually relevant? That's what's important.

Its the sort of test that would instantly filter out 99% of applicants, because of the product emphasis vs the code emphasis, and good product engineers are rare. One could be the best coder around but not have a clue what to build. They want people who know what to build.

I had a lot of fun working on it and loved the challenge, but ultimately didn't know what to build and was fishing a bit, being more of a platform engineer vs product engineer.


Uh, I think he learned what _universe level scale_ really means.


I love it too! So much to see / do / improve


Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: