Last year I got locked out of my apartment in Japan.
The host only picked up the phone — in Japanese. I don't
speak it. I stood outside for an hour.
So I'm building what I needed: you call, you speak English,
they hear Japanese — live.
Early access → https://t.co/To9CYv8fdi
Quick notes from this version:
• The first 6 seconds (the freeze) is the strongest part.
• The window shot showing the empty table works well.
• The final smile when it clicks is the payoff.
• But the breaths across the cut (S1 + dialing + final exhale) stack up more than intended.
AI video is still shot-strong and edit-weak on rhythm.
Shipping this one to see if the core story lands.
Would love honest feedback.
First cut of the restaurant story.
"The restaurant picked up — in Japanese."
"I froze. Couldn't say one word."
43 seconds, fully AI-generated + music.
Individual shots were okay. After cutting it together, the sighing and relief breaths became really obvious — too many of them.
Posting it anyway.
Build in public.
This is the actual wall: some of the best Japanese counters only take phone reservations. You stand outside, they answer in Japanese, and the table you flew for starts slipping away.
Yovoca is for when you want to make the call yourself — in your own voice.
Early access concept.
The guide with the real phrases: https://t.co/lNRPgJoT4s
v2 will have tighter breathing and pacing.
#travelproblems #travelhacks #aitools #translation #Yovoca
You're outside your Airbnb in Kyoto at 11pm.
The door code isn't working. The host isn't texting back —
just a number to call. It rings in Japanese.
That's the call Yovoca's for: you call, speak English, hear
the host back live, and get inside.
Early access → https://t.co/8DWUNw6gYb
Last year I got locked out of my apartment in Japan.
The host only picked up the phone — in Japanese. I don't
speak it. I stood outside for an hour.
So I'm building what I needed: you call, you speak English,
they hear Japanese — live.
Early access → https://t.co/To9CYv8fdi
You booked a rental car in Japan.
Pickup morning, your phone rings — the rental desk, in
Japanese. You catch one word in ten.
That's the call Yovoca's for: you answer, speak English,
hear the reply live, and sort it out yourself.
Early access → https://t.co/To9CYv8fdi
You find the perfect izakaya in Tokyo.
Great reviews, counter seats, you're set.
Then: "Reservations by phone only." In Japanese.
You don't need a concierge to do it for you. You call
yourself — speak English, they hear Japanese, live.
Early access → https://t.co/To9CYv8fdi
I build the website before you pay.
Not a mockup — your real page. Your photos, your Google
reviews, your booking button. You see it first, then decide
if it's worth $499.
Nail studios, restaurants, roofers, barbers, and more.
Want yours? Reply with your business + city 👇 https://t.co/ntgDz4ouus
🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length.
🔹 DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top closed-source models.
🔹 DeepSeek-V4-Flash: 284B total / 13B active params. Your fast, efficient, and economical choice.
Try it now at https://t.co/GCdiMzk1Dl via Expert Mode / Instant Mode. API is updated & available today!
📄 Tech Report: https://t.co/drlDrxkYtp
🤗 Open Weights: https://t.co/T13Y8i7SDM
1/n
Introducing Claude Opus 4.7, our most capable Opus model yet.
It handles long-running tasks with more rigor, follows instructions more precisely, and verifies its own outputs before reporting back.
You can hand off your hardest work with less supervision.
Computer use is now in Claude Code.
Claude can open your apps, click through your UI, and test what it built, right from the CLI.
Now in research preview on Pro and Max plans.
🎉 Just sponsored OpenClaw on GitHub — an awesome open-source AI assistant worth supporting!
If you love OpenClaw but hate the self-hosting headache, check out 👉 https://t.co/Gaz4yEdUUT — one-click deployment, zero config, up and running in under a minute.
Go sponsor your open source dependencies! 💙
#OpenSource #OpenClaw #AI
https://t.co/ni6mr3Bwhs
🎉 Just sponsored OpenClaw on GitHub — an awesome open-source AI assistant worth supporting!
If you love OpenClaw but hate the self-hosting headache, check out 👉 https://t.co/Gaz4yEdUUT — one-click deployment, zero config, up and running in under a minute.
Go sponsor your open source dependencies! 💙
#OpenSource #OpenClaw #AI
https://t.co/ni6mr3Bwhs
🎉 Just sponsored OpenClaw on GitHub — an awesome open-source AI assistant worth supporting!
If you love OpenClaw but hate the self-hosting headache, check out 👉 https://t.co/Gaz4yEdUUT — one-click deployment, zero config, up and running in under a minute.
Go sponsor your open source dependencies! 💙
#OpenSource #OpenClaw #AI
https://t.co/ni6mr3Bwhs
Day-1 support 🟧
MiMo-V2-Pro & Flash are now live on OpenClawUP.
Near Opus-level agent performance at 1/15th the cost — deploy your OpenClaw AI assistant with MiMo in 60
seconds.
11 models. One click. Free 3-day trial.
Try it → https://t.co/Gaz4yEdUUT
Feedback welcome — DM or reply!
The mystery is solved — Hunter Alpha was Xiaomi's MiMo-V2-Pro all along.
Quietly listed on OpenRouter March 11, topped the charts for a week, 1T+ tokens consumed, everyone assumed it was DeepSeek V4. Nope. It's from Fuli Luo's team at @XiaomiMiMo.
We've added both MiMo models to OpenClawUP:
⚡ MiMo-V2-Flash — SWE-bench #1 open-source, fraction of the cost
🔥 MiMo-V2-Pro — 1T params, 1M context, Claw-Eval top 3
Still early — would love feedback from anyone who tries them out. Let us know what works and what doesn't 🙏
MiMo-V2-Pro & Omni & TTS is out. Our first full-stack model family built truly for the Agent era.
I call this a quiet ambush — not because we planned it, but because the shift from Chat to Agent paradigm happened so fast, even we barely believed it. Somewhere in between was a process that was thrilling, painful, and fascinating all at once.
The 1T base model started training months ago. The original goal was long-context reasoning efficiency. Hybrid Attention carries real innovation, without overreaching — and it turns out to be exactly the right foundation for the Agent era. 1M context window. MTP inference for ultra-low latency and cost. These architectural decisions weren't trendy. They were a structural advantage we built before we needed it.
What changed everything was experiencing a complex agentic scaffold — what I'd call orchestrated Context — for the first time. I was shocked on day one. I tried to convince the team to use it. That didn't work. So I gave a hard mandate: anyone on MiMo Team with fewer than 100 conversations tomorrow can quit. It worked. Once the team's imagination was ignited by what agentic systems could do, that imagination converted directly into research velocity.
People ask why we move so fast. I saw it firsthand building DeepSeek R1. My honest summary:
— Backbone and Infra research has long cycles. You need strategic conviction a year before it pays off.
— Posttrain agility is a different muscle: product intuition driving evaluation, iteration cycles compressed, paradigm shifts caught early.
— And the constant: curiosity, sharp technical instinct, decisive execution, full commitment — and something that's easy to underestimate: a genuine love for the world you're building for.
We will open-source — when the models are stable enough to deserve it.
From Beijing, very late, not quite awake.
@mktpavlenko@saviomartin7 Agreed — real users = real bugs. We've been deep in the same OpenClaw trenches. Whole ecosystem benefits when multiple teams push through the rough edges.
@samuelchenard@saviomartin7 That's literally what we're building. OpenClawUP = one click, no Docker, no SSH, no config files. Pick your channels, hit deploy, done.
Free 3-day trial, no card: https://t.co/vfFALhDQrs
Let me know if you try it — always looking for honest feedback.