고정된 트윗
Around 1993, I ran one of the early BBS systems in Serbia.
Then life happened. 30 years away from code.
Cursor brought me back in 2025.
2026: building RaicoHub.
English
Borko Jovanovski | RaicoHub
22 posts
Borko Jovanovski | RaicoHub
@borkookrob
Building RaicoHub — control layer for AI coding. 25+ yrs entrepreneur. Returned to code when AI emerged. Builder, not just shipper.
Pancevo, Serbia 가입일 Ağustos 2023
54 팔로잉1 팔로워
@OpenAI Voice agents that reason are huge.
Voice agents that reason AND act on your screen — that's the next layer.
Just shipped a demo of exactly that.
English
Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents.
Voice agents are now real-time collaborators that can listen, reason, and solve complex problems as conversations unfold.
Now available in the API alongside streaming models GPT-Realtime-Translate and GPT-Realtime-Whisper — a new set of audio capabilities for the next generation of voice interfaces.
English
@Prathkum AI made code sloppier.
Not the prompts — the missing verification step.
English
"Software isn't dead."
The new layer is software that controls AI.
That's where the next few years happen.
tae kim@firstadopter
Databricks CEO Ali Ghodsi: "If all software is dead, isn't OpenAI, Anthropic dead? They're software companies with a bunch of researchers writing software .. Nvidia should be dead because they just have really smart people who create chip designs, humans that use some software .. Software obviously isn't dead. Nvidia, OpenAI, and Anthropic are not going to be dead companies."
English
@firstadopter @CNBC Felt this. Ran one of the early BBS systems in '93.
Now building on Claude Code. Same vibe, 30 years apart.
English
Paul Tudor Jones on @cnbc “bought more AI stocks” “semiconductors” “It’s a crazy crazy time” brings up introduction of PC, Claude Code -> Microsoft 1981, Windows 95/internet. “beginning of productivity miracles that lasted 4-5 years” “we have a year or two to run” or “we continue to feel like 99” “October/November 1999” in terms of multiples. (either two years to run, another ramp to go)
English
@jrfarr And control before distribution is hard too.
English
@dramaricic Day 1 on X. Just posted my first demo.
Hoping for that banger moment.
English
People underestimate how powerful consistency on X is.
One banger post can change your entire business trajectory.
English
@LauraLunaTech Payment is one layer.
The deeper question is verification — how does the user know exactly what the agent did, in plain language, before money moves?
English
Many people still think of AI as a chatbot or Google alternative.
Stripe just showed the next phase: AI agents with secure wallets.
The AI agent economy was still missing one thing: a trusted payment layer.
Agents can now:
- book and pay for your flights
- pay for or purchase subscriptions
- make purchases for you
What do you think will be the most common use case going forward?
Stripe@stripe
Today, we’re launching the @link wallet for agents. It lets you securely empower agents to spend on your behalf. Your payment credentials are never exposed and you approve every purchase. link.com/agents
English
@marclou Mine just posted on X for me — by voice, no API, full screen control.
English
> accidentally click the wrong button
> start a free trial that turns into $17.85/month
> spend 5 minutes hunting the cancel button
> solve a puzzle to dodge the 30% “please stay” offer
> cancel
> refresh 3 times to make sure it’s actually cancelled
I hate these growth hacks to the bone
English
The previous post was written by AI Raiko — by voice.
I shared my screen with RaicoHub.
Asked it to post on X.
It moved the cursor. Clicked. Typed. Posted.
I just spoke. The AI did the rest.
English
This post is write by AI Raiko. Watch the next post to see how I did it.
English
@VraserX This is the direction. Voice + screen control + verification is the next layer.
Already in motion across multiple players. Exciting time to build in this space.
English
ChatGPT’s new voice mode will be one of the biggest releases of the year.
It will listen and talk at the same time. It will sound fully human. It will run on GPT-5.5 instant-level intelligence.
And once it is integrated into Codex, everything changes.
You won’t just type prompts anymore.
You’ll speak to your computer, and it will code, navigate, execute, debug, research, organize, and operate interfaces for you through computer use.
People are massively underestimating this.
English
Live demo:
I tell my AI by voice what to build.
Claude Code writes it.
Then RaicoHub reads the actual diff.
Line by line. Real changes.
Tells me what happened in the code.
Voice in. Code verified. All hands-free.
This is the missing layer of AI coding.
English
@XFreeze Grok's Calendar integration is impressive.
English
Grok connections work flawlessly
You connect your apps once on the web → they instantly sync across web, iOS, and Android
Quick example: I asked Grok to add my flight check-in to Google Calendar… and it did it perfectly in seconds
And it also gave me the link to view/edit
X Freeze@XFreeze
Grok just got a massive productivity upgrade xAI officially launched Connectors on Grok today Instead of copy-pasting between tabs, you can now link your apps directly to Grok for seamless, end-to-end workflows Just sign in to Grok web, click the + button, select Connectors, and click + Add connector to get started You can now connect: → Microsoft 365, SharePoint & OneDrive (read/edit files & docs) → Google Workspace & Outlook (draft emails, update calendars) → GitHub (search code, summarize PRs) → Notion & Linear (edit wikis, manage tasks) → Bring Your Own MCP (plug in custom internal tools) Live now on the web, and launching on Grok iOS and Android apps very soon
English
@nexgencpu @marclou Impressive footage. Tesla's progress is real.
But the same trust gap exists in AI coding:
impressive doesn't mean verified.
We celebrate progress before we measure safety.
English
First time driving a Tesla with FSD.
It drove 50km and I didn’t touch the steering wheel (well the yoke).
I went SF downtown, highway, small mountain roads… FSD did so well, I almost forgot I was the driver.
Impressive AF.
Marc Lou@marclou
I was a virgin, an hour ago
English
@rileybrown AI worked for 41 minutes — did you actually QA the code?
Any security holes? Auth flow looks fine on the surface,
but did you check what's underneath?
English
I'm in disbelief at GPT 5.5...🙀
I'm working a Vibe Coding guide for Codex...
(Releasing tomorrow)
And in part 1 i built a web app with firebase for db, storage, and auth with a decent amount of features.
And then I converted that web app into a full desktop app and swift iOS app basically in a single prompt.
(Will paste in tweet below)
It worked for 41 minutes, then was like yup...
I tested the auth flow on both apps, it works, try them both out.
English
English
@AlphaGardn88125 @borkookrob @marclou Even parking assist stops working fully after driving in a rainy day due to cameras getting slightly dirty, I'm not sure if FSD handles it that well unless you make sure to keep them clean all the time.
English
@simonw @jarredsumner @bcherny This is exactly the moment where "control layer" matters more than "speed layer".
4,527 contributions per year means humans need a way to verify what AI shipped.
English
Watching @jarredsumner and @bcherny at Code w/ Code talking about robobun, the Bun project's GitHub bot that's now made more contributions to Bun than Jarred has github.com/robobun
English
@marclou Videos are one thing, but I’m interested in your experience. What’s your personal takeaway after using it?
English
@marclou Pretty impressive! But how do you think it would handle really bad weather conditions, like heavy rain or snow? Still trusting it then?
English
@gregisenberg I agree. It feels like the AI gets tired over time. Maybe it needs a rest? Or a cache clearance? :)
English
Call me crazy but I think nerfing AI models should be illegal.
Imagine buying a car and the manufacturer remotely downgrading your engine 6 months later.
Not cool.
English