An AI slop article about the limitations of vibe coding. How ironic.
HN user
tills13
Sorry but I'm not reading an AI slop article no matter how pertinent or interesting the subject is. You want my attention? Earn it. Write it yourself.
Yes: because it will simply steal (rather, has stolen) this guy's genuine, human, work.
I use AI for my job. I understand the impact (as much as anyone can) that it will have on society. I recognize the value.
But I just want to say that talking with AI casually is critically lame. I cringe every time I have to ask my Google Home to turn on the lights and people are having full-on conversations with it? And, imo, dangerous considering how sycophantic AI is. The stupidest, most gullible, most insecure person right now is looking at this thinking they are about to make a new friend.
Even in the age of AI how the hell can you make a game without programmers?
Yeah. Remember when that guy made Doom in TypeScript types? That was incredible. This feels shallow and dull. Interesting idea and cool that ClickHouse -- a primarily human made piece of software -- can even do this but I agree it no longer does it for me.
I love my pebble time 2. I wanted a tide app for fishing -- there wasn't one for my country yet (Canada, there are some good US ones)... So I had Claude make me one and had it on my wrist in an hour or so. I think they did a really good job with the dev. process with this watch.
It costs nothing to not be pedantic.
+1. Claude Code shows that _even while the model is incredible_, you still need proper engineering discipline to ship stable (and good) software.
I'm Canadian so that would be an honour.
Beyond just being dangerous, it's also incredibly frustrating to go down to my local grocery store and 50% of the stalls have these massive trucks and SUVs sticking out over the sidewalk / into the through-road / taking up literally the entire width of the stall. It boggles me that people buy these things and then use them for puttering around town 99% of the time.
Instant deposit via credit card? Is that not considered a cash advance?
We are fully embracing LGTM ourselves but this is really interesting. Loki for us has been great, though, so what is better about CH other than maybe sql being more expressive than LogQL?
Also like redis and clickhouse are diametrically different platforms. Wild to go from one to the other.
The app known for making shit up (as in: that's it's whole shtick)... Getting into medical advice?
cool looks like this nuked all of our authenticated connections in Heroku, too.
Me selling lemonade at the end of my driveway is about 300-800 million dollar business. That's just one thing I sell at the end of my driveway.
250k people in my city x $4/lemonade x 365 days per year
It's apocalyptic to the people who previously clocked in, did mediocre work, and clocked out. For those of us willing to put in a little effort, it's just another tool. Though I think there's still a disconnect at the managerial level where they think firing half the team and giving the rest AI is going to 10x revenue.
You get out of it what you put into it.
Beyond that, it's a force multiplier and it doesn't care if the force is positive or negative. Someone with poor software engineering principals can use AI to make an absolute mess quickly.
The difference between "art in general" and this is scale and speed. Sure, I'll grant you that people are going to engage in deception with or without this but the barrier to entry with this is literally on the floor. Do you have a $5 prepaid VISA? You can generate whatever narrative you want in 30 seconds. Replace the $5 Prepaid VISA with the pocketbook of a three letter agency and it starts getting crazy.
I know this is kind of at odds with this thread in general but
but I know it requires work (...) to finish it
If you're like me and, when you get to this stage, you tend to burn out and abandon the thing, have you tried using gen AI to get you over that hump?
I love coding and still do but I often reached a point where all the fun, easy things were done and I'd be stuck at 90% with only difficult and boring tasks. I've been using Claude recently to just get me over that hump and finish my projects. It can still be fulfilling if you do it right.
So are they defunding NASA or not?
These AI in Excel products are a financial crisis waiting to happen. Or maybe just Enron but stupider.
react to GitHub events from Anthropic-managed cloud infrastructure
Oh cool! vendor lock-in.
I think the point is that I don't have to remember the command. I just have to tell my agent in plain-English to do X.
For example, we're dragging our feet on Github Config as Terraform at our org so in the meantime I've been using Claude + the gh cli to deploy changes across repos. I don't need to know / remember the gh cli command to pull or push a ruleset, or script a loop in Bash, I just have to say
Claude pull the ruleset from <known good repo> and push it to <repo 1>, <repo 2>, <repo 3>
The CLI is also nice because it abstracts away authentication. I have another flow which doesn't have a CLI and Claude is more than happy to interpolate the API key that it read from a config file into the chat history (horrifying).
[flagged]
I keep forgetting have a 3080 laying around... Gotta figure that out.
4.4 expletives per word is insane. Their prompts must look like
** ** ** ** implement ** ** ** ** no ** ** ** ** ** mistakes
What do you run it on? And even then, I'm guessing your tokens per second are not great?
Is it not already a node app? So the only novel thing here is we know the original var names and structure? Sure, sometimes obfuscated code can be difficult to intuit, but any enterprising party could eventually do it -- especially with the help of an LLM.