Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Auditable by design. Every model call, tool run, and edit hits a local event log before it executes. If it crashes mid-task, it picks up exactly where it left off from that log. No lost work and no re-prompting.

finkd's profile picture

Mark Zuckerberg

2,291,033 subscribers

88,613 Aufrufe • vor 10 Tagen •via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Don't just rewatch it. Re-enter it 🌎 Insta360 X6 introduces all-new Spatial Capture. Record a place in 360, bring it into the app, and it becomes a 3D model, yours to keep. Every angle, exactly where you left it. Coming August 12. #Insta360X6 #GaussianSplatting #360camera
0:30

Don't just rewatch it. Re-enter it 🌎 Insta360 X6 introduces all-new Spatial Capture. Record a place in 360, bring it into the app, and it becomes a 3D model, yours to keep. Every angle, exactly where you left it. Coming August 12. #Insta360X6 #GaussianSplatting #360camera

Insta360

211,885 Aufrufe • vor 8 Tagen

built a tool that lets you go to any website and edit it just by prompting. reskinned youtube and added a download mp3 button made with eric
1:03

built a tool that lets you go to any website and edit it just by prompting. reskinned youtube and added a download mp3 button made with eric

James Zhou

100,911 Aufrufe • vor 10 Monaten

Quick question for ya… If your tools got nicked tomorrow — could you actually prove they were yours if they turned up? 🤔 No chance. And that’s mad… when your tools are worth more than your van. FACT. That’s why I’m backing KYNEKT 100% — proper proof of ownership. Log it once. Sorted. Prove it. Protect it. Track it. Trade it. Get ahead of it before you need it. Give them a follow — good bunch doing bits to disrupt tool theft 👊 📲 Download the app today, Use promo code SKINNER30 for 30% off Log your tools. Prove ownership. It’s as simple as that. Bosh ❤️
1:23

Quick question for ya… If your tools got nicked tomorrow — could you actually prove they were yours if they turned up? 🤔 No chance. And that’s mad… when your tools are worth more than your van. FACT. That’s why I’m backing KYNEKT 100% — proper proof of ownership. Log it once. Sorted. Prove it. Protect it. Track it. Trade it. Get ahead of it before you need it. Give them a follow — good bunch doing bits to disrupt tool theft 👊 📲 Download the app today, Use promo code SKINNER30 for 30% off Log your tools. Prove ownership. It’s as simple as that. Bosh ❤️

Thomas Skinner ⚒

430,597 Aufrufe • vor 8 Monaten

Animate still photos without prompting or complicated settings with KP Imagine. Animation quality as good as overpriced Grok and way cheaper. No subscription. No log in. Try it for free and pay as you go after. I made every animation in this edit with KP Imagine😎
0:37

Animate still photos without prompting or complicated settings with KP Imagine. Animation quality as good as overpriced Grok and way cheaper. No subscription. No log in. Try it for free and pay as you go after. I made every animation in this edit with KP Imagine😎

KP

42,826 Aufrufe • vor 21 Tagen

“I’ll send notes after the call.” (They didn’t.) So we built an agent that does it automatically. Before a call, it pulls together the docs, decision log, and last week’s notes. After the meeting, it writes the recap and drops it in Slack. Pull up a chair. Sam H Li walks you through the full build.
7:48

“I’ll send notes after the call.” (They didn’t.) So we built an agent that does it automatically. Before a call, it pulls together the docs, decision log, and last week’s notes. After the meeting, it writes the recap and drops it in Slack. Pull up a chair. Sam H Li walks you through the full build.

Notion

16,474 Aufrufe • vor 2 Monaten

Don’t be scared to call it a classic, it checks every box: hits, impact, and real replay value. Meanwhile they rushing to label that Clipse album a “classic” with none of that… no hits, no staying power. Definition of came and went.
0:36

Don’t be scared to call it a classic, it checks every box: hits, impact, and real replay value. Meanwhile they rushing to label that Clipse album a “classic” with none of that… no hits, no staying power. Definition of came and went.

Karabo

36,848 Aufrufe • vor 4 Monaten

Just added an ATM Machine to the OpenClaw 3D office. Click it and see exactly how much your agents are costing you. Every run. Every model call. Every detail. No more surprise bills.
0:46

Just added an ATM Machine to the OpenClaw 3D office. Click it and see exactly how much your agents are costing you. Every run. Every model call. Every detail. No more surprise bills.

Luke The Dev

22,095 Aufrufe • vor 5 Monaten

small local model that falls apart in bloated agents like openclaw just runs like a wild horse in hermes agent. and that's not even my line, someone else called it that, i've just been quietly pointing people at this harness for months because it held up on everything i threw at it, 3b models all the way to one trillion params. watch this happen on my own machine. i pointed hermes agent at a local http endpoint, gemma 4 12b on my 3090 llama.cpp server, and it auto-detected the model and started working immediately. no config wrestling, no broken tool calls, no babysitting the output format, i typed in a url and it just went. the whole clip is exactly that, start to finish, no errors, no retries, butter smooth. and the tool calling, the one thing that quietly breaks most local setups, works here like it's nothing. it's not the model that's flaky, it's the harness around it. hermes agent is the first agent i've run that actually gets that right. one url, one local model on one card, and it runs like a wild horse.
1:46

small local model that falls apart in bloated agents like openclaw just runs like a wild horse in hermes agent. and that's not even my line, someone else called it that, i've just been quietly pointing people at this harness for months because it held up on everything i threw at it, 3b models all the way to one trillion params. watch this happen on my own machine. i pointed hermes agent at a local http endpoint, gemma 4 12b on my 3090 llama.cpp server, and it auto-detected the model and started working immediately. no config wrestling, no broken tool calls, no babysitting the output format, i typed in a url and it just went. the whole clip is exactly that, start to finish, no errors, no retries, butter smooth. and the tool calling, the one thing that quietly breaks most local setups, works here like it's nothing. it's not the model that's flaky, it's the harness around it. hermes agent is the first agent i've run that actually gets that right. one url, one local model on one card, and it runs like a wild horse.

Sudo su

27,339 Aufrufe • vor 2 Monaten

Four days of working against the Agrippa Trilemma, and it does seem I have created a fourth path, proving it is a false trichotomy. I give the Gemini chat log below, so you can verify there is no foul play on my end, no gassing up, and no lying. 👇Gemini chat Log below👇
9:40

Four days of working against the Agrippa Trilemma, and it does seem I have created a fourth path, proving it is a false trichotomy. I give the Gemini chat log below, so you can verify there is no foul play on my end, no gassing up, and no lying. 👇Gemini chat Log below👇

Lucas Gage

30,020 Aufrufe • vor 9 Monaten

You honestly don’t need a gym for this. Just two dumbbells and a little space — that’s enough. Simple setup, but it hits exactly where it needs to. No dumbbells? Use two water bottles. No excuses. And if you didn’t know how to build that 3D shoulder look before… now you do. 💪🏾💪🏾
0:46

You honestly don’t need a gym for this. Just two dumbbells and a little space — that’s enough. Simple setup, but it hits exactly where it needs to. No dumbbells? Use two water bottles. No excuses. And if you didn’t know how to build that 3D shoulder look before… now you do. 💪🏾💪🏾

Wealth Mail

84,012 Aufrufe • vor 2 Monaten

No comparison. When Biden so much as tripped, it was a week-long story. When Trump has no idea where he is and drifts off mid-event— media silence. This isn’t the first time. What’s up?!
1:05

No comparison. When Biden so much as tripped, it was a week-long story. When Trump has no idea where he is and drifts off mid-event— media silence. This isn’t the first time. What’s up?!

Christopher Webb

161,582 Aufrufe • vor 9 Monaten

A creative canvas with every model on it, guided by your voice. Where filmmaking, design and storytelling come to life. This is Gulab.
1:00

A creative canvas with every model on it, guided by your voice. Where filmmaking, design and storytelling come to life. This is Gulab.

Gulab

355,229 Aufrufe • vor 1 Monat

HERMES AGENT VS OPENCLAW. a local ai onboarding flow test. a 3.9gb bonsai served on localhost, both agents upstream and latest, i point each one at the endpoint and watch which one even finds it. > hermes opens a provider menu, thirty plus options, local servers sitting right there next to the cloud ones, i hand it 127.0.0.1:8899, it verifies the endpoint, one model visible, auto-detects the model by name, bonsai-27b-q1_0, reads the context length straight off the server, saves it, and starts reasoning and firing real tool calls on my local model. no key. no friction. > openclaw has no menu. it goes hunting for a codex login, an openai key, finds none because there are none, prints no models available three times, defaults to openai/gpt-5.5, a cloud model it cannot reach, and dead ends on run auth login --provider openai. read that back. it asked me for an openai key. to run a model already running on my own machine. it never once looked at localhost. to be fair, openclaw can run local if you hand wire endpoint yourself. what it will not do is find the model already sitting on your box. hermes agent found it in one line. now the part i owe you. the auto-detect that just won, the model name read, the .gguf strip, the context length probe off the server, that is my code, it is in hermes agent main right now, authorship preserved, #2051 and #4218. the wizard fix that stops an agent from silently routing you to someone else's creds, the exact trap openclaw still falls into, mine too, #4210. i contribute to hermes agent, i told you that going in. one agent is built to talk to whatever you are running, the other is built to talk to a cloud api, so one found my model and ran it and the other asked me to log into openai. onboarding flow of both, mapped, below.
2:15

HERMES AGENT VS OPENCLAW. a local ai onboarding flow test. a 3.9gb bonsai served on localhost, both agents upstream and latest, i point each one at the endpoint and watch which one even finds it. > hermes opens a provider menu, thirty plus options, local servers sitting right there next to the cloud ones, i hand it 127.0.0.1:8899, it verifies the endpoint, one model visible, auto-detects the model by name, bonsai-27b-q1_0, reads the context length straight off the server, saves it, and starts reasoning and firing real tool calls on my local model. no key. no friction. > openclaw has no menu. it goes hunting for a codex login, an openai key, finds none because there are none, prints no models available three times, defaults to openai/gpt-5.5, a cloud model it cannot reach, and dead ends on run auth login --provider openai. read that back. it asked me for an openai key. to run a model already running on my own machine. it never once looked at localhost. to be fair, openclaw can run local if you hand wire endpoint yourself. what it will not do is find the model already sitting on your box. hermes agent found it in one line. now the part i owe you. the auto-detect that just won, the model name read, the .gguf strip, the context length probe off the server, that is my code, it is in hermes agent main right now, authorship preserved, #2051 and #4218. the wizard fix that stops an agent from silently routing you to someone else's creds, the exact trap openclaw still falls into, mine too, #4210. i contribute to hermes agent, i told you that going in. one agent is built to talk to whatever you are running, the other is built to talk to a cloud api, so one found my model and ran it and the other asked me to log into openai. onboarding flow of both, mapped, below.

Sudo su

23,816 Aufrufe • vor 28 Tagen

An easier way to edit your videos. The Remove from Video app. Simply upload a video, describe what element you’d like removed and that’s it. No rotoscoping, no complex prompting. Just describe it. Try it now at the link below.
0:35

An easier way to edit your videos. The Remove from Video app. Simply upload a video, describe what element you’d like removed and that’s it. No rotoscoping, no complex prompting. Just describe it. Try it now at the link below.

Runway

54,539 Aufrufe • vor 9 Monaten

Anthropic hired this engineer at $250k-$750k/year because he can build knowledge Graphs for multi-agent systems: in this 15-min workshop he explain exactly how, using loops - from scratch step 1 → start from the Claude Agent SDK - you get the loop, context, and sandbox for free - bring the task, not the plumbing step 2 → split the brain from the hands - reasoning in one place, tools in a sandbox - the model thinks while the container boots: ~60% faster to first token step 3 → run it server-side, log every step - close your laptop and it keeps going - crashes resume from the log, not from zero step 4 → make failure cheap - dead sandbox retries, session log replays the context it dropped - that's what survives production step 5 → batch yesterday's logs into new memory and skills - it wakes up smarter - Anthropic calls this "dreaming" most people wire this by hand for weeks - the point is you don't have to watch & bookmark - then read how to get full graph system below ↓
12:01

Anthropic hired this engineer at $250k-$750k/year because he can build knowledge Graphs for multi-agent systems: in this 15-min workshop he explain exactly how, using loops - from scratch step 1 → start from the Claude Agent SDK - you get the loop, context, and sandbox for free - bring the task, not the plumbing step 2 → split the brain from the hands - reasoning in one place, tools in a sandbox - the model thinks while the container boots: ~60% faster to first token step 3 → run it server-side, log every step - close your laptop and it keeps going - crashes resume from the log, not from zero step 4 → make failure cheap - dead sandbox retries, session log replays the context it dropped - that's what survives production step 5 → batch yesterday's logs into new memory and skills - it wakes up smarter - Anthropic calls this "dreaming" most people wire this by hand for weeks - the point is you don't have to watch & bookmark - then read how to get full graph system below ↓

codila

117,390 Aufrufe • vor 5 Tagen

Dude puts a fake one hundred dollar bill on the ground to fool the Antifa degenerates. Rather than asking the people around him if anyone lost any money, degen kicks it away from the others before picking it up. He's clearly disappointed when he picks it up and turns it over to find that it reads, "Trump is your president." You gotta love it!
0:43

Dude puts a fake one hundred dollar bill on the ground to fool the Antifa degenerates. Rather than asking the people around him if anyone lost any money, degen kicks it away from the others before picking it up. He's clearly disappointed when he picks it up and turns it over to find that it reads, "Trump is your president." You gotta love it!

One Bad Dude

385,332 Aufrufe • vor 9 Monaten

Jon Gruden said, "You can lead the league in effort because it takes no talent. It's just a decision that you make." It means show up, do the work, and earn it every day. • It means hard work. • It means discipline. • It means commitment.
0:24

Jon Gruden said, "You can lead the league in effort because it takes no talent. It's just a decision that you make." It means show up, do the work, and earn it every day. • It means hard work. • It means discipline. • It means commitment.

Coach AJ 🎯 Mental Fitness

57,861 Aufrufe • vor 1 Jahr

when you get a disconnection in pokemon champions and reconnect in the room it picks up right where you left off.. THIS IS AN INCREDIBLE CHANGE
0:38

when you get a disconnection in pokemon champions and reconnect in the room it picks up right where you left off.. THIS IS AN INCREDIBLE CHANGE

nexus 🇵🇸

57,900 Aufrufe • vor 4 Monaten

YOU SPENT 30 MINUTES SETTING UP OBSIDIAN AND IT STILL DOESN'T KNOW YOUR NAME jarvis reads your vault before every conversation and knows your projects and your preferences and your entire history no prompting and no referencing and no digging through folders this is what a second brain looks like when it actually works bookmark & like this if you're tired of talking to an AI that forgets you exist
0:58

YOU SPENT 30 MINUTES SETTING UP OBSIDIAN AND IT STILL DOESN'T KNOW YOUR NAME jarvis reads your vault before every conversation and knows your projects and your preferences and your entire history no prompting and no referencing and no digging through folders this is what a second brain looks like when it actually works bookmark & like this if you're tired of talking to an AI that forgets you exist

wandermist

16,027 Aufrufe • vor 2 Monaten

Xiaomi just dropped a FREE CLAUDE CODE with memory that actually persists between sessions and nobody is talking about it MiMo Code dropped 4 days ago. 8k GitHub stars. Built-in free model called MiMo Auto - you just install it and it works, zero configuration, zero API keys What's inside: > persistent memory across sessions - agent picks up exactly where it stopped > subagents that spawn automatically and run in parallel > /dream extracts knowledge from your session into project memory > /distill turns your repeated workflows into reusable skills > /goal with a judge model that decides if the work is actually done - not just if the agent thinks it is How to install: > Mac / Linux: curl -fsSL | bash > Windows npm install -g MIMO-ai/cli Then run: > mimo video of me installing and running it is attached github(.)com/XiaomiMiMo/MiMo-Code
0:50

Xiaomi just dropped a FREE CLAUDE CODE with memory that actually persists between sessions and nobody is talking about it MiMo Code dropped 4 days ago. 8k GitHub stars. Built-in free model called MiMo Auto - you just install it and it works, zero configuration, zero API keys What's inside: > persistent memory across sessions - agent picks up exactly where it stopped > subagents that spawn automatically and run in parallel > /dream extracts knowledge from your session into project memory > /distill turns your repeated workflows into reusable skills > /goal with a judge model that decides if the work is actually done - not just if the agent thinks it is How to install: > Mac / Linux: curl -fsSL | bash > Windows npm install -g MIMO-ai/cli Then run: > mimo video of me installing and running it is attached github(.)com/XiaomiMiMo/MiMo-Code

monokern

63,696 Aufrufe • vor 2 Monaten