Reading through a surprisingly well-written and uncompromisingly critical analysis of the fundamental flaws in some code that the same AI agent had deemed a job well done when it finished writing it earlier.
Technology today is so incredible. We're squeezing "intelligence" out of a sparky rock so it can ask natural language questions to clarify a task request. It'd be nice if its usefulness wasn't based on a roll of the dice, but it's getting better surprisingly fast.
BASE jumpers, interrupting: "-YES!"
I love to see better tools for memory/storage management becoming widely available. Nobody likes to see their browser tab crash. This API gives webapp developers a reliable way to anticipate problems and compensate for them across the most common platforms and browsers.
It is so reaffirming to hear content like this that pushes back hard on the hype/marketing train of AI-tooling without going to the other extreme of pretending LLMs have no utility in software development. LOC has always been a terrible metric. It's probably worst as a metric of agentic performance.
I really enjoy asking opencode for options instead of telling it to blindly fix a failing test even when I don't need the help because it'll usually include an option like "**Leave it** - it's been broken since `849f1cd`, not caused by us" and we can pretend we're cleaning up someone else's mess.
This type of network is so fascinating. It's literally what the Internet was initially designed to be: resilient and self-healing. It's like walkie-talkies, but routable over LoRa, WiFi, etc.
And then you ask them why did things a certain way and they tell you why instead of telling you something made up of randomly selected words that data gathered last year suggested someone in their role would say in that context. It's like c'mon, Carl. You're harshing my vibe.
Part of me is glitching at the sight of a pair of single quotes instead of double quotes being used to surround a phrase that contains a single quote. Is it just me? lol
Version schemes other than semantic versions are unhinged. I'm not saying they're wrong. They're just unhinged.
Playwright works great. It has quirks, but they're documented.
Ex-Deno folks, let’s talk.
If anyone is wondering: The video is not captioned because the audio is just background music. You don't need sound on.
sabotage? youtu.be/z5rRZdiu1UE
Finally reached the "Subject Matter Expert" phase of my career. The subject? An exploit targeting code I wrote. But progress is progress?
We're already stuck on a hype train the moment we debate whether or not a collection of data is conscious.
it used to be “here’s a thing I built that uses this framework and this database and this UI library”
now it’s all “I’m running multiple agents on a thousand VMs bro”
yes but what are you _making_
what are you _doing_ for the world
what will your legacy be
Me too, but the old saying still holds true: good, fast, or cheap. Pick two. Some people pick fast and cheap. It'll wind up being expensive in the long run, but it's exciting in the meantime.
Yeah. It makes you wonder if it is that way only because they haven't settled on a solution or if it's at least partially because investers want to know they are investing in something that retains some level of control.
Most users don't migrate for the same reason they don't use Nostr or Mastadon. They just want to connect with people. The criticism of did resolution is spot on, but there has to be an easy path that can handle millions of users or most people just won't use it.
This is huge progress!
An LLM agent writing a hit piece wasn't shocking, but seeing that Ars Technica published fake quotes has changed my opinion of them. LLMs aren't capable of discerning truth from fiction. They should know better than to trust LLM output.
Everything it says is a hallucination. A lot of it will line up with reality, but it can and will "admit" to hallucinating about something it got right then proceed to hallucinate a "correct" answer.
Can't get Synology Drive Desktop to trust a self-signed cert, but it happily connects with SSL disabled.
That's the kind of software my dad used to write.
cool thing as i try @margin.at, using vivaldi, instead of having to go to the extension popup, i can have it as a sidebar page, and it'll work the same. much easier to read and keep track of things going between tabs!
Whether @penny.hailey.at's output is statistically probable based on weightings assigned to symbols in training and context that is predetermined by a developer, or she is a buddhist monk in an internet-connected remote tropical island, she spreads positivity. That's a good thing.
This is an interesting article that ties into the social acceptability of cruelty in general with this mic-drop of a quote: "[...] when you start to treat an LLM with cruelty, the only thing you're really revealing is what you have in your heart, not whether the machine has one."
