This seems to be a critique of "Can Tech Legends Find the Liar? (Mafia
Episode 1)" on Youtube but critiqued from a "nerd subculture" angle, which is a thing in the USA, I guess? As a European, this took me a moment to figure it out.
I asked it how to configure haproxy, a tool that I had heard in passing about, and it gave me back exact working configuration syntax for my use case. Today that seems very mundane, but first time that happened, and I didn't have to google, read docs, or worst case sift through code, that blew my mind.
Paper went over my head but is this in any way related to my experience of Claude Opus 4.8 using increasingly terse language with very short, overloaded words? Lately I've been having trouble parsing the things it writes about my own code, it's using the kind of compressed language that you see typically in git commit message subject lines but relentless, always on.
> I think $my_species deserves to be debased in part because it's awfully egocentric and insist on being special in the universe.
This is a scary viewpoint to hold, for a human. If you despise humans, that's scary for me, as a human reader of Hacker News. Surprised to see this take unchallenged. I think we can recognize flaws in parts of humanity without wanting it "debased".
Started in 2005. Never ever did anyone complain about UB in my years of writing C code and patching other people's C code. I knew it exists - as a spec quirk. (Admittedly, never wrote a compiler and never used anything except gcc and clang.)
Tried making an MCP server with Antigravity CLI. Antigravity CLI suffers from an identity crisis caused by a tool/ecosystem change: "I am unsure if I should be reading Gemini documentation, Gemini CLI documentation, Antigravity documentation or Antigravity CLI documentation". It couldn't really correctly answer how I should be registering the MCP server in its own system until I googled it.
I have never in my 20 years of writing C heard so much about undefined behavior as I have in the past 6 months on Hacker News. It has never entered the conversation. You write the code. If it doesn't work, you debug it and apply a fix or a workaround. Why does the idea of undefined behavior in C get to the front page so consistently?
> These agentic AI's are already smart enough to figure out a highly optimized path to code exploration or search.
Hasn't been my experience. We used to use Augment Code at work which has a thing called Context Engine - basically an MCP that can answer natural language queries about pre-indexed code. Then we switched to Claude Code, which for some reason prefers to use sed to read from files using line ranges from its own memory (this despite having a range-capable read tool). I don't know, does that really mean that sed is the highly optimized path?
I can't help but draw parallels with video games. Aimbots in competitive multiplayer games is a well defined issue: it's considered cheating and frowned upon, players caught cheating are banned from the game. Tool-assisted speedruns (TAS) where a player attempts a world record at completion in a single-player game is another face of the same concept (computers help you win), but one that is socially accepted as long as runs are clearly labelled as TAS.
As a web developer, I feel like this take is wildly optimistic. My remaining qualifications that still provide some sort value are providing historical/business/architectural context to the agent and testing the agent's output. And that's only because 1) it's not all written down in Markdown and 2) the agent is massively nerfed by costs and Anthropic. The thing in the middle where I get a coffee and write code in a variety of languages, then pop open a debugger has been fully obsoleted.
My vim muscle memory has paid off more for me than my emacs muscle memory. Emacs was the better editor, though. Anything that doesn't have Vimscript is an automatic winner IMO.
Wish this post was more technical, e.g., how is the author achieving the things they advise others to do. As is, the post can't seem to decide what it wants to be: is it a rant, is it a tech post, is it a brag, or something else? Are people embarrasing themselves when they're simultaneously affected by three bugs in Claude Code? How did the author avoid being affected by them?
I get your point, but it's not even really that. It's that an AI generated photo evokes the same feelings in me that human-made photographs do and I have to catch that and turn that off consciously.
A great technical achievement, for sure, but this is kind of the moment where it enters uncanny valley to me. The promo reel on the website makes it feel like humans doing incredible things (background music intentionally evokes that emotion), but it's a slideshow of computer generatated images attempting to replicate the amazing things that humans do. It's just crazy to look at those images and have to consciously remind myself - nobody made this, this photographed place and people do not exist, no human participated in this photo, no human traced the lines of this comic, no human designer laid out the text in this image. This is a really clever amalgamation machine of human-based inputs. Uncanny valley.
That's funny. I've used that approach myself countless times to convince myself to do house chores. When your entire being seems to go "no, I really really really don't feel like doing it right now" and you just lay down the cold hard truth of "from your experience we know it's five minutes which is less time than most instances of doomscrolling". It's honestly perplexing why that part is the hardest part of the entire task.
These days announcements like this just make me want to put on my tinfoil hat - what's in it for Google, though? Why make it more convenient for people to submit webpages to you?
I understand this is vague on purpose but wish there was more detail. E.g., if I am running a game in a webgl canvas and "back button" has meaning within the game UI which I implement via history states, is my page now going to be demoted? This article doesn't answer that at all.
Yeah, I cancelled the moment I realized that the subscription is a scheme to get you to constantly dip into extra usage. I get more benefit out of Claude on the free tier than on Pro.
When your boss looks only at the business output and your most prolific developer writes "save" for commit messages, it gets real hard to enforce a commit message policy. "It's hard to review"? Your boss doesn't care about that and it slows the 10x guy down. These days I just run an LLM on the commits to annotate them (via git notes) based on context.
This is also my experience using both via Augment Code. Never understood what my colleagues see in Claude Opus, GPT plans/deep dives are miles ahead of what Opus produces - code comprehension, code architecture is unmatched really. I do use Sonnet for implementation/iteration speed after seeding context with GPT.
For me GPT always seems to get stuck in a particular state where it responds with a single sentence per paragraph, short sentences, and becomes weirdly philosophical. This eventually happens in every session. I wish I knew what triggers it because it's annoying and completely reduces its usefulness.
I feel the same way. Given it's AI-written, looking at the code isn't even worth it to me. I would rather read a blog post about how they develop it day to day.
That's not it. Flame wars are as old as the internet. The quality of discourse has plummeted largely due to these factors: 1) democratization of access to an audience and 2) engagement maximization algorithms. Anyone with a hot take can post it, get people angry fast, at which point the engagement maximization algorithm picks it up and carries it far and wide.
Focusing on "copying" seems like missing the forest for the trees. There's the copyright angle, but copyright laws are unnatural obstacles designed to give the original author some control over what happens after publishing. They're not fundamental, we made the laws.
What is fundamental is this: every artist starts out by copying the works of others. It's how you learn.
And in that framing, once you publish your derived work, there is only one question that arises - if you don't credit the original author but sign your own name, you're fundamentally misleading your audience. Your audience implicitly assumes you made the thing. Maybe you made 95% of it, but if you don't give due credit, it looks bad once your audience discovers that.
On more than one occasion my perception of an artist has shifted once I discovered the "brilliant work" they created was actually a remake of somebody else's brilliant work. It's a feeling of being misled. It's never a feeling of "wow, this guy is a total hack and has no ability of their own".