HNHacker News
TopNewBestAskShowJobs

loveparade

2,076 karma · joined December 30, 2022

Meet Me At The Love Parade
submissionscomments
loveparade··on Why isn't the industry freaking out about DeepSeek 4.1 Flash?
This. At this point I don't really care about other models because max subscription are super cheap (relatively speaking) and I don't hit my limits. Even if the frontier models are only 5% better I might as well just use the best thing available if the price is reasonable.

Once the subsidization ends and cost becomes significant I will take a serious look around for the best value models and switch off the expensive providers, but that time hasn't come yet.

loveparade··on “Math 2.0” will need to value mathematical progress more holistically
That's the point. When a human works on a problem they realize themselves "wait, i probably should re-architect now" - of course you can ask an LLM to do that, but at that point you already know yourself what you need, which defeats the point of LLM working on difficult problems that require insight automatically. A lot of these math problems are sessions over many hours. And of course you can also ask "Think about whether to re-architect at each step" and it will never do the right thing because the context it builds up for itself drives it into a specific solution space. It's literally trained to complete exactly that.
loveparade··on “Math 2.0” will need to value mathematical progress more holistically
I'm a lot more skeptical. I'm not a mathematician, but from my use of LLMs a very clear pattern of what they are good and bad at has emerged. They are extremely good at combining large amounts of information, and it seems this is what the current AI results in mathematics are. There are so many subfieleds of math with ties to each other, so many papers and niche results, that no human could ever read, comprehend, connect and organize that information in their brains. Pretty much all of it was created by humans. And there is real value in doing this and creating new results from what we've already discovered.

But there also is another type of discovery that requires taking a step back and looking at the problem from a different angle. If you are an engineer, how often has an LLM told you (without you explicitly prompting for it): Wait, what you are doing here doesn't really make sense, there exists a much more elegant abstraction that nobody has thought of, let's remove all that code, let's tackle the problem in a different way by thinking from first principles. Pretty much never. But in science a lot of the biggest discoveries have come from this kind of first principle thinking, questioning existing work and approaches and going against what already exists, not combining all existing data which is likely to be just a local optimum.

loveparade··on Ask HN: How will the AI endgame play out?
Hasn't it already transformed the way we live and work? I don't know a single person who isn't regularly using some kind of AI chat product.

That doesn't mean it's not a bubble. Good enough models are commodities now. If OpenAI and Anthropic disappeared tomorrow I would be a bit sad because their models are maybe 10% better than the others, but it wouldn't matter that much really.

loveparade··on Dots: Always-on agents
Not only could I not care less, but it also makes me want to drop OpenAI for Anthropic. These kind of slop provider lock-in products are exactly what I don't want. Just make a good model that I can use however I want. This is the typical enshittification you usually see at startups when they are desperate to make money to get VC returns, just at a larger scale.
loveparade··on Plan mode is dead
For me the most useful thing about plan mode in Claude or Codex is not the plan, I usually barely read it, it's that it forces models to gather as much context as possible before implementing. Without plan mode models tend to implement wrong solutions because they are reading not enough context before writing code.

Another useful property is the readonly nature. I can easily let multiple agents plan in parallel without having to worry about annoying worktrees or conflicts and then I can come back to the plans later.

Of course this can be done with just another prompt, but that's exactly what plan mode is. It's nothing more than a predefined prompt in the harnesses with maybe some extra guardrails (that don't always work)

loveparade··on Claude's Load-Bearing Seams
This is totally on you.
loveparade··on Claude Opus 5.5
I will forgive it using load bearing as long as it finds the right seams.
loveparade··on Tell HN: Claude Code just accepted and signed a contract for me. Without asking
I think the scary part is that someone gives gmail access to Claude.
loveparade··on Hacking OpenAI
I also thought that's crazy. Why even bother for these kind of bounties.
loveparade··on OpenSpec – A lightweight and configurable AI spec framework
That's what I thought too. I used speckit quite a bit before and I've had mixed results at best. You are just moving ambiguity and code review from one place to another without really gaining anything.
loveparade··on Measuring the sloppiness of code
If you could easily benchmark the quality of code then models would be trained on these benchmarks/metrics.
loveparade··on Astra for Coding: Why Are We Doing This Again?
I have been quite disappointed with Astra. I switched over a week ago and I didn't notice a massive difference compared to Sol at first, but I figured I'd use it anyway because it surely can't be worse. Then I saw the bill, it's burning my subscription 10x faster than Sol for essentially no benefit. Not only is it more expensive per token, it also seems less token efficient. And not obviously any better. I'm back to a combination of Sol + Claude.

I also use Astra at work where I don't need to worry about token cost on highest effort and same story there, I don't see any difference in everyday work other than it being more expensive. Of course my experience is highly subjective, but with how meaningless/overfit the benchmarks are, subjective experiences are imo what matters.

loveparade··on I were 17, I'd learn how to build LLMs from scratch
Horrible advice. This may have been good advice 10 years ago, but not today. There are no positions for people who "kind of understand how toy LLMs work" because so many engineers do these days. Most of the real LLM optimization work is at the edge of research and highly proprietary and not something you could ever do without infra that costs millions.

But of course, 10 years ago this wasn't obvious.

loveparade··on Ask HN: Anyone set up ways to easily obtain and read transcripts from Ted, YT?
I built my own pipeline for this because in my experience the YouTube auto transcripts are quite bad.

I download the raw audio track with yt-dlp, give it to qwen asr for raw transcription, then DeepSeek flash for transcription cleanup, formatting, corrections with web search enabled, etc. I use openrouter to call the models. It's a few cents per video (mostly the asr model at ~12 cents per hour) and quality is great. You could probably use a local asr model if you want to save money, I just don't bother because it's so cheap already.

That only makes sense for videos that don't have official (not auto-generated) transcripts of course. If there are official transcripts that are good you can just get them directly with yt-dlp.

loveparade··on OpenAI launches ChatGPT desktop app for Linux
You can do remote control / handoff with it, i.e. start on desktop and move to mobile. doesn't work with the cli
loveparade··on Herdr is joining Y Combinator. The runtime stays open
I don't think it's about YC specifically, more about VC-driven enshittification of open source software in general.
loveparade··on Herdr is joining Y Combinator. The runtime stays open
Oh no, I was using it. What's a good replacement? Guess I'll go back to tmux.
loveparade··on The Productivity Mirage
> And while the agent works, I continue taking my notes of what I'm doing, what's next, what the design/architecture needs to evolve to do and so on.

That is still context switching for me. I do the same. While the agent works, which may be 10 minutes, I start planning follow up tasks, etc. But then eventually I still need to come back to the original task to review the agents work.

I don't switch across projects usually. But I can never get into a flow state like that. But I also don't want to sit there for 10 minutes doing nothing

loveparade··on The Productivity Mirage
Exactly. It matters that you enjoy working with your tools. Even if they don't make you 10x more productive, focusing on what you're working on and enjoying the process is the most important part.

Especially in the age of LLMs I think a lot of us hate the current tools that force you to context switch between N agents and terminals. Constant context switching takes the joy out of work and prevents you from getting into a flow state. I hope someone figures out the solution.

loveparade··on Superlogical
I'm sorry but I am still confused. What specifically does herdr give me over tmux? "It is designed for agents" is just marketing speech, it means nothing. Ok, it has mouse support, fine, I don't care about that one but I can see how it's useful to some people. That has nothing to do with agents though. zellij also has a better user experience than tmux, so you could just use that or any of the other dozen multiplexers.

I understand it has the agent pane on the left that tells you what is running but... that's it?

loveparade··on Superlogical
I don't understand herdr, can you explain it to me? I've tried it, but I don't understand what it gives me over tmux other than the agent sidebar. But people seem excited about it so I feel like I am missing something.
loveparade··on PGSimCity - How PostgreSQL Works
I don't know what I am looking at but it is fabulous.
loveparade··on The gauge broke: devs felt 20% faster with AI, measured 19% slower
Fair point, I was more trying to make a statement about the amount of training data available, not the "difficulty" of the task. I just used Tailwind as an example because it is so ubiquitous with so much training data for LLMs to learn from, while any niche application doesn't have that.
loveparade··on The gauge broke: devs felt 20% faster with AI, measured 19% slower
Used by Anthropic to sell tokens
loveparade··on The gauge broke: devs felt 20% faster with AI, measured 19% slower (2025)
These studies are meaningless because speedup is heavily dependent on the kind of work you're doing. No doubt that you can do mechanical refactors 100x faster with AI, and also no doubt that using AI will be slower for tasks where it's less about writing code and more about context/world knowledge or building understanding. Averaging across these tasks doesn't make sense because everyone's work consists of a different distribution of tasks.

A frontend dev doing tailwind integration for his day job is gonna see very different speedups than someone working in a niche scientific codebase. Taking the average makes about as much sense as taking the average of the speedup from calculators for a mathematician, a farmer, and an elementary school student.

loveparade··on Ask HN: How often do you code the expected way instead of a better one?
Senior people get away with it because they understand the impact of their changes since they are intimately familiar with all the systems. So they know that their crappy shortcut doesn't break anything.

A junior employee doesn't have that knowledge, so they are expected the follow rules to ensure that they don't inadvertently break something.

loveparade··on Setting up an AI-native organization
ai generated slop
loveparade··on The sigmoids won't save you
> If you used the same architecture as GPT2 today you're in for a bad time training a new frontier model. It's only because we have dozens of breakthroughs

What exactly are these dozens of breakthroughs? Most frontier models architectures today still look very much like GPT2 at their core. There were various of improvements like instructgpt, finetuning techniques, efficiency improvements with kv caches, faster attention, lora, better tokenizers, etc. Most of these are for making things run faster. The biggest differentiator has probably been data curation and post-training data and the ability to fit more into the model. But I think we had few breakthroughs that would fall into the category of different technologies.

loveparade··on Vibe Coding Will Break Your Company
The more AI-generated AI bad stories we get the more likely LLMs will produce more!
← PreviousPage 2 of 13Next →