josu

> The above is a software engineering problem. Reimplementing a JSON parser using Opus is not fun nor useful, so that should not be used as a metric.

I've also built a bitorrent implementation from the specs in rust where I'm keeping the binary under 1MB. It supports all active and accepted BEPs: https://www.bittorrent.org/beps/bep_0000.html

Again, I literally don't know how to write a hello world in rust.

I also vibe coded a trading system that is connected to 6 trading venues. This was a fun weekend project but it ended up making +20k of pure arbitrage with just 10k of working capital. I'm not sure this proves my point, because while I don't consider myself a programmer, I did use Python, a language that I'm somewhat familiar with.

So yeah, I get what you are saying, but I don't agree. I used highload as an example, because it is an objective way of showing that a combination of LLM/agents with some guidance (from someone with no prior experience in this type of high performing architecture) was able to beat all human software developers that have taken these challenges.

You are looking at this wrong. Creating a json parser is trivial. The thing is that my one-shot attempt was 10x slower than my final solution.

Creating a parser for this challenge that is 10x more efficient than a simple approach does require deep understanding of what you are doing. It requires optimizing the hot loop (among other things) that 90-95% of software developers wouldn't know how to do. It requires deep understanding of the AVX2 architecture.

Here you can read more about these challenges: https://blog.mattstuchlik.com/2024/07/12/summing-integers-fa...

I know what's like running a business, and building complex systems. That's not the point.

I used highload as an example because it seems like an objective rebuttal to the claim that "but it can't tackle those complex problems by itself."

And regarding this:

"Claude is very useful but it's not yet anywhere near as good as a human software developer. Like an excitable puppy it needs to be kept on a short leash"

Again, a combination of LLM/agents with some guidance (from someone with no prior experience in this type of high performing architecture) was able to beat all human software developers that have taken these challenges.

Lol, the problem is not finding a solution, the problem is solving it in the most efficient way.

If you think you can beat an LLM, the leaderboard is right there.

>So my verdict is that it's great for code analysis, and it's fantastic for injecting some book knowledge on complex topics into your programming, but it can't tackle those complex problems by itself.

I don't think you've seen the full potential. I'm currently #1 on 5 different very complex computer engineering problems, and I can't even write a "hello world" in rust or cpp. You no longer need to know how to write code, you just need to understand the task at a high level and nudge the agents in the right direction. The game has changed.

- https://highload.fun/tasks/3/leaderboard

- https://highload.fun/tasks/12/leaderboard

- https://highload.fun/tasks/15/leaderboard

- https://highload.fun/tasks/18/leaderboard

- https://highload.fun/tasks/24/leaderboard

I was able to lead these two competitions using LLM agents, with no prior rust or c++ knowledge. They both have real world applications.

- https://highload.fun/tasks/15/leaderboard

- https://highload.fun/tasks/24/leaderboard

In both cases my score showed other players that there were better solutions and pushed them to improve their scores as well.

This reads like a hit piece. Cars crash, that obvious. Are Robotaxis crashing above or below human-driver rates?

I know what 99% of the people in HN are thinking while reading this post, and I agree, so I would like to hear the contrarian views:

Who is this useful for? What is the strategy behind this?

Read the article, the author is definitely in favor of using git.

Simple is good.

The monetary base expanded (aka "they printed a ton of money") between 2020-2022, so there were 2 options: the monetary base had to contract again, or the prices needed to adjust.

SPF is a Sun Protection Factor, meaning it multiplies the time it takes for your skin to burn. For example, if very light skin normally burns in about 10 minutes, SPF 20 stretches that to ~200 minutes, which is already over 3 hours. Since dermatologists recommend reapplying every 2 hours regardless, going beyond SPF 30–50 (which blocks ~97–98% of UVB) doesn’t add much practical benefit. Even for very fair skin, correct application and reapplication are far more important than chasing SPF 100.

Use Claudia to onboard the first users, gain some traction, and when the inevitable C&D letter comes change the name.

He may have burned the keys, not the coins. The process of burning the coins is by sending them to an address such as: 1111111111111111111114oLvT2

Airplanes. Some airlines offer 30 minutes of free wifi or something.

Ha, thanks for making the most of a bad comment.

Sorry about my comment, it didn't add anything to the conversation.

This reads as if it were written by a LLM.

>some people have to suffer because other people don't behave nicely

It's self fulfilling though. Some people won't behave nicely if a game comes with Denuvo.

"Although it’s typically not viewed as a partisan board, the Biden administration had installed the entire committee."

Ha! You must have never dealt with European universities.

> What coinbase needs are IRL offices where you can go and do things like account recovery, and where people trying to steal money can be caught and prosecuted

Is this satire?

We already went through this with crypto mining; the oceans didn't boil, the world didn't end.

I'm looking for it on the mobile app and I can't find it.

Yeah, same in Spanish.

An important detail that the article has somehow left out. Texcoco, one of Mexico City's main lakes is salty. The Aztecs built a system of dams to separate the salty waters of the lake from the rain water of the effluents.

I wasn't expecting that steampunk look.

This is horrible.

The original is a Twitter thread, not a serious article.

They hold 6k BTC, around 600M USD. So just a bit over 2x.