Just a fun tiny project. Got tired of the bulky ticker widgets that clog my potato laptop resources, so I made a ticker that sits right in your taskbar with live prices. ~5 MB of RAM. More features soon :>
Made with love by Maria w/ Claude Opus 5.5
https://t.co/nhvdZghFc3
Windows only, needs the Discord desktop app.
Yozora is not affiliated with or endorsed by Discord, Spotify, Apple, or Google.
Feel free to reply here for fixes and suggestions you might want!
Another tiny one. Wanted Discord to show what I'm listening to without another app hogging my laptop, so I made Yozora. Spotify, Apple Music, YouTube Music and YouTube, straight to your status. Free, open source and lightweight.
Made with love by Maria
https://t.co/ydgYqpZd9W
@landontgreen honestly glm 5.3 flash’s code is still really robust but for automation and other use like vision, agent swarms, etc. the latest ds checkpoint is the best open source model for it atm
Immediate thoughts on @bot after a day of use and setting things up:
Grok models are obviously behind OpenAI and Anthropic if accounting for raw intelligence, but jeez, it's seriously very personalized and comfortable to talk to.
It's what Google wishes Gemini was, and it's just a billion times more convenient and has relatively okay usage on the unified plan. The price tag is seriously worth it even if Grok by itself sucks. Just use up all your usage on @bot.
Huge blunder by OpenAI to lock this up behind their 100$ plan whose limits continue to get chopped day after day. Seems they're too focused on their "high-end" users by just admitting they lose the 20-30$ tier to Anthropic (for cheap power use) and xSI (for those needing automation outside of simply coding).
It does make me feel bad about how this space is going to end up obliterating a huge part of the virtual assistant/secretary job sector. It won't completely disappear, but I'm pretty sure by now that the most sought after VAs are those who already do so much work with AI workflows that they're basically all that's sought for at the moment.
Just a fun tiny project. Got tired of the bulky ticker widgets that clog my potato laptop resources, so I made a ticker that sits right in your taskbar with live prices. ~5 MB of RAM. More features soon :>
Made with love by Maria w/ Claude Opus 5.5
https://t.co/nhvdZghFc3
curious how it compares to the previous checkpoint. found the space bunny checkpoint to be good for long tasks but quality wise really behind ds 4.1. will try
MiniMax M3.1 Flash: Space Performance + Bunny Speed
🚀🐰 Yes, Space Bunny - which has topped global leaderboards with 200T+ tokens - was an earlier version of M3.1 Flash.
💰Redefining the performance economics of agentic AI. M3.1 Flash achieves frontier-level intelligence across key tasks such as Cowork (Automation-Bench: 62%; ALE: 30%), Coding (DeepSWE: 74%) and Visual Reasoning (BabyVision: 91%), at 1/3 the cost of M3 and 3x the speed.
API pricing (flat rate): $0.15 / $0.60 per 1M input/output tokens, with cache reads at $0.015 / 1M tokens.
Model weights will arrive on Oct 23.
API: https://t.co/fHRdSV73Hr
M Plan: https://t.co/XfJWSyauda
MiniMax Code for desktop: https://t.co/SGmLTI2HQm
@Sean_Hyman@Barchart the fiat floor is rising far faster than the cliff metals are falling from and it will be too late before many people realize that the "bubble" is a speculative has-been
@rodydavis would like to thank you for letting us paid pro subs being able to have argon usage on agy, been pretty much letting argon figure out which qol aspects i can take advantage of wrt limited resources, as well as cleaning up code bloat from older repos.