rsolva
rsolva on Hacker News
I have used Prospero for some work today, and I have to say I really like it! I have settled on a combination of Zed, Pi and Paseo so far, but I'm adding Prospero into the mix from now on.
I'm so conflicted about this. I do love being able to create and bring ideas to life at the light of speed. But I also see the unique value in the experience of coding, deeply caring about the craft. Can we have both?
Yeah, this is very common in the Norwegian mountain passes, of which we have many.
To be fair, often you have good ideas, but not enough time. I have had a lot of fun having Qwen3.8 27b running at home, having it explore and implement ideas that was way to ambitious for the time I had available to tinker with Home Assistant and Proxmox. It is an enabler and can also be a good tutor, when used as such. I have learned a lot.
Indeed, that takes some time getting used to! I wonder how well an LLM would OCR those types of handwritten pages. Probably way better and faster than what I can do!
I do think the book was meant to be read by a somewhat wider audience. This could have been his ambitious life's work, but no printer wanted (or knew how to) reproduce it? The dutch in the book is quite readable even today; this is from the introduction text, written as a poem (only rhymes in dutch):
---
To the art-loving pupil
This book was written for pleasure and instruction,
for anyone who doesn’t yet know how to colour from life,
whether prints or drawings, whatever their spirit moves them to,
and who lacks nothing but proper teaching.
Come, just read this book with me; it will spark your enthusiasm,
for in it I will show you, through image and text,
what you must do to give everything, true to life,
its proper colour and character, thoroughly and correctly.
That is why this book is filled with colours,
and beside them you will find how each one is prepared.
I have access to two and will explore this the coming weeks.
Wow, this looks great! Only thing missing is a flatpak :)
I run Qwen3.8 Flash Next on 2x Sparks at $WORK and it has been great! It can run 16 concurrent sessions with decent speed (~30-40 t/s per session) and can hold 8 full 256k contexts in cache. It has turned out to be a great production setup for our company.
I have a half finished repo that sets it all up for production (using systemd, not hacky scripts and one-off docker commands), if someone is interested in this, tell me, and it might give me the push to actually finish up the latest threads and publish it!
Nah, it is just right, nerdy, simple and not a blob of colors. It fits the project!
This! My customers love that they can call and email me to update their websites, not having to remember usernames, passwords and how the publish interface works. Wordpess or static does not really matter in many cases.
MCP is exactly the lipstick we needed to put on our pigs, APIs that is not ours, but open source tools we use internally and also wanted to expose to our agents.
Exactly, in our company, we have built MCPs that simplifies interactions with internal tools we use a lot, which saves time and tokens. Sure, we could let the agent poke and fumble around with a not-so-ideal API too, but it makes sense to formalize it and give the agents quick access to what we want it to fetch 99% of the time.
Keys that needs to be set in about:config
- browser.smartwindow.apiKey
- browser.smartwindow.customEndpoint
- browser.smartwindow.model
Adding my http endpoint (using LAN IP) seems to work, getting around the check in the regular settings.
Found the reason, HTTP-endpoints has to be localhost or 127.0.0.1, if you want to use other endpoints it needs to be HTTPS.
I have this feeling whenever I read my own (no llm) code that I wrote 6 months ago. Sometimes a couple of weeks is enough to feel alienated from my own, well considered code, that I spent a lot of time crafting with love.
That is why I try to make good, high level descriptions of what is going on at several levels of a project. Funny thing is, I just kept on doing this with llms, using AGENTS.md at almost any subdir of a project. It works for me, and it seems to work for the llms too.
I tried adding my own endpoint, but the save button was still greyed out so it did not work. Maybe the feature is not fully implemented yet? In about:config, I could add the endpoint and api key, but not the model name.
Agreed on all points, but you forgot to mentioned that Google pay close to no taxes in Norway (~1%). At the same time, their hyperscaler in Skien alone will, when finished, consume ~5% of total energy production. Put another way, 25% of what households use.
Now Google is planing another hyperscalar in Østfold, and other hyperscalars are being built in rapid succession (about 50 is planned), putting a severe strain on our power transfer net.
Just tried your slack client, it has all the features I need and it is super smooth and lightweight, thanks!
I love this! Hacky recycling of old computer parts, home-cooked fan controllers and a website that is just plain HTML with a stylesheet that is so short I don't even have to scroll to read it all. Just write part 2 already, I want to know what you can squeeze out of those AMD cards <3
I have seen many a model card claim Spark compatibility, but without any proof or instructions. There are vibe-patched images of vLLM that kinda works with NVFP4 models, but I have not seen any support from NVIDIA. Does not seem to be a priority for some reason.
I made a small booking site for a local dutch canal boat, which has a calender function. A simple PHP app. I checked the Apache logs recently, and it had THOUSANDS of claudebot and other AI UserAgents flooding the logs every day, apparently because the scrapers keep hitting the 'next month' button on the calendar in a an infinite loop, all day, everyday!
This is a small booking app without any useful information at all, it surprises me that the AI boots have no discernment about what the are scraping, just wasting their own and other peoples resources. And their own reputation! You would thing they could spare a few tokens on a classifier model to do a quick evaluation of their scraping efforts, but apparently they do not.
Anyway, I have done my best to block these UAs and so far it seems to have improved the situation.
I still have an instance of it running and get email reminders about birthdays, but no, I don't think it has been actively developed for years.
Fatty fish accumulates heavy metales and other unhealthy components and pregnant women in Norway is told to limit the intake. But it has been controversial, the industry is not happy with these recommendations!
This seems like a rare gem in a space swamped with lazily LLM generated summaries. Added to my RSS feed!
I use Kagi's search API with my agents, including their summarizer, and it has been great!
I got hired by a local company exactly for my experience with running linux servers at home and in a semi-professional capacity. They had hired someone with perfect credentials from university with several masters degrees, but they had to let him go after half a year because he did not fit in to their linux environment that has been operating since the 90s. I had no formal education, but many years with tinkering, self-hosting and operating linux machines for a small number of customers, and they could not hire me fast enough. They told me that it is really hard to come by people with this mix of experiences, everything is in the clouds these days.
Exactly! It is so empowering to host my own instance at home and own my own identity online, using GoToSocial.
I do NOT consider the Fediverse and the myriads of implementations of it to be social media, but rather a social web. More like websites with the abilities to communicate and interact in different and interesting ways.
Social media is dead, and has been for a while. Many use it still, but it is not primarily social. The social part was mainly a ploy to get peoples attention and then badly abusing it in ever more creative and sinister ways.