I like to follow them and look for benchmark for each LLM release.

https://x.com/ValsAI/status/2102086608476590432

From my perspective, HTTP requests have been mastered for years (decades?). What's the point of switching libraries? What's so extraordinary about the new HTTP library that makes requests look crap?

I understand that new protocols appear from time to time (like HTTP/2), but that's very rare. And if there are performance differences between two libraries, are they really that huge? Even if they are, 99% of people don't need that boost. What prevents someone from just improving the existing library's performance?

Post from the author

Comments URL: https://news.ycombinator.com/item?id=49348091

Points: 7

# Comments: 2

I don't understand how people can be so out of touch.

Comments URL: https://news.ycombinator.com/item?id=49087752

Points: 16

# Comments: 3

Comments URL: https://news.ycombinator.com/item?id=48835111

Points: 776

# Comments: 1501

The compiler is incredibly helpful because it catches errors and gives clear explanations and the LLM can iterate over it. I’ve also added the elm-review package with the default configuration, which is fantastic for ensuring code quality.

I think they stay for a few months. Maybe they just don't tell their company and the company still think they are working in the same place.

What's the point of a crazy cheap model if it's shit ?

I code most of the time with haiku 4.5 because it's so good. It's cheaper for me than buying a 23€ subscription from Anthropic.

The frontier models have become so good that it's getting almost impossible to notice meaningful differences between them.

Meanwhile, when a smaller / less powerful model releases a new version, the jump in quality is often massive, to the point where we can now use them 100% of the time in many cases.

And since they're also getting dramatically cheaper, it's becoming increasingly compelling to actually run these models in real-life applications.

Haiku 4.5 is already so good it's ok for 80% (95%?) of dev tasks.

I've been frustrated with static site generators that pile on features like tags, themes, plugins, and endless configs just to get a simple blog running. So I built *BoumWave*: a dead-simple CLI tool that converts your Markdown posts into HTML using your own templates. That's it. No bloat, no learning curve—just pure, fast blogging.

*What it does:*

- *Markdown to HTML, done right*: Write posts in Markdown, generate clean HTML with automatic SEO (Open Graph, Twitter Cards, JSON-LD, canonicals).

- *Multilingual from the start*: Native support for multiple languages. Create posts in one command, and it handles the rest.

- *Full template control*: Use your own HTML templates. It auto-inserts posts into your index between `` and ``.

- *Zero config hassle*: One `boumwave.toml` file with everything explained with inline comments. Init, scaffold, write, generate.

Check it out on GitHub: https://github.com/CedricRaison/BoumWave

Comments URL: https://news.ycombinator.com/item?id=45901194

Points: 3

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=45440894

Points: 4

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=45184017

Points: 6

# Comments: 1