Sabitlenmiş Tweet
sparbz
19.9K posts
sparbz
@sparbz
building cool shit. @atf_ai @agentgovinc @agentnative
NYC Katılım Mart 2009
266 Takip Edilen1.7K Takipçiler
claude will kill openclaw, but will it kill what is next?
Claude@claudeai
You can now enable Claude to use your computer to complete tasks. It opens your apps, navigates your browser, fills in spreadsheets—anything you'd do sitting at your desk. Research preview in Claude Cowork and Claude Code, macOS only.
English
Perplexity Computer one-shotted the Terminal worth $30000/yr
ₕₐₘₚₜₒₙ@hamptonism
Perplexity just became the the first Al company to truly go head-to-head with the Bloomberg Terminal... Using Perplexity Computer (with no local setup or single LLM limitation), it was able to build me a terminal with real-time data to analyze $NVDA using Perplexity Finance:
English
@_StanGirard @soloish90 it’s literally designed for you to use your subscription with lmao
English
I was burning $200/day on agent API calls.
Then I realized: I already pay $200/month for Claude Code Max.
So I reverse-engineered its protocol.
Now I spawn agents via REST API, monitor them from a dashboard, and pay nothing extra.
OSS 👇
github.com/The-Vibe-Compa…
English
legality might come with a degree of “safety” but the weed just sucks & therefore is more expensive they’re basically glorified mids.
time to bring back telegram and smoke on that schizo pack
English
unfortunately my first exposure to weed was like top crop (high trichome) and legal weed is just not there. unfortunately, the same goes for carts & pens
princess of the world@fragrancewife
legal weed is not as good as iilegal weed
English
@sparbz Are you generating more than $10M USD a year?
English
Why 3 models when you can use a single one?
huggingface.co/LiquidAI/LFM2.…
kwindla@kwindla
NVIDIA just released a new open source transcription model, Nemotron Speech ASR, designed from the ground up for low-latency use cases like voice agents. Here's a voice agent built with this new model. 24ms transcription finalization and total voice-to-voice inference time under 500ms. This agent actually uses *three* NVIDIA open source models: - Nemotron Speech ASR - Nemotron 3 Nano 30GB in a 4-bit quant (released in December) - A preview checkpoint of the upcoming Magpie text-to-speech model These models are all truly open source: weights, training data, training code, and inference code. This is a big deal! Jensen said in the CES keynote yesterday that he expects open source models to catch up to proprietary models this year in a number of categories. NVIDIA is putting their weight behind making this happen. (As Alan Kay said, the best way to predict the future is to invent it.) The code for this agent is open source too, of course. You can deploy it to production with @modal and @pipecat_ai cloud, or run locally on an @nvidia DGX Spark or RTX 5090.
English
damn gemini just like me fr
armistice@arm1st1ce
gemini 3 pro generated this continuation on the first try. what a model
English
@JakeBrownLive Kazuma Okamoto is intriguing to me but what japanese power hitter came over and had no issue with the move
English
My guess would be the Mets 1st baseman in 2026 will be Yandy Diaz or Kazuma Okamoto.
English
English
There are no words to describe what I am feeling right now, what a huge honor.
Thank you everyone at @arcprize, especially @fchollet, @GregKamradt, @mikeknoop for choosing TRM for the 2025 #ARC Paper Award!
Special thanks to @k_schuerholt for replicating TRM! 🙏
ARC Prize@arcprize
ARC Prize 2025 Paper Award Winners 1st / "Less is More: Recursive Reasoning with Tiny Networks" (TRM) / A. Jolicoeur-Martineau / $50k 2nd / "Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI" (SOAR) / J. Pourcel et al. / $20k 3rd / "ARC-AGI Without Pretraining" / I. Liao et al. / $5k
English
@JasonAponte2103 @Rob_Lowder Oh, she’s out… she’s outtt… what time you want me to bring the bitch back??
English
Per sources, Jauan Jennings told Cleveland Browns defensive lineman Shelby Harris that he would take his mother out to a nice seafood dinner and never call her again.
English
just built a local AI waifu on my two macbooks by using the oss parallax inference library!!! not super smooth yet but parallax is still the easiest way to run llms locally on top of mlx - and no bigco can steal my waifu. still need folks to help her see/hear/draw since mlx has no legit wrapper yet.
i’m running a campaign giving away mac minis + dgx spark. please please share your localhost ai model setup by using parallax (you don't need a gpu to try self-hosting you can just start with an extra macbook you borrowed from your friend like i did) or any fun app built on top of yourself host model to link below.
come build sovereign intelligence with me 🫶
English