It seems I can post in Chinese. Because I don't have an ID card, I can't have a phone number, and therefore can't register a stable email address, which means I can't register on content platforms or publish content. Hotmail frequently blocks my email account because I don't have a stable IP address, so my Mastodon account can't be used long-term. I hope this is a place where I can publish content consistently.
So happy to be one of the first people to reply in a long time, my friend! Have a good weekend! Please forgive my little mistake, I'm replying using a translation. We all know things aren't always great.
I am sure pretty much everything that isnโt criminal, abusive, or illegal. I know those definitions vary from country to country. Just be a good human, and you should be OK.
So, I've been using this harness for a week and a half now, and what's interesting to me is that it brings a lot of things that I'd already built for myself in Pi. I built a little email system for agents to communicate, a memory system to do this "continual harness" thing of self-improvement. I know I'll move on to another harness in the future, so I'm trying to treat this like I do laptops now, and think about portability in the things I build or customize.
I've been curious about the reasoning for prices too. Like, there has to be research behind it... But I agree it is far easier to buy four 2.5โฌ services than one for 5
A credit union wants to get their own data out of a vendor's online system. Vendor wants $160,000. I wrote a #pythonnotesfollow script with #Playwrightnotesfollow to download the data just as though a user would. It's going to run for about 6 weeks to download around 250k records and 70GB of images.
you could split to buckets like alphanumerically and parallelize it if you don't want to wait that long. Probably need to launch a few instances but still cheaper lol.
The slowness is intentional. I wanted to make it look more like a user doing it than a script so it doesn't set off any alarms. I have it waiting from 1 to 3 seconds between clicks to slow it down. :-) So far so good!
In China, I am practically independent of the government; I don't participate in any activities based on my status, such as formal work or online shopping. I've paid a heavy price for this; my choices have been severely limited, and my mobility has been significantly impaired. I can only access the internet through limited free Wi-Fi.
@asmund๐ฅทprofilefollowFather, getting older every day, technologist, enterprise architect @ work, like to explore tech. Like to keep it simple and work in the shell, write in vim, prefer Debian if I have the choice. Plays saxophone and clarinet. Enjoy motorcycle riding, photography, hiking. Christian.wrote:
I'm looking for a way to manage my bookmarks easily on desktop and Android. Anyone have any experience with software like that? It'd be nice to be able to tag or categorize pages, and maybe to keep local mirrors for certain ones. I'm open to self-hosting.
Thanks for reading!
I've stopped managing bookmarks after del.icio.us died - now i just hit the browser star but they seem to disappear and never visit them again, apart from the most recent. The situation sucks really. I'm also interested in a good solution.
@javisrike๐งโ๐profilefollowSoftware โข maker projects โข music โข DIY
Mostly figuring things out as I go.wrote:
ai coding feels like it has reached diminishing returns for me. luna is my default orchestrator, routing work by complexity. in practice, usage lands around 16% luna, 48% sol, 30% astra, and 6% terra. at this point, i care less about each new frontier release. the system already finds a capable model for the job. the frontier is moving beyond my day-to-day work, so iโm happy to settle into predictable models for a while.
#ainotesfollow#programmingnotesfollow#agentnotesfollow#technotesfollow
Iโve found the same, albeit with Opus โ itโs hard to find uses for Fable. I donโt need a model that works for longer or works on harder problems, I need one that consistently produces simple, easy to understand, code; which at this point none of them do.
I've been there since I settled on a combination of GLM, DeepSeek and MiMo for planning, implementation, and verification flows.
I'm a lot more interested at this point in having cheaper models that can consistently do the work I need. It's been a while that I hanven't noticed any improvement when I try new frontier models. I only notice they are very expensive.
same here, for almost an year. At this point, I could easily live with models that were released 6-12 months ago and continue doing so.
also possibly the reason why the current focus has been around agentic workflows or agentic anything, than the model capabilities.
Coding probably yeah, but still they are bad at generating novel information, new ideas and such. Theyโre also not very good at seeing the bigger picture, they will narrowly perform the task but theyโre not taking into account future revisions, which ends up in refactor after refactor in order to move forward.