Gilad
154 posts

Gilad
@GiladVent
How old you ask? Well i was writing code since before firebug.
Katılım Şubat 2020
97 Takip Edilen4 Takipçiler

🤖 Bring your own AI models to @code!
Connect models from providers you already use, run local models, and choose the right model for every workflow in VS Code.
📖 Read the full post: aka.ms/vscode/blog/by…

English

@ThePrimeagen May i ask if you were a kids person before becoming a father?
English

The api has stabilized drastically, we might have a few minor things moving forward but when it comes to stability its considered production ready, as long as you don't hit any bugs its good to be used.
With that in mind we're working hard internally to get stability woth e2e testing so we can move more rapidly and easily fix bugs which shoulf happen soon and drastically increase our velocity towards stable v1
English

LLMs are bad at math.
They’re bad at orchestration.
But they’re really good at writing TypeScript.
So we gave them a runtime.
Code Mode in TanStack AI lets the model write & execute TS instead of chaining tools.
🧠 1 call instead of N
⚡ parallel execution
📉 fewer tokens
✔︎ correct results
This changes how you build AI apps.
Blog ↓
tanstack.com/blog/tanstack-…
English

@forgecodehq How about a proper UI for those of us that doesn't like to work with a CLI?
English

@GutmanYotam @iloveisraell @MashaBleadov משטר רצחני שמכוון לאזרחים. מי שחושב שטילי מצרר נורים לעבר יעדים אסטרטגים לא מבין את הייעוד שלהם כלל.
עברית

@iloveisraell @MashaBleadov הוא לא טועה...
מי ירה לשם באופן רצוני?
עברית

@coreyhainesco yep, using bunx but still the same. the skills folder is installed but the tools folder, can see it anywhere.
English

@GiladVent Are you using the full npx command? Claude Code should be able to handle it for you even if you type it in wrong.
English

Peter Steinberger is joining OpenAI to drive the next generation of personal agents. He is a genius with a lot of amazing ideas about the future of very smart agents interacting with each other to do very useful things for people. We expect this will quickly become core to our product offerings.
OpenClaw will live in a foundation as an open source project that OpenAI will continue to support. The future is going to be extremely multi-agent and it's important to us to support open source as part of that.
English

@jarredsumner Do you think it is possible to get to a point where Bun is faster than Go, or the inherit compiled vs runtime thing
makes it impossible?
English

@DrizzleORM Then i would argue in favor of electron. It ships with a known version of chromium as the browser instead of whatever is bundled with the operating system in Tauri.
English

@GiladVent we don't care about size tbh, it's all about flexibility and ease of development/iterations
English

Introducing TanStack CAD! ... just kidding. But seriously this is jaw-droppingly awesome usage of so much tech. @SamWillis just raised the bar into outer space with this "demo".
Sam Willis@samwillis
New demo: collaborative AI CAD in the browser 🚀 Built with @ElectricSQL + Durable Streams + @tan_stack DB+AI+Start - ElectricSQL + DB: data sync - Durable Streams: presence + AI + CAD (Yjs!) sync - TanStack AI: AI for cad modelling 🤯 - Coded with @cursor_ai
English

@tan_stack query's useSuspenseQuery has such a terrible DX. God forbid you need a conditional or a sequential query.
English

Stop paying Arcads $11 for a single AI UGC video 🤯
Yeah, I just built my own Arcads inside Airtable.
Same features, fraction of the cost.
Perfect for e-comm brands & agencies who need AI UGC at scale without bleeding cash.
Here's the problem:
Arcads charges $11 per video (!!!)
Yeah, there's a reason you can't locate their pricing ANYWHERE on their homepage.
That's $110/month for just 10 videos.
If you're testing creative at any real volume, the math stops working fast.
So I built my own system:
→ Actor library with 30+ ready-to-use AI characters
→ Create custom actors with Nano Banana Pro
→ Generate variations (same character, different scenes)
→ Add products directly into your actor's hands
→ Quick mode: 8-second hooks via Veo 3.1
→ Extended mode: longer talking-head testimonials
→ B-roll generator for lifestyle clips
→ Direct integration with ElevenLabs to select any voice
The cost?
~40 cents per second for Veo 3 hooks.
~11 cents per second for AI avatar videos.
That's a few bucks per video vs. $11.
No monthly video caps.
No per-video pricing killing your margins.
I recorded a full 20-minute breakdown showing exactly how this works—the actor library, UGC generator, B-roll creator, everything.
Want to see the full walkthrough + learn how to get access?
> Comment "UGC"
> Like this post
And I'll send it over (must be following so I can DM)
English

@C_A_DOT_IO @antonvputra wow you really don’t understand how software works huh?
English













