پن کیا گیا ٹویٹ
Kamakura
9.1K posts
Kamakura
@KamakuraCrypto
Vibecoder / Trader Not stopping until my port is 7 figs. Documenting my journey here to prove everyone wrong.
Solana شامل ہوئے Ocak 2025
2.5K فالونگ4.4K فالوورز
oh boy
a whole new userbase about to get onboarded
Thariq@trq212
We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord. Use this to message Claude Code directly from your phone.
English
@glitch_ @NousResearch please i need private access priority to the repo now thanks
English
hermes agent by @NousResearch + my swarm + qmd = wild performance
hermes on qwen with shared qmd outperforming stand alone opus 4.6 for me...
English
holy shit
opensource models are catching up to closed source
the whole AI space is shifting
every time I log into this app it feels like I’m 2 years behind lol
the sheer amount of competition in the AI field is crazy, everybody wants to be the best.
It’s time to invest in datacenters
and set up my 10x3090 LLM rig 👀
MiniMax (official)@MiniMax_AI
English
long live CLI and Skills
MCP’s were a mistake
read this if you want to level up your claude game
Thariq@trq212
English
BREAKING: Anthropic report shows Israel ranks higher than any country in per-capita Claude usage.
English
NOOOOOOOOOOO
please @AnthropicAI fix @claudeai
maybe i gotta set up that 10x3090's set up after all
English
what do you guys use for executing / writing code?
For planning / researching I use:
Opus 4.6
GPT 5.4
GLM 5
but after they all cross review and make the perfect plan
should I use a non reasoning model to execute the plan?
or keep a reasoning model for execution?
lmk please
English
this is why ram prices are so crazy high rn
Crazy Moments@Crazymoments01
Which bed would you sleep in? 🤔
English
@WellzOnSol $800, found another one for $650 that i'm gonna pick up soon prolly.
Need a new pc/server set up for this
English
Setting up my first 3090!
the learning curve begins now 🫡
already been building my orchestrator
now it's time for the fun part 👀
How many more should I buy?
If I buy 5-10 wouldn't colocation in a DC be better?
Sudo su@sudoingX
let me get you started in local AI and bring you to the edge. if you have a GPU or thinking about diving into the local LLM rabbit hole, first thing you do before any setup is join x/LocalLLaMA. this is the community that will help you at every step. post your issue and we will direct you, debug with you, and save you hours of work. once you're in, follow these three: @TheAhmadOsman the oracle. this is where you consume the latest edges in infrastructure and AI. if something dropped you hear it from him first. his content alone will keep you ahead of most. @0xsero one man army when it comes to model compression, novel quantization research, new tools and tricks that make your local setup better. you will learn, experiment, and discover things you didn't know existed. @Teknium maker of Hermes Agent, the agent i use every day from @NousResearch. from Teknium you don't just stay at the frontier, you get your hands on the tools before everyone else. this is where things are headed. if you follow me follow these three and join the community. you will be ahead of most people in this space. if you run into wrong configs, stuck debugging hardware, or can't get a model to load, post there so we can help. get started with local AI now. not only understand the stack but own your cognition. don't pay openai fees on top of giving them your prompts, your research, and your most valuable thinking to be monitored and metered. buy a GPU and build your own token factory.
English
going to start picking up more on this
got something in the pipeline almost ready to be released
hopefully it will make my life easier when generating code
stay tuned
Brian Armstrong@brian_armstrong
Operating in stealth mode is almost always a mistake. Talk publicly about what you're building. You’ll build momentum, get real feedback, and someone will reach out with the other half of your idea you didn’t realize you were missing.
English
i wonder what the ETH audience has to say about this
Luminaries@luminaries
the birth of Solana
English
@peer_rich i'm literally contemplating the same thing. maybe buy 10x 3090's ?
English
Kamakura ری ٹویٹ کیا
sometimes I scroll on X and I wonder
how does one absorb all the information
sift AI slop through yet more AI
track every open source / LLM revelations
without your own context window flooding
we are but human LLM's
we forged the machines to transcend our limits
only to mirror them perfectly
English