Very cool! At least the landing page is amazing! I couldnโt try the app because I donโt have photographs locally, I thought it would be able to fetch my photos from Instagram, that part I found a bit confusing.
Now that you mention it like this, is it that you create the masonry collage so that someone can do a perfect Instagram carousel?
@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.
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!
Dealing with the my first visible issues with migadu dot com
Luckily, most stuff there are secondary and not super important. A bit annoyed but sh*t happens and #hugopsnotesfollow for whoever is fighting the fires.
Why do so many tools have JSON config filesโฝ Commenting why options have been set the way they have is just such a basic thing to want to doโฆ Why do tech people have such an aversion to writing things downโ
TOML is a better format for configuration files IMO, if not for many reasons, primarily because TOML accepts comments.
However, one annoying thing for TOML was the lack of schema, and the reliance on JSON Schema for that. Which I decided to tackle years ago when I started the TOML Schema project. In the past few months I leveraged code agents to take to the finish line and got something compelling: tomlschema.org
Thatโs really cool. I suppose it would allow people to verify their config file is valid without having to pass it to in the intended program, which might be running in production or infeasible to run locally โ very interesting
Exactly! The schema also enables tools to have rich editors to config files without having to know about the config file format upfront. There is an editor for TOML Schema as an example, on the website.
At moms house for the holiday weekend so the kids can see Nana. She has a "premium Plex" account on her tv serving a truly massive amount of content. Allegedly the brother of a long time friend is offering the "service". She says that the service will go down when the host is having outages, so the infra is likely local.
I brought my year this weekend. We are going to dig in to this guys operation. Intuition dictates that there is some hand rolled accounting going on. I'd like to see it.
@fastidiousprofilefollow"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyerswrote:
"My feed" shows two unread messages, but I can't find them, and browsing away from it, and coming back doesn't clear that count. Perhaps sorting (unread at the top) when there unread messages is a good idea @stagasprofilefollowcreative technologist
creator of textlog?
@fastidiousprofilefollow"Beware those that would deny you access to information, for in their heart they dream themselves your master." โ Sid Meyerscontinued:
Under the overarching influence of a single, powerful force, China's open-source models filter out a large amount of content unfavorable to their designs during the pre-training stage, and then incorporate a significant amount of content defending their designs into the data constructed during the SFT stage. A corrective dataset is urgently needed for fine-tuning.
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.