The rho coding harness Iโve made has come along way and Iโm constantly trying to evolve it, but whenever I go back to pi itโs startling the difference of what a solid computer science background brings.
there's no fundamental physical limit that prevents silicon from developing taste and judgement, but language is a lossy compression of reality.
taste comes from experience, from the shadowy mass of episodic memory, which swirls and convects at the boundary of consciousness. the ideas recombine into new ones in the nuclear reactor of the hippocampus.
but no matter how imbued with meaning and expertise is a handmade wardrobe we still get our shit from ikea
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.
@davidprofilefollow๐ A lifetime Apple user. Partner says I am pedantic, sarcastic, and cynic. I just want to be me.wrote:
I am a remote worker, and has been for 4 years now. It works great. But the owner of the office I've been renting have sold the building, and the new owner has different visions. I could work from home, but my 3 month daughter is a screamer. I had a great, cheap deal. All alternatives I find is like 3x the price.
I stopped interacting much with social media years ago and am honestly not sure how to do this any moreโฆ but I like the shape of what is starting here.
likewise. Its just nice to have an "even playing field" without any perceived hierarchy or weird material incentives to perform the way you'd be pushed to on regular SM.
Reminds me of the Kiwix offline Wikipedia "nopic" version. (I downloaded that version because it's much smaller than the full version that includes images.)
Images are fine for me, but should be behind a link, or a small thumbnail. Non-animated. Videos too.
But thatโs me. They will most likely have to be hosted elsewhere, while the thumb could be here.
Nah. We are ok with just text.
Yeah, before you know it the feed becomes a collection of memes. Have to click or perhaps a browser extension that you personally see the opengraph/linked image in the feed but it's not inviting people to post them for the feed itself.
@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:
Vรฅr konges livsgjerning gรฅr mot slutten, landet samler seg for รฅ ta farvel med en konge som har vรฆrt samlende og god for landet. Mรฅ Gud velsigne hans minne og hans etterfรธlger. #norgenotesfollow#kongharaldnotesfollow
Our king's life's work is coming to an end, the country comes together to say goodbye to a king who has been unifying and good for the country. May God bless his memory and his successor. #norwaynotesfollow#kongharaldnotesfollow
@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.
