aaronscott

I think their solution is still sub-optimal. Ideally a secondary agent would pre-process the prompt, select relevant information from the catalogue, then pass that on to the primary agent.

This way the primary agent only has relevant information in their context to make decisions and take actions.

Context management is still under valued imo.

Something that others haven’t mentioned is that you can flash an open source OS/reader software (Crosspoint, among others) so you can change the UI and experience for your preferences. I like having an e-reader that lets me modify how it works.

I replaced the battery on my kindle 4 not that long ago. It had the best UX for extended reading when compared to newer kindles.

The biggest downside was not having a frontlit display.

I recently switch to an xteink x4, and found that several others in that community migrated from kindle 4s as well. So there are still some number of users in the world that value the device.

Same here, I quite enjoy it. Plus there is open source software available, such as crosspoint. It’s easy to flash and an opus call away to change the behavior if you want something to work differently.

This is awesome!

Thanks for explaining the reasoning behind implementing your own version instead of using Al Dente. The straightforward UI is really appealing.

I paid for an Al Dente license long ago and have been very happy with it, sail mode and temperature sensitive charging are great features (although I’m not sure how big of an impact sail mode makes).

It’s great to see alternatives available though. Having command line access is really cool.

They have an ultrawide mode available now. Personally I find it very uncomfortable. You have to move your whole head to see the sides, and the vision pro is heavy. Looking off to the side for a length of time is uncomfortable.

It would be nice if the search provider could be configured. I would like to use this with Kagi.

They have a free demo that is fairly extensive. It should give you a good feel for whether the game is worth it to you.

> I like to define my subroutines using a modern language like C++, which goes 47 gigaflops. This means C++ is three orders of a magnitude faster than Python. That's twenty years of progress per Moore's law.

This is great. I love the idea of measuring performance differences in “years of Moore’s law.”

Twenty years puts the delta in an easy to understand framework.

I agree with your observation, although it seems unpopular at the moment. It’s clear the video is slowed down and seeing how his hands respond at the end of his action, it looks like he’s throwing the wheel very quickly.

The tires start moving immediately, so it looks more like a limit in how quickly they change direction. It appears laggy because they don’t finish the movement when he does. They do respond right away when he shifts his arms a little in the middle of the video.

Like others, wanted to say thank you for writing Aider.

I think you've done a fantastic job of covering chat and confirmation use cases with the current features. Comments on here may not reflect the high satisfaction levels of most of your software users :)

Aider helps put into practice the use cases that antirez refers to in their article. Especially as someone get's better at "asking LLMs the right questions" as antirez refers to it.

This is amazing, thanks for sharing it! I’ve been thinking about building something along these lines, so it’s great to see a working model.

I completely agree. A huge business with a singular focus isn’t going to pivot into the music business (or any of the myriad use cases the general public throws at it). And if they did use someone’s info, it’s more likely an unethical employee than a genuine business tactic.

Besides, the parent program uses the API, which allows opting out of training or retaining that data.

During a job interview I was asked to teach something off the cuff. There were two interviewers in the meeting, so I decided to show the difference that a good mic with good placement can have on call quality. Switched from my nice mic that was one shaka[0] away, to the laptop mic that was about two arm lengths away (maybe 8 shaka’s). They were shocked at the difference and one asked “is that what I sound like right now?”

I went on to discuss how sound intensity is inverse to the square of the distance, so double the mic distance and it’s 1/4 the intensity. So the distant mic was picking up ~1/64th the volume. When there isn’t much of a difference between my voice and room echoes it becomes hard to listen to.

They started a discussion about how much it would cost to outfit everyone with external mics after that haha. For anyone wondering, even a cheap lapel or broadcast mic that’s close to your face will sound much better than a distant laptop, due to the comparative volume of your voice verses the environment.

[0] One shaka, or one “hell yeah” is a unit of measure an audio engineer shared with me once. Extend your thumb and pinky, and get your mic about that far from your mouth for good sound. One or two shaka’s is generally very good.