sailorganymede

In my company, we already have agents messing around on our internal systems interacting via Playwright to try break things

I can't wait for the HackerHacker: HackerNews comments cited by other HackerNews comments

This is cool and all but the controls don't work on my laptop. I keep going up.

I get what they say but what I see or have seen is totally different. I come from an engineering culture where we got AI token leaderboards and mandates to use AI for every single step of the development process. We started running into bad bugs recently due to people just copy pasting the Jira into the prompt so I feel there is space to put some intentionality in the areas which matter.

Not yet. But you’re like the 5th person to mention it so I think I’ll add that feature. There are some AI prevention stuff like you can’t copy paste which means you gotta use the visualisation.

Honestly I love to see people working on this problem ! I actually built a similar project myself (https://github.com/bhurghundii/vibecheck.dev) except it prevents you from merging on the PR level. I’d love to get in touch to talk about it sometimes.

Edit: I see there are a lot of people questioning the value of this. The thing is that there are teams where people are just pumping tons of AI code without understanding their work (literally take the ticket and dump it) and shipping it. culture change is the right answer but v hard but this at least slows things down and is quick to implement

Never thought I'd see my team on HN but I really love the changes Arsenal has done. I remember only 10 years ago, we were super corporate and quite trend chasing (with our captain Aubameyang et al. doing reaction videos and sweg sweg) and you could really tell the messaging was supposed to be sanitised and generic. I noticed esp. when Arteta got in, we started to actually have an identity of our own with the typefaces and a brand new song and all the focus on our history etc.

The core point here is that AI is a massive thing (at the moment) so it's probably a good idea to understand it deeply. Not sure why people are so worked up about it.

I did a hackathon this year. I used to do them 10 years ago when I was a student and the biggest difference is the intention of the hackathon. 10 years ago, it was all about having fun and learning some new and cool (it was where I learned NodeJS) but today, the sentiment is all about "what can GTM tomorrow?" or "what would VCs want to fund?"

I can't say I found the Hackathon I did particularly fun. Nothing thrilling about making Claude do things while drinking the free coke.

Not yet. It’s still pretty awful and I haven’t figured out the UX too great but if you are interested, I’d be happy to show you what I got together so far.

A PR quality gate which grills me to make sure I understand the code changes I am making before I merge. I have been working on an AI app which deals with vulnerable users lest I ruin the experience for my customers so I am a little bit hesitant to "go fast" but I find AI really helpful in my process.

I actually have been working on it for a little while but this is the first week where it's been quite helpful.

This is the thing that annoys me. They have the Fallout series hostage and moves like this sadden me because I can't expect the next game to particularly great when stuff like this happens.

I am a big fan of Vite. But I have zero clue what those other tools are. I swear to God, I just put my head down to do some work and all the sudden, frontend tooling has evolved. I wonder if there is a push towards a "boring but works" stack.

Hey man - yeah I’m down to chat! My email is in my bio so just reach out there and we can chat

I’m working on a GitHub quality gate that checks your PRs, guesses if it’s a total vibe coded piece of shit, and then grills the dev to check if they actually understood what they wrote. This way, my time as a reviewer doesn’t get wasted.

Inspired by my experience at my day job.

Looking for testers if anyone wants to help out!

I run an art training app and one of the features I am working on is AI generated critique (it's an app for training realism.) And I noticed if I gave the AI the original image, the tonal breakdown of the image the app generates as well as the user's drawing, it delivered critique far better and more targeted.

I believe I had the same one? I remember travelling Europe and going to the same place like 3 times while I was in Iceland!

Thank goodness. It was a pain to do this manually

Can I get on this action too? This sounds like a good idea.

I donated - it's valuable software and I love it very much. My feeling is as long as it's not hounding me for future payments i.e. calling me up during the day, it's fine.

News sites are going irrelevant anyways. I'd imagine they are pushing hard for this because traffic has died cause AI overviews have hit direct traffic to websites and independent writing platforms like Substack / Medium mean I can read a quality opinion on a matter I care about.

Value-study-practice-o-matic is the best name I've come up so far. It's just an automated way of practicing rendering when painting.

I noticed that the orders hasn't bumped up that much since this was shared last time. Not really sure I see the growth here is showing a lot of demand for a European smartphone - although I could totally be wrong given the geopolitical situation.

I worked on text chat ages ago over TOR. Honestly so happy to see that the ecosystem is still going!

No Mans Sky but it’s a text based MUD. Using LLMs ofc.

A lot of teenagers complain they spend too much time on social media and this will put some friction that wasn’t present before. I assume this will put a dent in traffic for companies like SnapChat etc. so I wonder how those companies will react.