quadrifoliate

Joined 7 years ago

Karma
6,326
Submissions
1,017
Member since
Aug 15
Maximum Hacker News aside of the week writer.

Email: <username>@protonmail.ch

View on Hacker News

Recent submissions

Comment · 18 days ago
To be clear, when I said "can you", I didn't mean "does the system allow this", more like "are you, the person I am speaking to who is the architect of the system, confident that you could make a fix to this system without the LLM's help?".

> I also encourage "old-fashioned" PRs for anyone who wants to gain a deeper understanding in a certain area of the code.

Yeah, this is kind of what I meant. I think in some future, these are going to be really valuable for maintainers.

Comment · 18 days ago
> To see people who literally work in the field of automating almost everybody else out of their jobs

Over-generalization. Lots of us have had nothing to do with automating people out of their jobs, unless you want to go really far back, like "in 1921 people used to do this with a slide rule and you put them out of a job over a hundred years later, somehow".

> ...doctors have rigged medicine! It's one of the biggest social problems in the United States.

Another over-generalization. I know lots of people, some of whom are doctors. You know what no one says about the doctors? "Hey, there's a member of a cartel who's artificially keeping prices high. How disgusting!". They all say "Oh cool, he/she's a doctor!" It's only for terminally online people that this is some huge social problem.

> complaining that our field isn't run like the East Coast Dockworkers unions

Exaggeration. You don't need to be run like the East Coast dockworkers unions to mandate certain professional standards and certifications so some Pointy Haired Boss who read a blog post on the Internet (nowadays, who got a sycophantic answer from his LLM) can't just make up rules about the software you ship. Now I'm fairly sure you haven't worked at companies like this; count yourself lucky.

Comment · 20 days ago
Could you fix a bug in this codebase yourself, without the help of agents?

Maybe trying this would be a good experiment? Say route 10 or 20% of any future issues to the “Chief” to troubleshoot and fix directly, and record those for further work?

Comment · 25 days ago
I know this is like saying "I could do what Jackson Pollock does if I just threw some paint around"...but I can't really shake the feeling that that Muuto Post looks like something out of my dorm room but for 1255 dollars.

I guess the modularity (you can purchase more lights) is a real feature though?

Comment · 1 month ago
I'm thinking more of the design language and lack of modular functionality part here. Ikea stuff is perfectly fine and minimalist, but the FORSBOGG shelf and the GLOMBOR lamp never seem to be built with any kind of underlying design language in mind and may or may not go together. The BLOKKE box sticks out when you put it in the FORSBOGG. Yes there are notable exceptions (KALLAX inserts, etc.)

This is the same problem I see with these Stripe tools. This may not actually be a problem for real users at Stripe.

Comment · 1 month ago
It's not just you. Let's take a small paragraph and break it down.

> Surface-agnostic APIs: Kai ships with an opinionated web application and a Slack integration, but the main primitive is the underlying API that powers them both. The agent is a service, not an application, and surfaces are simply customized views into it.

I...kinda get that they built an API that the agent polls. And then Slack or the webapp both invoke the agent? If so, the above paragraph is obscuring the point. Also, why isn't there a diagram showing it? There is a diagram below showing "Execution Environment" below, but that one doesn't show the API. And Kai and "Stripe Product Agents" are parallel paths on it. Does it not call out to this API anywhere?

I doubt if most people these days actually try to understand any of this, or just go "Agents? Cool! Here's some product that's vaguely similar that I like or have worked on!".

Comment · 1 month ago
Even for non-inside hires, I feel like it's more efficient for me as a hiring manager to go out and look for candidates rather than triage some AI-generated pile of crap.
Comment · 1 month ago
The issue is not that that the presentation work has been offloaded to AI. It's that the result is sloppy.

People are always going to judge based on what seems "surface-level". Stuff like legibility also matters just for data comprehension, the AI tic of constantly repeating key numbers all over a presentation or webpage actively hurts legibility.

Comment · 1 month ago
At this point why don't you try to go out and contact candidates yourself or via a recruiter rather than posting jobs? It seems to me that with LLM-based tools you are going to find it increasingly difficult to get those 2-3 out of the 40; all 40 will be LLM-written to perfect match your posting.
Comment · 1 month ago
> Ultimately, it is pragmatic for businesses to behave this way, but it is a shame for those who love the craft. I think we took for granted the beautiful ornate hand carved furniture era of software engineering. We are now in the ikea era.

I feel this so much. I thought AI would make it easier to get lots of hand-carved ornate furniture; but right now what we are getting looks like the typical Ikea product line -- a bunch of mismatched pieces by a host of different designers with no common underlying design theme or continuity (I'm talking specifically about the looks and design, not the materials).

Comment · 1 month ago
They have published a bunch of stuff about their internal tools in the past. Look up https://stripe.com/blog/stripe-home and compare it to this, as an example.

It's always possible that in reality they were always a bit less polished behind the scenes though.

Comment · 1 month ago
Stripe is the company I usually hold up as the exemplar of polished internal tools. Hopefully this is taken the right way and I don't want to be negative towards the teams working on this, but I see a distinct lack of polish in these tools and presentations. Some examples:

- Unnecessary AI copy throughout the interfaces like "Browse, discover, and manage skils for your agents", "No favorites yet — hover a card and click the star to pin it here", "One execution environment, shared across agents". These instantly read as AI copy and decrease my enthusiasm.

- Inconsistent, AI-sloppy look-and-feel with different typefaces spattered across the interface.

- The session metrics slide looks busy and AI-generated. It repeats 360,014 sessions in one of the cells at the top, but also has a "360K sessions" in the heading.

I don't know if I'm the only one that notices this stuff, or whether others see it too.

Comment · 1 month ago
> everything he described seemed the same or basically the same as every other employer

If 24 hour SLA and employers helpfully following up on what you got wrong in the interview and offering to get on office hours with you so you could retry in six months is "basically the same as every other employer", I have been interviewing at the wrong places for 15 years.

This is, of course, assuming that everything the author says is true. They could be exaggerating. It sounds exhausting to do these office hours as an interviewer in addition to running a company.

Comment · 1 month ago
You are choosing a really bad example to make your point. Not letting extensions operate on the actual site where you install the extensions isn't being "comically evil" by any means.
Comment · 1 month ago
What reality are you living in?

The software job market, especially for those of us outside the major tech hubs has been severely biased in favor of employers for the last 3 years, with constant layoffs and rising inflation.

If I was working for Automattic I can definitely see electing to stay there until the job market improves.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton