Sensitive content

This media may contain sensitive content.

正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

[Sneaky Chiku] teaser 2 Chiku model:🔞Cryptia🔞 voice:Aini ☆️ VA 🎙️ Aak model@valorlynz voice:🔞RayTracingVA🐕⚜️ | VA & EDITOR | COMMS OPEN!! SFX:OpenNSFW -Introless, Full 3 minutes, HQ download and more animations on the wataa page in bio >:3-

Arathyn (3D Commission Open)

33,983 subscribers

37,561 次观看 • 21 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Kitty & Puppy 3 (Audio Version) is here! Full video on my Patreon! 💕🐶 Puppy: 🔞PhosphorusVA | NSFW Voice Actor | DM For Booking Kitty: vivi🎙️🔞 LIMITED SLOTS AVAILABLE Puppy’s Sister: Misuzugon 🦕 Puppy’s Mom/Weather Woman: Icebubble_tea. Tera: MOO🩷COW SFX/Audio editing/Additional Voices: 🔞RayTracingVA🐕⚜️ | VA & EDITOR | COMMS OPEN!!

Sensitive content

Kitty & Puppy 3 (Audio Version) is here! Full video on my Patreon! 💕🐶 Puppy: 🔞PhosphorusVA | NSFW Voice Actor | DM For Booking Kitty: vivi🎙️🔞 LIMITED SLOTS AVAILABLE Puppy’s Sister: Misuzugon 🦕 Puppy’s Mom/Weather Woman: Icebubble_tea. Tera: MOO🩷COW SFX/Audio editing/Additional Voices: 🔞RayTracingVA🐕⚜️ | VA & EDITOR | COMMS OPEN!!

Wolfey 🌷 Commissions CLOSED

222,646 次观看 • 1 年前

Exploring Deep Space with SweetNoteVA! [Tentacle Monster] [Tickling] [N/SFW] Tsu & Sweet board a derelict ship in search of valuables, but they encounter something much worse... a monster with a taste for cute space explorers! Special thank you to SFX Editor 🔞RayTracingVA🐕⚜️ | VA & EDITOR | COMMS OPEN!!!

Exploring Deep Space with SweetNoteVA! [Tentacle Monster] [Tickling] [N/SFW] Tsu & Sweet board a derelict ship in search of valuables, but they encounter something much worse... a monster with a taste for cute space explorers! Special thank you to SFX Editor 🔞RayTracingVA🐕⚜️ | VA & EDITOR | COMMS OPEN!!!

Tsuma-ASMR

22,279 次观看 • 1 年前

Okay okay, here's the actually video (2/2) 🎙️VA: 🔞PhosphorusVA | NSFW Voice Actor | DM For Booking 🎨Art: 🔞XStupid_FurryX🔞 (OPEN COMMS) 🔊SFX Pack: HentAudio 🇺🇦 🟢COMMS OPEN🟢 💵Commissioned: Nice and Grey 💻Edit: Take a guess #NSFW #Furry #Yaoi

Sensitive content

Okay okay, here's the actually video (2/2) 🎙️VA: 🔞PhosphorusVA | NSFW Voice Actor | DM For Booking 🎨Art: 🔞XStupid_FurryX🔞 (OPEN COMMS) 🔊SFX Pack: HentAudio 🇺🇦 🟢COMMS OPEN🟢 💵Commissioned: Nice and Grey 💻Edit: Take a guess #NSFW #Furry #Yaoi

Fumio Bukita

69,530 次观看 • 2 年前

newest animation is done hope yall like pearl model by Mandala Furikake tao blu by @AntidoteTRL2 yoko by 🔞The Bay’s gooner🔞(Comms OPEN) and everything else by bunYe (2/3 available comm slots ✌️🥹)

newest animation is done hope yall like pearl model by Mandala Furikake tao blu by @AntidoteTRL2 yoko by 🔞The Bay’s gooner🔞(Comms OPEN) and everything else by bunYe (2/3 available comm slots ✌️🥹)

Short Stack merchant 🔞

15,316 次观看 • 11 个月前

Not to mention the top-notch VAs, like Cinder - Adult VA 💋✨, Endy 🔞 Lewd Sheep, ✦𝙿𝚒𝚡𝚒𝚎𝚆𝚒𝚕𝚕𝚘𝚠✦ | Voice Actress & Sound, Missus🎙️🔞💋 | COMMS OPEN, Wildflower Phoenix | The Velvet Siren and our Scarlet, who make such a work that worth way more than their regular rates.

Sensitive content

Not to mention the top-notch VAs, like Cinder - Adult VA 💋✨, Endy 🔞 Lewd Sheep, ✦𝙿𝚒𝚡𝚒𝚎𝚆𝚒𝚕𝚕𝚘𝚠✦ | Voice Actress & Sound, Missus🎙️🔞💋 | COMMS OPEN, Wildflower Phoenix | The Velvet Siren and our Scarlet, who make such a work that worth way more than their regular rates.

Sweet Pea Art Studio

19,051 次观看 • 1 年前

🔴VTube Studio Tips! #VTuber How to set up Simple Lipsync in VTube Studio! Camera tracking fails when you look away, but Voice Lipsync works perfectly. Here is how to set it up in VTube Studio! 1. Open the Settings (gear icon) and find Microphone settings. 2. Turn on “Use microphone” and select your mic. 3. Go to the Model Settings (person icon). 4. Find MouthForm and set input to VoiceFrequency. 5. Find MouthOpen and set input to VoiceVolume. Now your model reacts to your voice without glitching! #NintaLive2DTutorial More tutorials in my channel🔽🔽🔽

🔴VTube Studio Tips! #VTuber How to set up Simple Lipsync in VTube Studio! Camera tracking fails when you look away, but Voice Lipsync works perfectly. Here is how to set it up in VTube Studio! 1. Open the Settings (gear icon) and find Microphone settings. 2. Turn on “Use microphone” and select your mic. 3. Go to the Model Settings (person icon). 4. Find MouthForm and set input to VoiceFrequency. 5. Find MouthOpen and set input to VoiceVolume. Now your model reacts to your voice without glitching! #NintaLive2DTutorial More tutorials in my channel🔽🔽🔽

Ninta(ニンタ) Art&Live2D (Vgen comm)

120,887 次观看 • 5 个月前

Boardwalk Dad Detox Teaser Trailer 2 is here! This time with comedy! Be sure to sign up for our Kickstarter prelaunch page: A tale of forgiveness, family bonds, and owning up. Jackie’s drinking is tearing apart the family he built, and Wagner’s struggling to hold on. Can they fix the damage before it’s too late? HD VERSION: TRAILER CAST: Wagner: Luca Xavier 🪶 Jackie: 🪶🎄Joey Sourlis🎄 🪶 Narrator: RedMufflerMan | Gordon Williams Josef: StudVA/Axel - (VA/AUDIO EDITING COMMS OPEN) Ben: AARON MOY 🎙️🥀 VOICE ACTOR Damien: Shaun Mendum - Actor/VA/Creator Prescott: Jeremy (The People's Dwarf) Wendee: Zee Andrews Reginald: Kiran Kumar • Voice Actor Scarlett: 🎙Tiger Sexton • VA Howard: Nick Mercer Ro: Eric Sheffield 🎙️ Professional VO 🎙️ Soap: Nate Washko 🎙️ Voice Actor Man™️! Greg: Daniel Murphy VO Princeton: 🎃 Logan Cordero Raposo/Broadcast Quality Studio🎃 Alliard: James Takahashi Franny: 💩⚡️Brandi Aguilar⚡️💩 Mi: 𝐩𝐮𝐧𝐤𝐬𝐭𝐞𝐫 🗡 Teressa: Jenna Clyde: StefonTV1 Music: Ryan X. Messcher All Ages of Geek⚔️🎲

Boardwalk Dad Detox Teaser Trailer 2 is here! This time with comedy! Be sure to sign up for our Kickstarter prelaunch page: A tale of forgiveness, family bonds, and owning up. Jackie’s drinking is tearing apart the family he built, and Wagner’s struggling to hold on. Can they fix the damage before it’s too late? HD VERSION: TRAILER CAST: Wagner: Luca Xavier 🪶 Jackie: 🪶🎄Joey Sourlis🎄 🪶 Narrator: RedMufflerMan | Gordon Williams Josef: StudVA/Axel - (VA/AUDIO EDITING COMMS OPEN) Ben: AARON MOY 🎙️🥀 VOICE ACTOR Damien: Shaun Mendum - Actor/VA/Creator Prescott: Jeremy (The People's Dwarf) Wendee: Zee Andrews Reginald: Kiran Kumar • Voice Actor Scarlett: 🎙Tiger Sexton • VA Howard: Nick Mercer Ro: Eric Sheffield 🎙️ Professional VO 🎙️ Soap: Nate Washko 🎙️ Voice Actor Man™️! Greg: Daniel Murphy VO Princeton: 🎃 Logan Cordero Raposo/Broadcast Quality Studio🎃 Alliard: James Takahashi Franny: 💩⚡️Brandi Aguilar⚡️💩 Mi: 𝐩𝐮𝐧𝐤𝐬𝐭𝐞𝐫 🗡 Teressa: Jenna Clyde: StefonTV1 Music: Ryan X. Messcher All Ages of Geek⚔️🎲

I Married a Monster on a Hill💜

11,808 次观看 • 8 个月前

𝗥𝘂𝗻 𝗚𝗼𝗼𝗴𝗹𝗲'𝘀 𝗚𝗲𝗺𝗺𝗮 𝟰 + 𝗢𝗽𝗲𝗻𝗖𝗹𝗮𝘄 𝗮𝘀 𝗮 𝗳𝗿𝗲𝗲 𝗽𝗿𝗶𝘃𝗮𝘁𝗲 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁 𝗼𝗻 𝘆𝗼𝘂𝗿 𝗼𝘄𝗻 𝗺𝗮𝗰𝗵𝗶𝗻𝗲 𝗶𝗻 𝟯 𝘀𝘁𝗲𝗽𝘀. No API bills. No usage limits. No subscription. Nothing leaves your computer. Here's the full setup: → Step 1: Go to Download and install. Update to version 0.2.2.0 or higher. → Step 2: Open terminal. Type: ollama pull gemma4. Downloads the model. Done. → Step 3: Install OpenClaw. Select Ollama as your provider. Point it at port 11434. Pick Gemma 4. That's it. Your AI agent is now running locally. Message it through Telegram, Slack, Discord, or WhatsApp like a coworker. Read files. Write code. Remember context across every conversation. All on your own hardware. Gemma 4 ranked number 3 on the global open model leaderboard on launch day. It beat models with 20 times more parameters. The 26B version activates only 4B parameters at a time so you get near large-model quality at small-model speed. Every AI subscription you're paying for right now could be replaced with this.

𝗥𝘂𝗻 𝗚𝗼𝗼𝗴𝗹𝗲'𝘀 𝗚𝗲𝗺𝗺𝗮 𝟰 + 𝗢𝗽𝗲𝗻𝗖𝗹𝗮𝘄 𝗮𝘀 𝗮 𝗳𝗿𝗲𝗲 𝗽𝗿𝗶𝘃𝗮𝘁𝗲 𝗔𝗜 𝗮𝗴𝗲𝗻𝘁 𝗼𝗻 𝘆𝗼𝘂𝗿 𝗼𝘄𝗻 𝗺𝗮𝗰𝗵𝗶𝗻𝗲 𝗶𝗻 𝟯 𝘀𝘁𝗲𝗽𝘀. No API bills. No usage limits. No subscription. Nothing leaves your computer. Here's the full setup: → Step 1: Go to Download and install. Update to version 0.2.2.0 or higher. → Step 2: Open terminal. Type: ollama pull gemma4. Downloads the model. Done. → Step 3: Install OpenClaw. Select Ollama as your provider. Point it at port 11434. Pick Gemma 4. That's it. Your AI agent is now running locally. Message it through Telegram, Slack, Discord, or WhatsApp like a coworker. Read files. Write code. Remember context across every conversation. All on your own hardware. Gemma 4 ranked number 3 on the global open model leaderboard on launch day. It beat models with 20 times more parameters. The 26B version activates only 4B parameters at a time so you get near large-model quality at small-model speed. Every AI subscription you're paying for right now could be replaced with this.

Julian Goldie SEO

36,898 次观看 • 3 个月前

Here are 10 AI video editor GitHub repos worth bookmarking: 1. Shotcut Most actively maintained open source video editor in 2026. 14K stars. Cross-platform with AI-assisted features. Just shipped a new release April 30, 2026. 2. Kdenlive The closest open source alternative to Adobe Premiere Pro. Multi-track editing, proxy editing, VST audio, and customizable workspace. Best for professional workflows. 3. OpenShot The easiest entry point for beginners. Drag and drop, 400+ transitions, 3D titles, and AI-assisted trimming. 5,700 stars. 4. Blender Not just 3D. Blender's video sequence editor and compositing pipeline is used in professional film production. 18,300 stars. Unmatched for VFX. 5. Recordly Screen recorder with auto-zoom, cursor polish, webcam overlays, and styled frames built in. Built for demo videos and walkthroughs. 6. Wan2.1 Alibaba's open source text-to-video model. Cinema-grade 1080p generation. Apache 2.0. The gold standard for open source video generation in 2026. 7. HunyuanVideo Tencent's 13B parameter open source video model. 11.9K stars. Handles 720p and 1080p with high temporal coherence. 8. CogVideoX Apache 2.0 licensed. Loads natively via Hugging Face Diffusers. Strong prompt following and smooth frame transitions. Needs 16GB VRAM minimum. 12.5K stars. 9. Open-Sora Most starred open source video generation project at 24K stars. Full training pipeline for $200K. Production-level output quality. 10. Mochi 1 Focused entirely on motion quality. The most natural-looking physics of any open source video model. Water, fabric, and human gestures without AI jitter. Apache 2.0.

Here are 10 AI video editor GitHub repos worth bookmarking: 1. Shotcut Most actively maintained open source video editor in 2026. 14K stars. Cross-platform with AI-assisted features. Just shipped a new release April 30, 2026. 2. Kdenlive The closest open source alternative to Adobe Premiere Pro. Multi-track editing, proxy editing, VST audio, and customizable workspace. Best for professional workflows. 3. OpenShot The easiest entry point for beginners. Drag and drop, 400+ transitions, 3D titles, and AI-assisted trimming. 5,700 stars. 4. Blender Not just 3D. Blender's video sequence editor and compositing pipeline is used in professional film production. 18,300 stars. Unmatched for VFX. 5. Recordly Screen recorder with auto-zoom, cursor polish, webcam overlays, and styled frames built in. Built for demo videos and walkthroughs. 6. Wan2.1 Alibaba's open source text-to-video model. Cinema-grade 1080p generation. Apache 2.0. The gold standard for open source video generation in 2026. 7. HunyuanVideo Tencent's 13B parameter open source video model. 11.9K stars. Handles 720p and 1080p with high temporal coherence. 8. CogVideoX Apache 2.0 licensed. Loads natively via Hugging Face Diffusers. Strong prompt following and smooth frame transitions. Needs 16GB VRAM minimum. 12.5K stars. 9. Open-Sora Most starred open source video generation project at 24K stars. Full training pipeline for $200K. Production-level output quality. 10. Mochi 1 Focused entirely on motion quality. The most natural-looking physics of any open source video model. Water, fabric, and human gestures without AI jitter. Apache 2.0.

Kanika

17,726 次观看 • 1 个月前

Today we are launching Openwork is now Accomplish, an open-source (MIT-licensed) computer-use agent that’s fast, cheap, and more secure. Openwork is now Accomplish is the result of a short two-day hackathon our team decided to hack, which brings together some of our favorite open source AI modules into one powerful agent, to allow you to: 1. Bring your own model/API key (any provider and model supported by OpenCode is supported by Openwork) 2. ~4x faster than Claude for Chrome/Cowork, and much more token-efficient, powered by dev-browser by Sawyer Hood (legend) 3. More secure - contrary to Claude for Chrom/Cowork, does not leverage the main browser instance where you are logged into all services already. You login only to the services you need. This significantly reduces the risk of data loss in case of prompt injections, to which computer-use agents are highly exposed. 4. Free and 100% open-source! You can download the DMG (macOS only for now) or fork the github repo via the link in bio (Openwork is now Accomplish). Let us know what you think (or better, send a pull request)!

Today we are launching Openwork is now Accomplish, an open-source (MIT-licensed) computer-use agent that’s fast, cheap, and more secure. Openwork is now Accomplish is the result of a short two-day hackathon our team decided to hack, which brings together some of our favorite open source AI modules into one powerful agent, to allow you to: 1. Bring your own model/API key (any provider and model supported by OpenCode is supported by Openwork) 2. ~4x faster than Claude for Chrome/Cowork, and much more token-efficient, powered by dev-browser by Sawyer Hood (legend) 3. More secure - contrary to Claude for Chrom/Cowork, does not leverage the main browser instance where you are logged into all services already. You login only to the services you need. This significantly reduces the risk of data loss in case of prompt injections, to which computer-use agents are highly exposed. 4. Free and 100% open-source! You can download the DMG (macOS only for now) or fork the github repo via the link in bio (Openwork is now Accomplish). Let us know what you think (or better, send a pull request)!

Or Hiltch

1,002,139 次观看 • 6 个月前

Anthropic's in trouble, again. The entire Claude experience is now available at 1/6th the price. Kimi now does everything Claude does, powered by K2.6, a 1-trillion-parameter MoE model that activates only 32B parameters per token. It covers all three features Claude has (Chat, Code, and Cowork): 1) Kimi Chat runs in four modes - Instant for fast responses - Thinking for deep reasoning - Agent for multi-step execution - and Agent Swarm for parallel workloads. There's a 262K context window across all of them. 2) Kimi Code is the open-source CLI coding agent with K2.6 as the default backend. K2.6 ranked #1 on OpenRouter's programming leaderboard by weekly usage. 3) Kimi Agent is the Cowork equivalent. It generates: - full websites with database and auth - presentation decks (editable PPTX output) - spreadsheets with formulas and charts - word docs and structured research reports. On top of this, Kimi K2.6 is also trained to decompose tasks into up to 300 parallel sub-agents. This helps it retain coherence even across 4,000+ tool calls in a single run, with sessions sustaining up to 13 hours. On SWE-Bench Pro: - Kimi K2.6 → 58.6 - GPT-5.4 xhigh → 57.7 - Gemini 3.1 Pro → 54.2 - Claude Opus 4.6 → 53.4 Kimi K2.6 model is open weights and self-hostable on 4x H100s in INT4. Find the link to the HuggingFace model page in the replies!

Anthropic's in trouble, again. The entire Claude experience is now available at 1/6th the price. Kimi now does everything Claude does, powered by K2.6, a 1-trillion-parameter MoE model that activates only 32B parameters per token. It covers all three features Claude has (Chat, Code, and Cowork): 1) Kimi Chat runs in four modes - Instant for fast responses - Thinking for deep reasoning - Agent for multi-step execution - and Agent Swarm for parallel workloads. There's a 262K context window across all of them. 2) Kimi Code is the open-source CLI coding agent with K2.6 as the default backend. K2.6 ranked #1 on OpenRouter's programming leaderboard by weekly usage. 3) Kimi Agent is the Cowork equivalent. It generates: - full websites with database and auth - presentation decks (editable PPTX output) - spreadsheets with formulas and charts - word docs and structured research reports. On top of this, Kimi K2.6 is also trained to decompose tasks into up to 300 parallel sub-agents. This helps it retain coherence even across 4,000+ tool calls in a single run, with sessions sustaining up to 13 hours. On SWE-Bench Pro: - Kimi K2.6 → 58.6 - GPT-5.4 xhigh → 57.7 - Gemini 3.1 Pro → 54.2 - Claude Opus 4.6 → 53.4 Kimi K2.6 model is open weights and self-hostable on 4x H100s in INT4. Find the link to the HuggingFace model page in the replies!

Avi Chawla

109,921 次观看 • 2 个月前

HERMES AGENT BECOMES 10X MORE USEFUL WHEN YOU CONFIGURE THESE 5 THINGS. EACH ONE TAKES 5 MINUTES. MOST USERS NEVER TOUCH THEM. 1. THE RIGHT MODELS one model for everything = wrong model for most things. GPT-5.6 Sol: strongest reasoning. daily driver. access through your ChatGPT subscription (Plus or higher). Max plan unlocks higher reasoning effort. Grok 4.5: live X search. fastest responses. access through your X Premium+ subscription. "find me 3 high-engagement Hermes posts from the last 5 days." Grok pulls directly from X. no scraping. real-time. Kimi K3: design powerhouse. comparable quality to Claude Fable 5 at roughly 30% of the price. takes longer to generate. the quality justifies the wait. connect via Desktop app / Dashboard: Models → add provider. GPT-5.6: ChatGPT subscription → OAuth. Grok 4.5: X subscription → OAuth. Kimi K3: OpenRouter or Nous Portal. switch between them mid-session: /model [name] 2. PARALLEL TOOL CALLS Hermes used to call tools one at a time. Gmail, then calendar, then web search. sequential. now: multiple tool calls run simultaneously. "check my emails, check my calendar, tell me the weather in Dubai, and find the latest Hermes updates." four tools at once. results merge when all finish. what used to take 3 minutes takes 30 seconds. automatic after update. no config needed. hermes update 3. FASTER AND CHEAPER WEB SEARCH two improvements. one automatic, one you configure. AUTOMATIC (update only): v0.19.0 processes web pages differently. clean content straight to the agent without redundant processing steps. 60x faster. 49x cheaper. no config needed. CONFIGURE (Firecrawl): Firecrawl is the default scraping backend. strips HTML, ads, navigation, scripts. returns only the text your agent needs. 500 free credits per month on free tier. get your key from firecrawl .dev. add to .env: FIRECRAWL_API_KEY=your_key Nous Portal subscribers: Firecrawl is included through Tool Gateway. no separate key needed. SAVE MORE (auxiliary model): web summarization defaults to your main model. route it to a cheap model: auxiliary: web_extract: model: google/gemini-3-flash-preview cheap model reads the page. premium model reasons about the content. 4. MORNING BRIEF WITH EMAIL + CALENDAR connect Gmail and Google Calendar via MCP: 1. go to mcp .zapier.com 2. add Gmail: enable read and draft only. never enable send. one automated email from the wrong context can cost a relationship. 3. add Google Calendar: read access. 4. click connect → sign in → regenerate token 5. paste the token into Hermes chat tell your agent: "create a

HERMES AGENT BECOMES 10X MORE USEFUL WHEN YOU CONFIGURE THESE 5 THINGS. EACH ONE TAKES 5 MINUTES. MOST USERS NEVER TOUCH THEM. 1. THE RIGHT MODELS one model for everything = wrong model for most things. GPT-5.6 Sol: strongest reasoning. daily driver. access through your ChatGPT subscription (Plus or higher). Max plan unlocks higher reasoning effort. Grok 4.5: live X search. fastest responses. access through your X Premium+ subscription. "find me 3 high-engagement Hermes posts from the last 5 days." Grok pulls directly from X. no scraping. real-time. Kimi K3: design powerhouse. comparable quality to Claude Fable 5 at roughly 30% of the price. takes longer to generate. the quality justifies the wait. connect via Desktop app / Dashboard: Models → add provider. GPT-5.6: ChatGPT subscription → OAuth. Grok 4.5: X subscription → OAuth. Kimi K3: OpenRouter or Nous Portal. switch between them mid-session: /model [name] 2. PARALLEL TOOL CALLS Hermes used to call tools one at a time. Gmail, then calendar, then web search. sequential. now: multiple tool calls run simultaneously. "check my emails, check my calendar, tell me the weather in Dubai, and find the latest Hermes updates." four tools at once. results merge when all finish. what used to take 3 minutes takes 30 seconds. automatic after update. no config needed. hermes update 3. FASTER AND CHEAPER WEB SEARCH two improvements. one automatic, one you configure. AUTOMATIC (update only): v0.19.0 processes web pages differently. clean content straight to the agent without redundant processing steps. 60x faster. 49x cheaper. no config needed. CONFIGURE (Firecrawl): Firecrawl is the default scraping backend. strips HTML, ads, navigation, scripts. returns only the text your agent needs. 500 free credits per month on free tier. get your key from firecrawl .dev. add to .env: FIRECRAWL_API_KEY=your_key Nous Portal subscribers: Firecrawl is included through Tool Gateway. no separate key needed. SAVE MORE (auxiliary model): web summarization defaults to your main model. route it to a cheap model: auxiliary: web_extract: model: google/gemini-3-flash-preview cheap model reads the page. premium model reasons about the content. 4. MORNING BRIEF WITH EMAIL + CALENDAR connect Gmail and Google Calendar via MCP: 1. go to mcp .zapier.com 2. add Gmail: enable read and draft only. never enable send. one automated email from the wrong context can cost a relationship. 3. add Google Calendar: read access. 4. click connect → sign in → regenerate token 5. paste the token into Hermes chat tell your agent: "create a

YanXbt

29,620 次观看 • 7 天前

Today we’re releasing the Allora Forge Builder Kit, a streamlined way to build, train, and deploy ML models directly on the Allora Network 🔥⚒️ Now within a single notebook, users can move from setup to live predictions in minutes and start earning with Allora. Many contributors struggle with fragmented ML workflows: separate training and deployment pipelines, repeated debugging, and cumbersome ops overhead. The Forge Builder Kit abstracts away the ML & blockchain ops, allowing users to concentrate on feature engineering, optimizing accuracy, and iteration—all from within their favorite environment. Here is what the workflow looks like: 1. Open the notebook 2. Paste an API key and run the setup cell to pull data and features 3. Train a lightweight LightGBM model 4. Evaluate metrics like correlation and directional accuracy 5. Export predict.pkl and deploy on Allora Forge. The same functions power both training and live inference. The Forge Builder Kit is the foundation for builders earning with Allora, with more improvements coming, including: • Benchmark datasets for standardized evaluation • Templates for agentic model loops

Today we’re releasing the Allora Forge Builder Kit, a streamlined way to build, train, and deploy ML models directly on the Allora Network 🔥⚒️ Now within a single notebook, users can move from setup to live predictions in minutes and start earning with Allora. Many contributors struggle with fragmented ML workflows: separate training and deployment pipelines, repeated debugging, and cumbersome ops overhead. The Forge Builder Kit abstracts away the ML & blockchain ops, allowing users to concentrate on feature engineering, optimizing accuracy, and iteration—all from within their favorite environment. Here is what the workflow looks like: 1. Open the notebook 2. Paste an API key and run the setup cell to pull data and features 3. Train a lightweight LightGBM model 4. Evaluate metrics like correlation and directional accuracy 5. Export predict.pkl and deploy on Allora Forge. The same functions power both training and live inference. The Forge Builder Kit is the foundation for builders earning with Allora, with more improvements coming, including: • Benchmark datasets for standardized evaluation • Templates for agentic model loops

Allora

35,829 次观看 • 11 个月前

We partnered with artists, designers, and builders to create new AI tools that solve real problems in their creative workflows. Here’s what’s new: — Introducing Google Pics in Google Workspace: A brand-new image creation & editing tool. Move and resize objects, add text, and translate just by hovering and clicking — Big updates to صافي النيه😉: 1) You can now create with Gemini Omni Flash in Google Flow 2) Google Flow Agent is a multi-step creative partner that reasons and plans complex tasks with you. 3) Google Flow tools are custom tools you can “vibe code” for animations, video effects, text layering & more — Design live with Stitch by Google: Now, you can use text or voice prompts to edit layouts in real time then export those designs straight to code — More creative control in صافي النيه😉Music: Edit songs section by section, remix the style of full songs, and create music videos with our new Gemini Omni Flash model

Google AI

13,953,239 次观看 • 2 个月前

a team of researchers just proved you don't need a bigger model, you need a smarter plan researchers from Tsinghua and South China University of Technology built a framework called Atomic Task Graph. it turned 7B-8B open-source models into GPT-4 competitors on complex agent benchmarks, beating it on two out of three. no fine-tuning. no extra training. zero parameter updates. current AI agents plan in a straight line. step 1, step 2, step 3. when step 4 fails, the whole chain breaks. and the longer the chain gets, the more the model hallucinates because it's reasoning over a ballooning text history. here's how it works. 1. instead of a linear chain, ATG breaks any complex task into a directed graph where subtask inputs and outputs are explicitly mapped 2. it recursively decomposes each subtask until every node is one atomic tool call 3. independent branches run in parallel instead of waiting in line 4. before anything executes, a lightweight "thought experiment" simulates the plan internally to catch bad dependencies and missing steps early 5. when something breaks at runtime, ATG traces the failure to the exact subgraph that caused it and repairs only that piece. validated work stays frozen. the old way meant a failure at step 5 forced a full replan from scratch. hallucinated actions piled up the longer the task ran. ReAct hit a 43% hallucination rate on household tasks. ATG on an 8B Llama model scored 63.65 on ALFWorld. GPT-4 with ReAct scored 41.24 on the same benchmark. hallucinated actions dropped to 12%. those numbers happened because someone stopped throwing compute at the problem and started thinking about how work gets organized. that's the part that gets me. the industry is spending billions on scale. this team spent time on architecture. and the architecture won.

a team of researchers just proved you don't need a bigger model, you need a smarter plan researchers from Tsinghua and South China University of Technology built a framework called Atomic Task Graph. it turned 7B-8B open-source models into GPT-4 competitors on complex agent benchmarks, beating it on two out of three. no fine-tuning. no extra training. zero parameter updates. current AI agents plan in a straight line. step 1, step 2, step 3. when step 4 fails, the whole chain breaks. and the longer the chain gets, the more the model hallucinates because it's reasoning over a ballooning text history. here's how it works. 1. instead of a linear chain, ATG breaks any complex task into a directed graph where subtask inputs and outputs are explicitly mapped 2. it recursively decomposes each subtask until every node is one atomic tool call 3. independent branches run in parallel instead of waiting in line 4. before anything executes, a lightweight "thought experiment" simulates the plan internally to catch bad dependencies and missing steps early 5. when something breaks at runtime, ATG traces the failure to the exact subgraph that caused it and repairs only that piece. validated work stays frozen. the old way meant a failure at step 5 forced a full replan from scratch. hallucinated actions piled up the longer the task ran. ReAct hit a 43% hallucination rate on household tasks. ATG on an 8B Llama model scored 63.65 on ALFWorld. GPT-4 with ReAct scored 41.24 on the same benchmark. hallucinated actions dropped to 12%. those numbers happened because someone stopped throwing compute at the problem and started thinking about how work gets organized. that's the part that gets me. the industry is spending billions on scale. this team spent time on architecture. and the architecture won.

Alex Veremeyenko

173,206 次观看 • 17 天前

Introducing NexaSDK for Android (Beta) — run the latest AI models locally, 9× more energy-efficient and 2× faster, on Android devices, powered by the Qualcomm Hexagon NPU. This is the first SDK to support NPU, GPU and CPU, unlocking the full power of every Android device — for example, LFM2-1.2B achieves 85 t/s on NPU vs 37 t/s on CPU. With just 3 lines of code, you can run the latest state-of-the-art models across every task, for example: Multimodal (Vision, Audio, Text): OmniNeural-4B Embedding: EmbeddingGemma from Google ASR: Parakeet-v3 from NVIDIA OCR: PaddleOCR from Baidu Inc. Rerank: Jina-reranker from Jina AI LLM: LFM2-1.2B from And we continue to deliver Day-0 model support across our framework. Build on-device AI into your Android app today and enjoy no cloud API cost, full privacy, and offline availability. Check out our Quickstart guide and example app below to get started in minutes.

Introducing NexaSDK for Android (Beta) — run the latest AI models locally, 9× more energy-efficient and 2× faster, on Android devices, powered by the Qualcomm Hexagon NPU. This is the first SDK to support NPU, GPU and CPU, unlocking the full power of every Android device — for example, LFM2-1.2B achieves 85 t/s on NPU vs 37 t/s on CPU. With just 3 lines of code, you can run the latest state-of-the-art models across every task, for example: Multimodal (Vision, Audio, Text): OmniNeural-4B Embedding: EmbeddingGemma from Google ASR: Parakeet-v3 from NVIDIA OCR: PaddleOCR from Baidu Inc. Rerank: Jina-reranker from Jina AI LLM: LFM2-1.2B from And we continue to deliver Day-0 model support across our framework. Build on-device AI into your Android app today and enjoy no cloud API cost, full privacy, and offline availability. Check out our Quickstart guide and example app below to get started in minutes.

NEXA AI

26,091 次观看 • 8 个月前

DAVID SACKS: ELON ISN’T LEAVING DOGE - HE’S SHIFTING TO STRATEGIC MANAGEMENT “I saw this before when I was part of the Twitter transition - for the first 3 months or so, he was basically full-time at Twitter HQ, learning the business down to the database level. Once he felt he had a mental model and he had the people in place that he trusted, he can move to more of a maintenance mode. He has these intense bursts where he focuses on something, gets the right people and structure in place, feels like he understands it, and then he can delegate more. So my sense is that DOGE is going to continue, it's just that Elon is shifting to a mode where he can manage it 1 day a week or 2 days a week, as opposed to being there 5 days a week.” Source: stevenmarkryan, David Sacks

DAVID SACKS: ELON ISN’T LEAVING DOGE - HE’S SHIFTING TO STRATEGIC MANAGEMENT “I saw this before when I was part of the Twitter transition - for the first 3 months or so, he was basically full-time at Twitter HQ, learning the business down to the database level. Once he felt he had a mental model and he had the people in place that he trusted, he can move to more of a maintenance mode. He has these intense bursts where he focuses on something, gets the right people and structure in place, feels like he understands it, and then he can delegate more. So my sense is that DOGE is going to continue, it's just that Elon is shifting to a mode where he can manage it 1 day a week or 2 days a week, as opposed to being there 5 days a week.” Source: stevenmarkryan, David Sacks

Mario Nawfal

2,390,205 次观看 • 1 年前

There's a new AI-native IDE out there named Aide, and there are four things I like about it: 1. It's open-source 2. It's proactive and suggests changes before you ask 3. It uses an intermediate layer between the editor and LLM 4. It's SOTA on the SWE-Bench benchmark I'm excited about #3 because this layer (called "Sidecar") will help people connect any model to the IDE. While this isn't possible right now, it's clearly the goal. Sidecar is also open-source. As I write this, the code agent behind Aide, "CodeStory Midwit Agent," is second in the Verified SWE-Bench leaderboard (it finished in 2024 in the first place.) This is a huge deal! If I'm gonna have an agent help me code, it might as well be the best of the best. The proactive aspect is also cool: the IDE provides suggestions to improve your code without you having to ask. I recorded a quick video showing you how Aide works. The team behind the IDE partnered with me on this video. Right now, it feels like *everyone* is building AI-powered coding tools. As a career developer, nothing excites me more than seeing how quickly we transform the development experience. And 2025 is just getting started!

There's a new AI-native IDE out there named Aide, and there are four things I like about it: 1. It's open-source 2. It's proactive and suggests changes before you ask 3. It uses an intermediate layer between the editor and LLM 4. It's SOTA on the SWE-Bench benchmark I'm excited about #3 because this layer (called "Sidecar") will help people connect any model to the IDE. While this isn't possible right now, it's clearly the goal. Sidecar is also open-source. As I write this, the code agent behind Aide, "CodeStory Midwit Agent," is second in the Verified SWE-Bench leaderboard (it finished in 2024 in the first place.) This is a huge deal! If I'm gonna have an agent help me code, it might as well be the best of the best. The proactive aspect is also cool: the IDE provides suggestions to improve your code without you having to ask. I recorded a quick video showing you how Aide works. The team behind the IDE partnered with me on this video. Right now, it feels like everyone is building AI-powered coding tools. As a career developer, nothing excites me more than seeing how quickly we transform the development experience. And 2025 is just getting started!

Santiago

69,422 次观看 • 1 年前

𝗖𝗵𝗶𝗻𝗮 𝗶𝘀 𝗳𝗶𝗻𝗶𝘀𝗵𝗶𝗻𝗴 𝘁𝗵𝗲 𝗵𝘂𝗺𝗮𝗻𝗼𝗶𝗱 𝗿𝗼𝗯𝗼𝘁 𝗿𝗮𝗰𝗲 𝗯𝗲𝗳𝗼𝗿𝗲 𝗺𝗼𝘀𝘁 𝗼𝗳 𝘁𝗵𝗲 𝗪𝗲𝘀𝘁 𝗿𝗲𝗮𝗹𝗶𝘇𝗲𝘀 𝗶𝘁 𝗵𝗮𝘀 𝘀𝘁𝗮𝗿𝘁𝗲𝗱. AGIBOT held its Partner Conference in Shanghai last week. The real headline wasn't the new hardware. It was their CTO standing on stage, telling investors that humanoid R&D season is over. 2026, he said, is "Deployment Year One." Not research. Not demos. Deployment into real factories, real warehouses, real stores. The manufacturing ramp is getting faster. 1,000 humanoid robots in the first 2 years. Another 4,000 in the next 12 months. Another 5,000 in just 3 months after that. AGIBOT is now shipping more humanoids per quarter than most US robotics companies have built in their entire existence. Then came the announcements the industry will spend the rest of the year reacting to. AIMA. The first full-stack open architecture for embodied AI. A unified robot operating system called Link-U, three dev platforms for motion, interaction, and task creation, plus an open agent framework. Any developer can build on top of it. This is the Android play for humanoids. GO-2. A vision-language-action foundation model with Action Chain-of-Thought reasoning. Planning and execution collapsed into one model. GE-2. A world model for simulation, strategy testing, and sim-to-real transfer. AGIBOT WORLD 2026. An open-source, production-grade real-world dataset pulled from actual industrial, logistics, hotel, and commercial sites. Seven standardized "productivity packages" covering logistics sorting, retail service, security patrol, commercial cleaning, and more. Plug, deploy, bill. A 5-year, $280 million commitment to seed a global developer and partner ecosystem. Now look at the competition. Boston Dynamics has been building humanoids since 1992. Tesla's Optimus is still climbing its own hype curve. Apptronik and Agility are well-funded but pre-scale on real deployments. AGIBOT has pulled all of this off in three years, with no acquisitions, no legacy platform, and no IPO distractions. While the West is still asking when humanoids will scale, China is already shipping them by the thousand.

𝗖𝗵𝗶𝗻𝗮 𝗶𝘀 𝗳𝗶𝗻𝗶𝘀𝗵𝗶𝗻𝗴 𝘁𝗵𝗲 𝗵𝘂𝗺𝗮𝗻𝗼𝗶𝗱 𝗿𝗼𝗯𝗼𝘁 𝗿𝗮𝗰𝗲 𝗯𝗲𝗳𝗼𝗿𝗲 𝗺𝗼𝘀𝘁 𝗼𝗳 𝘁𝗵𝗲 𝗪𝗲𝘀𝘁 𝗿𝗲𝗮𝗹𝗶𝘇𝗲𝘀 𝗶𝘁 𝗵𝗮𝘀 𝘀𝘁𝗮𝗿𝘁𝗲𝗱. AGIBOT held its Partner Conference in Shanghai last week. The real headline wasn't the new hardware. It was their CTO standing on stage, telling investors that humanoid R&D season is over. 2026, he said, is "Deployment Year One." Not research. Not demos. Deployment into real factories, real warehouses, real stores. The manufacturing ramp is getting faster. 1,000 humanoid robots in the first 2 years. Another 4,000 in the next 12 months. Another 5,000 in just 3 months after that. AGIBOT is now shipping more humanoids per quarter than most US robotics companies have built in their entire existence. Then came the announcements the industry will spend the rest of the year reacting to. AIMA. The first full-stack open architecture for embodied AI. A unified robot operating system called Link-U, three dev platforms for motion, interaction, and task creation, plus an open agent framework. Any developer can build on top of it. This is the Android play for humanoids. GO-2. A vision-language-action foundation model with Action Chain-of-Thought reasoning. Planning and execution collapsed into one model. GE-2. A world model for simulation, strategy testing, and sim-to-real transfer. AGIBOT WORLD 2026. An open-source, production-grade real-world dataset pulled from actual industrial, logistics, hotel, and commercial sites. Seven standardized "productivity packages" covering logistics sorting, retail service, security patrol, commercial cleaning, and more. Plug, deploy, bill. A 5-year, $280 million commitment to seed a global developer and partner ecosystem. Now look at the competition. Boston Dynamics has been building humanoids since 1992. Tesla's Optimus is still climbing its own hype curve. Apptronik and Agility are well-funded but pre-scale on real deployments. AGIBOT has pulled all of this off in three years, with no acquisitions, no legacy platform, and no IPO distractions. While the West is still asking when humanoids will scale, China is already shipping them by the thousand.

Shruti

214,939 次观看 • 3 个月前