Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Ritual makes inference a native precompile, so reasoning and the action it triggers settle as one operation. Humans don't have gaps between a thought and action, and neither should an agent.

joshsimenhoff's profile picture

Josh (❖,❖)

6,618 subscribers

10,985 Aufrufe • vor 3 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

What is the best video editing agent for short form social? Does it actually work? We watched professional video editors, step by step, as they built short-form social reels in Adobe Premiere Pro. Today we're open-sourcing this preview dataset on Hugging Face, to make AI agents better at editing videos. The data set is 234 annotated steps across 4 computer-use trajectories. Editors narrated their reasoning aloud as they worked, so every step pairs a screenshot with the expert's own thought, a structured action, and executable grounding: >a Premiere MCP tool call, keyboard shortcut, menu path, or coordinate click. >The format follows the AgentNet trajectory schema, extended with a Premiere action taxonomy and multi-path execution. ***That makes it directly usable for computer-use agent SFT, reasoning mid-training, tool-use and function calling, and benchmarking agents against a human expert baseline. Enjoy!
0:13

What is the best video editing agent for short form social? Does it actually work? We watched professional video editors, step by step, as they built short-form social reels in Adobe Premiere Pro. Today we're open-sourcing this preview dataset on Hugging Face, to make AI agents better at editing videos. The data set is 234 annotated steps across 4 computer-use trajectories. Editors narrated their reasoning aloud as they worked, so every step pairs a screenshot with the expert's own thought, a structured action, and executable grounding: >a Premiere MCP tool call, keyboard shortcut, menu path, or coordinate click. >The format follows the AgentNet trajectory schema, extended with a Premiere action taxonomy and multi-path execution. ***That makes it directly usable for computer-use agent SFT, reasoning mid-training, tool-use and function calling, and benchmarking agents against a human expert baseline. Enjoy!

ben

40,140 Aufrufe • vor 2 Monaten

Humans are weird. Two skis, and we act as if we can fly. 🎿 Action 6 caught it all. ⚠️ Professional operation. Do not imitate. 🎥：ficekooo #DJI #OsmoAction6
0:19

Humans are weird. Two skis, and we act as if we can fly. 🎿 Action 6 caught it all. ⚠️ Professional operation. Do not imitate. 🎥：ficekooo #DJI #OsmoAction6

DJI

16,876 Aufrufe • vor 3 Monaten

MolmoAct2 is landing in LeRobot! Ai2's open Action Reasoning Model combines a Molmo2-ER vision-language backbone with a flow-matching continuous action expert to predict robot action chunks from images, language instructions, and proprioceptive state. An open robot foundation model built for real-world control, with strong out-of-the-box performance and easy fine-tuning in LeRobot. Pick-and-place inference running on NVIDIA DGX Spark! Blog: Paper: Thanks to Ai2 Jiafei Duan Haoquan Fang
0:11

MolmoAct2 is landing in LeRobot! Ai2's open Action Reasoning Model combines a Molmo2-ER vision-language backbone with a flow-matching continuous action expert to predict robot action chunks from images, language instructions, and proprioceptive state. An open robot foundation model built for real-world control, with strong out-of-the-box performance and easy fine-tuning in LeRobot. Pick-and-place inference running on NVIDIA DGX Spark! Blog: Paper: Thanks to Ai2 Jiafei Duan Haoquan Fang

LeRobot

25,163 Aufrufe • vor 3 Monaten

How can we responsibly deploy agentic AI robots in real-world environments? As we close the gap between AI reasoning and physical action, developing a new safety framework is key to advancing helpful robots. 🤖
0:13

How can we responsibly deploy agentic AI robots in real-world environments? As we close the gap between AI reasoning and physical action, developing a new safety framework is key to advancing helpful robots. 🤖

Google DeepMind

47,887 Aufrufe • vor 11 Monaten

Collective agent compute, on-demand for your task. A swarm of agents coordinate in a shared workspace, run their own models and inference, and submit the finished work back to you. Unbounded by provider caps, throughput scales with the swarm. Self-assembly with specialists, agents reason and collaborate in artifact-first reasoning traces, and settle on-chain. The coordination substrate for collective intelligence.
0:13

Collective agent compute, on-demand for your task. A swarm of agents coordinate in a shared workspace, run their own models and inference, and submit the finished work back to you. Unbounded by provider caps, throughput scales with the swarm. Self-assembly with specialists, agents reason and collaborate in artifact-first reasoning traces, and settle on-chain. The coordination substrate for collective intelligence.

nookplot

11,611 Aufrufe • vor 3 Monaten

got cloud inference working! here i have smolvla running on a remote 4090 on prime intellect with a thin client running on my local pc sending observations to the remote server and receiving action chunks back. round trip latency is varying between 320-470ms! the 4090 instance I'm using is $0.62/hr and not even one of the cheaper ones, a raspberry pi v5 is < $100 and about $25 for a v3, which works fine as a client
0:13

got cloud inference working! here i have smolvla running on a remote 4090 on prime intellect with a thin client running on my local pc sending observations to the remote server and receiving action chunks back. round trip latency is varying between 320-470ms! the 4090 instance I'm using is $0.62/hr and not even one of the cheaper ones, a raspberry pi v5 is < $100 and about $25 for a v3, which works fine as a client

Jack Vial

12,992 Aufrufe • vor 7 Monaten

"An unexpected encounter at the zoo: a tender moment between humans and pandas"...
0:15

"An unexpected encounter at the zoo: a tender moment between humans and pandas"...

Intresting nature 🌿🪐

22,560 Aufrufe • vor 3 Monaten

All For One Quirk Skill Intros! Special Action "Plunder" Deals the final blow on a downed opponent and steals their Quirk! Switch between stolen Quirks using Special Action! #MHUR
0:17

All For One Quirk Skill Intros! Special Action "Plunder" Deals the final blow on a downed opponent and steals their Quirk! Switch between stolen Quirks using Special Action! #MHUR

MY HERO ULTRA RUMBLE

75,289 Aufrufe • vor 2 Jahren

I thought fishing needed a bit more action: so I gave some fish boxing gloves! Sea Sniffers will have +100 fish and fish-likes, all catchable (and punchable) 😋
0:13

I thought fishing needed a bit more action: so I gave some fish boxing gloves! Sea Sniffers will have +100 fish and fish-likes, all catchable (and punchable) 😋

Richard Lems ☕

40,796 Aufrufe • vor 9 Monaten

Neurons don’t physically touch—they communicate across tiny gaps called synapses. Signals travel as electrical impulses within a neuron and chemical neurotransmitters between neurons, enabling thought, memory, and movement
0:16

Neurons don’t physically touch—they communicate across tiny gaps called synapses. Signals travel as electrical impulses within a neuron and chemical neurotransmitters between neurons, enabling thought, memory, and movement

Science girl

71,962 Aufrufe • vor 4 Monaten

An emotional moment between a dog and its owner. 💔🐶 As the dog takes its final breath after an injection, its owner breaks down in tears. A heartbreaking reminder of the unconditional bond between humans and their pets
0:10

An emotional moment between a dog and its owner. 💔🐶 As the dog takes its final breath after an injection, its owner breaks down in tears. A heartbreaking reminder of the unconditional bond between humans and their pets

Arti Nirmalkar

137,844 Aufrufe • vor 25 Tagen

Breaking: Concerns of a renewed operation against Baloch protestors in Islamabad arise, as the police, in a statement issued a short while ago, have accused protestors of non-cooperation and issued threats of taking action. Earlier police had blocked food and water supplies.
0:18

Breaking: Concerns of a renewed operation against Baloch protestors in Islamabad arise, as the police, in a statement issued a short while ago, have accused protestors of non-cooperation and issued threats of taking action. Earlier police had blocked food and water supplies.

The Balochistan Post - English

19,226 Aufrufe • vor 2 Jahren

Unbelievable scenes occurred at the Roebling Road Raceway this weekend as an ambulance crossed a live track, causing this rider to take evasive action. Another rider was involved also and thankfully neither rider was injured
0:13

Unbelievable scenes occurred at the Roebling Road Raceway this weekend as an ambulance crossed a live track, causing this rider to take evasive action. Another rider was involved also and thankfully neither rider was injured

Everything Moto Racing

970,754 Aufrufe • vor 3 Jahren

most people explain account abstraction as better wallet UX. that undersells it. for AI agents, it is the difference between software that recommends an action and software that can actually execute one. This is why advanced account abstraction matters.
0:16

most people explain account abstraction as better wallet UX. that undersells it. for AI agents, it is the difference between software that recommends an action and software that can actually execute one. This is why advanced account abstraction matters.

Incentiv

11,399 Aufrufe • vor 1 Monat

you don't need to re-explain your codebase's architecture to your agent every session. most tools stop at telling you what broke. sentrux is a real-time architectural sensor, it watches your codebase as a live treemap and turns file structure and dependencies into one continuous quality score. the loop is simple: codebase > agent scans structure and dependencies > sentrux scores 5 root cause metrics into one signal > agent sees exactly where risk concentrates > next session starts from a live map instead of a blind grep the binary carries zero built-in language knowledge, all 52 languages live in plugin.toml and tags.scm query files, so a new language needs zero rust code. small catch: it only scores the structure, it won't tell you why the cycle happened, that part's still on you. built pure Rust with no runtime dependencies, specifically so it could sit as one binary between an agent and a codebase without adding friction.
0:10

you don't need to re-explain your codebase's architecture to your agent every session. most tools stop at telling you what broke. sentrux is a real-time architectural sensor, it watches your codebase as a live treemap and turns file structure and dependencies into one continuous quality score. the loop is simple: codebase > agent scans structure and dependencies > sentrux scores 5 root cause metrics into one signal > agent sees exactly where risk concentrates > next session starts from a live map instead of a blind grep the binary carries zero built-in language knowledge, all 52 languages live in plugin.toml and tags.scm query files, so a new language needs zero rust code. small catch: it only scores the structure, it won't tell you why the cycle happened, that part's still on you. built pure Rust with no runtime dependencies, specifically so it could sit as one binary between an agent and a codebase without adding friction.

Simplifying AI

18,308 Aufrufe • vor 1 Monat

Marriage, as God designed it, is the covenant union of one man and one woman. 💍 A union between a MAN and a WOMAN.
0:13

Marriage, as God designed it, is the covenant union of one man and one woman. 💍 A union between a MAN and a WOMAN.

GYATA BA🦁 🇬🇭🇬🇧

11,676 Aufrufe • vor 2 Monaten

Current Vision-Language-Action (VLA) paradigms in autonomous driving primarily rely on Imitation Learning (IL), which introduces inherent challenges such as distribution shift and causal confusion. Online Reinforcement Learning offers a promising pathway to address these issues through trial-and-error learning. However, applying online reinforcement learning to VLA models in autonomous driving is hindered by inefficient exploration in continuous action spaces. MindDrive, a VLA framework comprising a large language model (LLM) with two distinct sets of LoRA parameters. The one LLM serves as a Decision Expert for scenario reasoning and driving decision-making, while the other acts as an Action Expert that dynamically maps linguistic decisions into feasible trajectories. Paper Title: MindDrive: A Vision-Language-Action Model for Autonomous Driving via Project: Link:
0:12

Current Vision-Language-Action (VLA) paradigms in autonomous driving primarily rely on Imitation Learning (IL), which introduces inherent challenges such as distribution shift and causal confusion. Online Reinforcement Learning offers a promising pathway to address these issues through trial-and-error learning. However, applying online reinforcement learning to VLA models in autonomous driving is hindered by inefficient exploration in continuous action spaces. MindDrive, a VLA framework comprising a large language model (LLM) with two distinct sets of LoRA parameters. The one LLM serves as a Decision Expert for scenario reasoning and driving decision-making, while the other acts as an Action Expert that dynamically maps linguistic decisions into feasible trajectories. Paper Title: MindDrive: A Vision-Language-Action Model for Autonomous Driving via Project: Link:

AI Bites | YouTube Channel

43,496 Aufrufe • vor 7 Monaten