aarvin_roshin

This reminds me of File Explorer's cut behavior. It's a nice idea but the layout shift on paste is disorienting.

Spot on:

> I think as we look forward to the future, more inference will start happening locally for one reason or the other. This brings the distribution story front and center. In order to have more applications running inference locally, we need to make running inference easier.

This makes these projects so much more trustworthy and easier to approach:

> Were any of the words here written using AI? Nope. They came from my mouth or my fingers.

The button on the homepage is hardcoded to this book, which I find extremely strange. Why not choose a random book, and why pick such a confusing quote?

Unrelated to the idea, but this website strangely blocks `Alt+←` and `Alt+→` to cycle through browser history.

Edit: It seems the website overrides the `←` and `→` arrow keys specifically, and using `event.preventDefault()` causes the problem. I think it's good practice to ignore keys with modifiers in such a situation.

The author's original blog post, which goes into some more detail: https://antonz.org/solod

Previously: https://news.ycombinator.com/item?id=48925420

Announcement from Cursor, whose team also trained the model: https://cursor.com/blog/grok-4-5.

Notably:

> Grok 4.5 and Composer 2.5 are two different model weight classes, and we're excited to support both sizes and weights. Composer 2.5 will remain offered, and we will release new models of this size going forward.

I'm most curious about whether OpenAI finally taught its models how to design interfaces. They have been behind the other labs in this area for what feels like ages.

Thoughts[^0] from Theo, who had early access:

> It's a damn good model. Not quite as "smart" as Fable, but it is incredibly capable. Fixed all the problems I had with GPT-5.5.

> It is incredibly determined. Will run for a day without even using a /goal. It understands subagents incredibly well and is great at orchestrating. It's super pleasant in use cases like OpenClaw and Hermes Agent. It knows iOS dev incredibly well.

> It has rough edges too, but FAR fewer than 5.5 did.

> For many things, gpt-5.6-sol will become my obvious defaults.

> It is better about [following instructions] than 5.5 was. Understands intent well and hammers until it gets there. Sometimes a bit too hard.

Also[^1]:

> gpt-5.6-sol is world leading in computer use. It made me use it 100x more. When we lost access to 5.6, I quickly started to go insane without it

[^0]: https://nitter.net/theo/status/2074708892341481755 [^1]: https://nitter.net/theo/status/2074720467395756499