Interacting with LLMs like Copilot has been most interesting for me when I treat it like a rubber duck.
I will have a conversation with the agent. I will present it with a context, an observed behavior, and a question... often tinged with frustration.
What I get out of this interaction at the end of it is usually a revised context that leads me figure out a better outcome. The AI doesn't give me the outcome. It gives me alternative contexts.
On the other hand, when I just have AI write code for me, I lose my mental model of the project and ultimately just feel like I'm delaying some kind of execution.
One of his electro-mechanical units was on display in Victoria, Australia. Most amazing assemblage, you can sort-of get the idea from things.
I read online that at his end, Baird was proposing a TV scan-rate we'd class as HD quality, which lost out to a 405 line standard (which proceeded 625/colour)
There is also a quality of persistence in his approach to things, he was the kind of inventor who doesn't stop inventing.
Mm. Part of GW's modern success is that roughly a decade ago they decided to push third parties to create a ton of Warhammer-branded experiences. There's even a Warhammer movie in the works, if I remember right. That would never have been possible before that "please use our IP" shift.
For me, over the last thirty years I've amassed and then sold a big Warhammer collection multiple times. It finally dawned on me a few years ago that I don't actually like playing the game (I'm really bad at it), but I loved the miniatures. No one else really made the same style of minis. About when we hit the "you can just 3D print an entire army" time period is when I stopped liking even that part of the hobby, and exited for good.
Ah that makes complete sense. So they had to go with AOS for IP reasons which allowed them to have more control of videogames, comic, future movies etc. That makes sense.
Good to know your views on playing the game! I have similar feelings (but I stopped playing with the armies side when I was a teenager).
Yeah that's where I started out in 2021. Been at it for almost 5 years now, last three of which full time. I'm indexing about 1.1 billion documents now off a single server.
Hard part is doing it at any sort of scale and producing useful results. It's easy to build something that indexes a few million documents. Pushing into billions is a bigger challenge, as you start needing a lot of increasingly intricate bespoke solutions.
(... though it operates a bit sub-optimally now as I'm using a ton of CPU cores to migrate the index to use postings lists compression, will take about 4-5 days I think).
I'm mostly living off grants and donations at this point, but the plan down the line is to polish it up well enough to make some money off providing an API like the one Google is making it a hassle to access with this change :-)
Might find YaCy interesting. It’s meant to be a decentralised search engine where users scrape the internet and can search other users indexes in a kind of torrent like way.
I found it didn’t really work as a real search engine but it was interesting.
Well you'll get blocked some places but it's not too big of a deal. If you're running an above board operation, you can surprisingly often successfully just email the admin explaining what you're doing, and ask to be unblocked.
Every gas station, grocery store, convenience store, pharmacy, urgent care, every bank, every tech company, every computer manufacturer, most food production companies, most farms, every resource extraction company, every manufacturing company.
Any health care organization - from your list, pharmacies and urgent care - that is profit-driven is not holding health as top priority.
If an organization that should be focused on making people healthy is instead focused on how many currency units it can extract from other entities, there is (as they say) a misalignment of priorities.
Very cool. The one thing that prevents me from trying this out as a potential note-taking daily driver is the lack of support for LaTeX.
I recently switched from Obsidian to Zettlr due to some rendering and performance issues on Linux, and it's been a great experience. However, I always like to see new entrants in the arena.
LaTeX support is a reasonable request! It's not on the immediate roadmap, but here's my thinking:
Options considered:
- KaTeX/MathJax-style rendering (would need a Rust math renderer or JS bridge)
- Typst integration (Rust-native, modern alternative to LaTeX)
- External tool pipeline (render via pandoc/LaTeX CLI)
Typst is interesting since it's also Rust-based and simpler than full LaTeX. Would inline math ($x^2$) and display math ($$...$$) cover your use case, or do you need full document features?
Added to the roadmap consideration list. Thanks for the feedback!
Good to know! Inline + display math is a more tractable scope. Typst or a Rust KaTeX port could handle that without needing full LaTeX. Added to the consideration list with that clarification.
Agreed. Having an open-source alternative to (the otherwise excellent) Typora would be fantastic; as far as I can tell the main feature Ferrite is currently lacking to be used for most (all?) applications where I use Typora is a way to easily write and render maths formula. (As far as I am concerned, support for TeX math would be ideal due to wide support from the existing ecosystem; but Typst would work too.)
Thanks! TeX math support ($...$ and $$...$$) is planned for v0.4.0. We're going pure Rust (no JS runtimes), targeting common LaTeX syntax. See the planning doc on github (docs folder) for details.
I will have a conversation with the agent. I will present it with a context, an observed behavior, and a question... often tinged with frustration.
What I get out of this interaction at the end of it is usually a revised context that leads me figure out a better outcome. The AI doesn't give me the outcome. It gives me alternative contexts.
On the other hand, when I just have AI write code for me, I lose my mental model of the project and ultimately just feel like I'm delaying some kind of execution.
reply