HNHacker News
TopNewBestAskShowJobs

loveparade

2,076 karma · joined December 30, 2022

Meet Me At The Love Parade
submissionscomments
loveparade··on I quit drinking for a year
I haven't had a drink in 6 months or so. Not because I wanted to stop, I just have not had the desire to drink recently.

Now I would love to tell you about all the amazing magical healthy benefits that have come with that, but unfortunately there are none. I feel no difference at all.

loveparade··on To my students
Doesn't matter who reads it. The point is that you will probably never learn to do "high level system design" well if you do not have enough experience writing and refactoring code yourself. It's like you wanting to become the chef of a kitchen and giving instructions without having ever prepped food.

There is indeed something useful about trying to write elegant code. Not because others read it. But because that's how you learn about the engineering tradeoffs and abstraction that exist everywhere.

loveparade··on Anthropic takes $5B from Amazon and pledges $100B in cloud spending in return
I give it one to two more years before open source models have fully caught up. Products are commodities and models are commodities too. GPUs cores are still hard to get for inference at scale right now. They need a platform with lock in but unsure what that would look like and why it wouldn't be based on open source models.
loveparade··on Anthropic takes $5B from Amazon and pledges $100B in cloud spending in return
Good lucking getting GPUs.
loveparade··on OpenAI backs Illinois bill that would limit when AI labs can be held liable
Not really, when OpenAI was formed in 2015 there were no LLMs, at least none that worked well. It was a regular AI research lab mostly doing Reinforcement Learning on game environments like Atari similar to DeepMind. Once they struck gold with LLMs (2019 or so?) and saw there is money to made everything changed, as expected when a bunch of SV types get involved.
loveparade··on We've raised $17M to build what comes after Git
I watched the video but I don't quite get it. I feel like I'm missing something? A nicer git workflow is not what I need because I can ask an LLM to fix my git state and branches. This feels a bit backwards. LLMs are already great at working with raw git as their primitive.

I'm curious what their long term vision they pitched investors is.

loveparade··on Claude mixes up who said what
Yeah, it looks like a model issue to me. If the harness had a (semi-)deterministic bug and the model was robust to such mix-ups we'd see this behavior much more frequently. It looks like the model just starts getting confused depending on what's in the context, speakers are just tokens after all and handled in the same probabilistic way as all other tokens.
loveparade··on I've sold out
For me the reason to add dependencies to my projects is exactly because they are maintained upstream and I don't need to worry about maintaining them myself. If I need to fork and maintain it myself I'd rather write my own version of it that perfectly fits my use case, or use another dependency that is maintained.
loveparade··on I've sold out
Understandable, I'd probably do the same in his position. Still sucks, we've seen this pattern a thousands times before and what happens next is pretty obvious.

I was prototyping something with pi under the hood for a personal project, going to switch off it now.

loveparade··on OpenAI says its new model GPT-2 is too dangerous to release (2019)
Are you sure they are not just refusing to solve your UI bug due to safety concerns? They may be worried you'll take over the world once your UX becomes too good.
loveparade··on Show HN: I built a tiny LLM to demystify how language models work
It really seems it's mostly AI comments on this. Maybe this topic is attractive to all the bots.
loveparade··on Show HN: I made a YouTube search form with advanced filters
You could manage your subscriptions in an RSS reader, that's what I used to do. Each channel has multiple RSS feeds associated with it for different types of videos (live, vod, etc).
loveparade··on Show HN: I made a YouTube search form with advanced filters
The whole Youtube experience has gotten so bad over the years. I love the youtube content, but I wish I didn't have to deal with the UI/UX and recommendations that the YT app forces on me.

Annoying Shorts. I'm trying to keep my watch history clean to "steer" recommendations, but YT keeps adding things to it that I didn't actually watch just because I happened to hover my mouse over a video, etc.

loveparade··on Running Gemma 4 locally with LM Studio's new headless CLI and Claude Code
Interesting, I don't like codex exactly because of its built-in sandboxing. If I need a sandbox I rather do a simple bwrap myself around the agent process, I prefer that over the agent cli doing a bunch of sandboxing magic that gets in my way.
loveparade··on Running Gemma 4 locally with LM Studio's new headless CLI and Claude Code
What do you recommend? I've tried both pi and opencode and both are better than claude imo, but I wonder if there are others.
loveparade··on The threat is comfortable drift toward not understanding what you're doing
I see these analogies a lot, but I don't like them. Assembly has a clear contract. You don't need to know how it works because it works the same way each time. You don't get different outputs when you compile the same C code twice.

LLMs are nothing like that. They are probabilistic systems at their very core. Sometimes you get garbage. Sometimes you win. Change a single character and you may get a completely different response. You can't easily build abstractions when the underlying system has so much randomness because you need to verify the output. And you can't verify the output if you have no idea what you are doing or what the output should look like.

loveparade··on The threat is comfortable drift toward not understanding what you're doing
I think it just really depends. There is no fixed rule to how PhD programs are supposed to work. Sometimes your advisor will suggest projects he finds interesting and wants to see done, he just doesn't have time to do it himself. That's pretty common. Sometimes advisors don't have that and/or want students to come up with their own projects proposals, etc.
loveparade··on LLM Wiki – example of an "idea file"
That has been my experience as well. Most of the value of writing docs or a wiki is not in the final artifacts, it's that the process of writing docs updates your own mental models and knowledge so that you can make better decisions down the road.

Even if you can get an LLM to output good artifacts that don't eventually evolve into slop, which is questionable, it's really not that useful, especially not for a personal wiki.

loveparade··on Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw
I assume this means we can no longer use Claude code sessions in editors like zed because it also wraps claude cli via ACP?
loveparade··on Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw
Yeah and it doesn't help that the claude CLI itself IMO isn't that great. It feels a bit like a sloppy vibe coded app. So they are forcing me to use an inferior product.
loveparade··on Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw
That's why I am using Codex. I slightly prefer Claude in terms of code quality, but it's close, but not being able to use my subscription with other CLIs and apps ruins Claude for me.
loveparade··on Ask HN: What are you moving on to now that Claude Code is so rate limited?
Codex, it's much more generous. And doesn't lock you into using their CLI.

Still I'm a bit surprised you burn through tokens that quickly. I rarely ever reach my limit.

loveparade··on Show HN: Home Maker: Declare Your Dev Tools in a Makefile
I'd disagree. You're not learning anything if you close your eyes and tell your LLM "set up home manager" - but you'll learn a lot if you read the code it produces, ask clarifying questions, and actually try to understand what is happening. It's just a tool that helps you avoid doing tons of research manually by searching google, and helps you avoid dealing with ugly nix syntax.
loveparade··on Show HN: Home Maker: Declare Your Dev Tools in a Makefile
Now with LLMs it's even easier. Writing nix code is hard, but reading it is straightforward because it's declarative, so you can easily review what an LLM produces. And it's not much code either, a simple home manager setup is maybe 100 lines total.

1. Install nix / determinate nix

2. Tell your favorite llm to set up https://github.com/nix-darwin/nix-darwin with home manager if you are on mac, or just home manager if you are on linux

3. Review the code and ask for clarifications

You'll have a set up in 20 minutes.

loveparade··on Show HN: Home Maker: Declare Your Dev Tools in a Makefile
Or just use nix with home manager. Battle tested, lots of built-in functionality, works perfectly. Author claims the learning curve for it is weeks, but I had my setup up and running in a 1-2 hours at most and have been super happy with it.
loveparade··on Claude Code Unpacked : A visual guide
I doubt there is anything special about the transformer code the frontier labs use. The only thing proprietary in it are probably the infrastructure-specific optimizations for very large scale distributed training and some GPU kernel tricks. The real moat is the training data, especially the RLHF/finetuning data and verifiable reward environments, and the GPU clusters of course.

The open source models are quite close, and they'd probably be just as good with the equivalent amount of compute/data the frontier labs have access to.

loveparade··on Claude Code's source code has been leaked via a map file in their NPM registry
It's exactly the same as the open source codex/gemini and other clis like opencode. There is no secret sauce in the claude cli, and the agent harness itself is no better (worse IMO) than the others. The only thing interesting about this leak is that it may contain unreleased features/flags that are not public yet and hint at what Anthropic is working on.
loveparade··on Claude Code's source code has been leaked via a map file in their NPM registry
Your favorite LLM is great at building a super buggy renderer, so that's no longer a moat
loveparade··on Ask HN: Are you too getting addicted to the dev workflow of coding with agents?
I've heard similar things from many people know, but I don't feel like this at all. I don't find coding with Claude any more or less addictive than without. I do find coding with claude slightly more fun, but mostly because brainstorming with someone/something feels less lonely than writing code alone. I wonder where the discrepancy comes from.

Seeing the final result of a feature doesn't really give me any dopamine. Maybe because I'm mostly working on projects I know how to do. When I give it a prompt I already know what the result should look like, so I'm not really surprised by anything it produces.

loveparade··on Ask HN: Have you cancelled any software subscriptions because AI replaced them?
There are a few personal scripts I replaced with an LLM prompt/skill. Can't really think of any subscriptions though.
← PreviousPage 3 of 13Next →