thomas536

+1 to using MUD as a learning tool. Learn about agent loops, prompting iteration, etc.

I vibe coded a few room proof of concept MUD. I added a tools called `oracle` (aka me) that it could ask me questions to help along its way; and the ability to interject in the loop with a hint. Just as I might want an llm to stop to ask me for help instead of plodding along...

Interesting to limit the number of turns and see where it gets stuck or how quickly it can finish.

I refuse to believe this is the only way to make it cheaper. Standardization and modular components could help. Might not be cheap enough. But surely we can be more imaginative!

My intuition is that a small radio from the 80s is sufficient. Has relatively small size and passive speaker. Small passive speaker and small enclosure are cheap aka not 100+ USD. A tonie box sounds fine. Can I diy reproduce one similar at low cost (less than buying 50 USD)?

I've spent countless hours searching for a small, good quality passive speaker. In a roughly 4 inch cube size. That comes with an good (acoustically) box/enclosure. Plenty exist in various forms (kits) but I never know if they sound as good as even laptop or phone speakers. Which is a low bar, but still can't find good reviews.

I wonder where the water is coming from for these sites

Did they publish that fact anywhere?

Is anyone using this on Android?

Perhaps? I remember the article arguing more comprehensively why a different order would be beneficial, but maybe I am just misremembering

I once read an article about SQL and how reordering the sections of a query would make it more ergonomic for users (iirc things like specifying what you want first and then how to present it last, more like a pipeline). I searched many times over the years but have not been able to find it again.

Re hydration

Do you have any good reading on that link? Searched just now and there's a lot to wade through to find a good article

What's your favorite PTT mic? I'm always on the lookout for great device recommendations!

Ah finally found one! Looks great!

Are there similar relatively simple methods or simd tricks for multi-way merges?

Still looking for a microcontroller that can fit on my wrist [watch-like form factor] with built in microphone, deep sleep, quick wake, and quick push audio to wifi or BLE...

A recently launched pi tablet hits a couple of the requirements but definitely not all

https://www.kickstarter.com/projects/745629624/cutiepi-raspb...

https://twitter.com/TwitterSupport/status/129400382869048524...

I ran across this person's blog, who seems like they have some different slants on publishing that might interesting to you:

https://www.jeffgeerling.com/blog/6-lessons-learned-self-pub...

Sorry to hijack this thread, but too curious if you made any headway from your "Non-cloud voice recognition for home use?" post? Sounded like an interesting use-case.

tia

+1 I appreciate your answer!

(Yeah the exact billing model is fungible/an example to get people to think in terms of actually willing to fork over money.)

Do you mean you might have a specific and relatively small set of videos that you would like searched, but at a much lower price point (e.g. 10k videos at less than $10/year)?

The only public search engine that I'm aware of using common crawl is ChatNoir.

https://groups.google.com/d/msg/common-crawl/3o2dOHpeRxo/H2O...

Most searching (e.g. web, email, torrents) is based on ads, which works because of the utility to a huge number of people. There are many things one might in passing want to be able to search (e.g. quickly finding the location of particular book on your disorganized bookshelf, non-web text content, etc.) but don't have mass appeal to sustain ads revenue. And even many of those wants aren't worth paying a few dollars for let alone the cost of hosting search.

So does anyone in the HN crowd have a search-based itch they're willing to pay to have scratched that's not already handled by existing search products?

I can do this as well (recall where a stray phone is), but don't understand why I notice and remember better than others. Do I remember more "that's out of place" instances, am I more predisposed to prefer things be in a certain place? Not sure.

If people's public bookmarks aren't available online, I'd encourage you to publicly post them somewhere. Even if they aren't useful to you anymore, they are good signal for good content, which I think is worth trying to preserve for future use.

I'll second the recommendation for Kaldi. It's more complicated to get running vs pocketsphinx, but in my experience Kaldi has better accuracy/lower latency in general cases vs pocketsphinx (assuming caveats below).

https://github.com/gooofy/zamia-speech/ has been training good [acoustic] models which are worth looking at (including training with robustness against noise). They've also got lots of code and docker images and documentation.

pocketsphinx isn't actually that bad to use with their latest acoustic models and small vocabularies (so its utility depends on your exact use case). But it's not generally good with far field mics/dsp processed audio, not really good with noise, and in my experiments quite not as fast as Kaldi.

Better/larger language models in my experience make a world of difference (esp in the general vocab case) for improving accuracy for either of kaldi or pocketsphinx. Nobody really seems to talk about this(?), since everyone always uses the news corpus from like the 80s as the default language model.

I haven't really ever gotten the various ~deepspeech systems working, so I can't speak to them.

https://lwn.net/Articles/776435/

Yeah my killer feature is a microphone, which the PineTime doesn't have...

I must be missing something because 6.5 days * $21/day = $136.5

"""

The entire process now took 6.5 days and cost $21/day. Our total cost all said and done was $115!

"""

Pine is working on a watch but by no means will they be eating the market.

https://www.pine64.org/pinetime/

Ah interesting.

There are URL attributes that you can set to make the whole node clickable [1].

Do you need only one link per node or do you want the node's text to be fully blown/rendered html (i.e. multiple links per node)?

[1] https://www.graphviz.org/doc/info/attrs.html#d:URL