raajg

This approach is interesting. Does this mean that I can limit the the words to the ones I actually use and build a tiny model that finds the closest match to only those words I use in 99% of my conversations?

not that straightforward for agents. They're basically competing with https://brave.com/search/api/, https://www.tavily.com/ etc.

Is it just me, or others are also weirded out with that website being all images including all the text

Great to see the interest in RCT . also https://labs.ramp.com/rct

THIS!

Couldn't stop reading! It's been an embarrassingly long amount of time since I got hooked to something like this. Keep going!

I'm currently reading 'There Is No Antimemetics Division' and this news item reminds me of that. Also, 1984, in which the government actively establishes false narratives as actual history and do it so many times that it's impossible to remember what really happened.

the post on BoopSnoop was very impactful for me too! As a software engineer, it's drilled into your brain that you have to think about high scalability and user facing products. I used to have a lot of ideas, but the first instinct was always to build a paid user facing product. None ever got built. But after reading that post a few years ago, my mindset was completely flipped. Since then I've built umpteen tools, services, macOS menubar apps, tail scale services .. just for myself. And I love it!

Don't think it's 'true' plain text. HTML/CSS rendering 'like' plain text.

Still beautiful though!

Telegram -> 1 Group/agent -> OpenClaw running on an old laptop

Using it for journaling and capturing ideas. Previous workflow as iPhone Memos. Now it's

voice message -> openclaw -> transcribe using parakeet -> git repo

I've been dabbling with STT quite a bit and built my own tool using Deepgram. But just tried Handy and it's SO FREAKING FAST! Love it.

This was recently shared on HN: https://visualrambling.space/dithering-part-1/

For anyone interested in seeing how dithering can be pushed to the limits, play 'Return of the Obra Dinn'. Dithering will always remind you of this game after that.

- https://visualrambling.space/dithering-part-1

- https://store.steampowered.com/app/653530/Return_of_the_Obra...

Time to set up Pi-Hole on my Rapsberry Pi 4

https://pi-hole.net/

I think that local search, retrieval, and filing will become much easier with LLMs.

There are already tools and products in the market that allow you to rename and organize files. I believe this is the future.

We have developed various systems over decades, but I anticipate with LLMs it'll be so easy to file and retrieve things that we won't even have to think about it.

42

Ref: google.com/search?q=answer+to+life+the+universe+and+everything

More than a Roman character, Catalina reminded me of "Howard Roark" from The Fountainhead. It's been at least a decade since I last read it, but I thought the movie was quite influenced by that book.

Been using the LLM cli by simonw and love it.

https://github.com/simonw/llm

https://llm.datasette.io/en/stable/

Pro tip: Use $pbpaste to inject clipboard contents in a prompt

I just 'star' the repos

looks promising, but after looking at the website I'm yearning to learn more about it! How does it compare to alternatives? What's the performance like? There isn't enough to push me to stop using ChatGPT and use this instead. Offline is good, but to get users at scale there has to be a compelling reason to shift. I don't think that offline capabilities are going to be enough to get significant number of users.

Another tip, I try out a new chat interface to LLMs almost every week and they're free to use initially. There isn't a compelling reason for me to spend $10 from the get to for a use case that I'm not sure about yet.

Been 4 months and I'm pretty happy with the following setup: PiHole + RaspberryPi + Tailscale

With Pihole running on a tailnet all my devices use it by default as long as they're on the same tailnet. That way I have seamless ad-blocking even when I'm on cellular data or my friends' wifi networks.

Recently bought a Raspberry Pi 4, spun it up and installed various things on Ubuntu running from an SD Card. I now have a server running in my room again after probably a decade!

I'm not 16. :p

On my 14in Macbook Pro I CANNOT TELL THE DIFFERENCE AT ALL

Manual coffee grinder + French press

For someone unexperienced with ESP32 but wanting to dip your toes, I'd highly recommend M5Stack - https://m5stack.com/ . No affiliation whatsoever, but I started playing with some basic boards last year for the first time and the the tiny devices they build have so many different sensors, transmitters, etc that you can start with a lot of early experiments just using a single device and a USB-C cable.

Pretty barebones but working web servers are possible. Example: https://randomnerdtutorials.com/esp32-web-server-arduino-ide...

I read this article last year and found it to be a pretty good in-depth analysis of how Evernote had a lot of potential but lost in so many ways:

- [Why Evernote Failed to Realize Its Potential |The Full History](https://nira.com/evernote-history)

oh wow, I would have never imagined that 'that' would be preventing me from running llama + llava! Confirming that I have Crowdstrike running too.

Yep, same issue. and the error message is unhelpful

I don't see how 'Tesla' is not top of the list here. For the 'Trouble Areas' I suspected they're normalizing over the 'length of ownership' which would bias the scores towards older car companies.