Johnny Hacking

@Lovable @readwise save

Lovable's Google connectors are live. You can now build full-stack apps that talk directly to data from Google: Gmail, Calendar, Drive, Sheets, Slides, Maps, Gemini Enterprise, and BigQuery.

@trq212 @readwise save

@derrickcchoi @readwise save

My colleagues wrote up a great post on using Goals in Codex. They go through when to use them, what changes when a Goal is active, and how to write Goals that give Codex a clear outcome, constraints and verification criteria. Also how we designed Goals at the architecture level if you’re curious. developers.openai.com/cookbook/examp…

@HeyGen @readwise save

Last week we showed educators how to make lessons more engaging with Avatar Shots Now turn that cinematic intro into long-form content with Avatar V Create a natural “portal” between scenes, stitch it in AI Studio, and make it feel like one continuous shot Full prompt below ↓

@MyCreativeOwls @readwise save

lovablecookbook.com - Search for SKILLS Copy and paste Security Audit Supabase RLS Audit Deep Debug Pre-Launch Checklist Mobile Responsive Audit Performance & Lighthouse Audit

Breaking: @Lovable just released SKILLS Here are my 6 skills you can use today 👇

@HeyGen @readwise save

Avatar V now takes direction Custom Motion let you cue specific motions, expressions and gazes → A lean-in before a key point → A smile for emphasis → A thumbs up at the end Whatever the moment calls for, just type it

@nickbaumann_ @readwise save

My laptop has become a “satellite device” since I started using Codex from my phone. And my Mac mini has become the “home.” It’s clunky, but the end state feels more like how we’re going to be working in the near future: I’m currently running the Codex app on 2 devices: 1. my MacBook 2. my Mac mini My laptop isn’t reliably connected to Wi-Fi enough, so I keep a Mac mini on my desk that is always connected. When I kick off new threads from my phone, I start them on the Mac mini. When I’m working from my desk, I run them there too. The cool part is that I’ve added my MacBook and Mac mini as connected devices to each other. That means I can start and resume threads from either device. So if I’m in a meeting but want to continue a thread on my laptop that was started on my Mac mini, I can do that. I’ve also set up mutual SSH for Mac mini <> MacBook, so files are easy to access from either side. It’s not fully seamless yet, but the model works. What this means: - I have an always-on Codex that is accessible from my phone, with its own dev environment - All threads are always accessible from any of the 3 devices - I can run heartbeat threads that stay on 24/7 It’s a little makeshift today, but the shape of it feels very real to me: Codex is no longer tied to whichever computer happens to be open in front of me. It starts to feel like something I can stay connected to across whatever device I’m using.

@nickbaumann_ @readwise save

@googleaidevs @readwise save

We’re expanding the Gemini API File Search tool 🔍 with 3 new updates that enable developers to more easily build multimodal RAG systems with enhanced precision: + Multimodal Support: By leveraging our Gemini Embedding 2 model, File Search can now reason across image and text simultaneously. + Custom Metadata Filtering: Bring structure to unstructured data by tagging files with custom key-value labels. This pre-filters your data and boosts search speed. + Exact citations: File Search can now capture and return the exact source (down to the page number) for every piece of information indexed. See multimodal File Search in action with our example app in @GoogleAIStudio. Chat with your entire image and doc library, ask questions, and trace answers back to the source: goo.gle/4tKSz1k

@MatthewBerman @readwise save

New Agent Kit: Excalidraw Diagram Create Excalidraw diagram JSON files that make visual arguments journeykits.ai/browse/kits/cl…

@patloeber @readwise save

Excited to launch multimodal support in the Gemini API File Search tool🚀 You can now use Gemini Embedding 2 to embed & store images & documents, which makes it super simple to create RAG systems! Plus, we can now cite page numbers! I created a developer guide & starter app👇

@HeyGen @readwise save

We had 15 launches in April But when you zoom out, the one story all of it tells is this: Video is becoming the standard for communication Your agent can generate it Your meetings can become it And your content can localize into 175 languages ICYMI, here’s the April recap

@Lovable @readwise save

Today we’re releasing the Lovable MCP server in Research Preview. Create, iterate on, and deploy apps directly from your terminal or AI agent. Available now.

@AiwithYasir @readwise save

🚨 Google just dropped official skills for AI agents. 13 skills. Compatible with Claude Code, Cursor, Copilot, and more. They let agents execute advanced tasks and automate complex workflows. Free and 100% open-source:

@Mnilax @readwise save

the bottleneck Karpathy keeps pointing at isn't the model. it's the file you wrote three months ago telling it how to work. his whole framing: code isn't the verb anymore. > you express your will to agents 16 hours a day. > running more of them in parallel is the unlock. > and he drops this line halfway through, no fanfare: "now you can have optimization over the instructions." that's the sentence. the instructions are the new bottleneck. and almost nobody has a process for optimizing them. i built one for myself. it reads 100 of my past Claude Code sessions and rewrites my CLAUDE.md from what the transcripts show, not from what i thought i wrote. one Saturday morning later: a 38-line memory file. 73% of my old CLAUDE.md got deleted. most of it was one-off corrections that hardened into permanent rules months ago and were quietly steering every agent i ran. four behavior patterns surfaced that i had never written down. the loudest one: my prose corrections outnumber code corrections 8.2 to 1. that ratio was running silently through every session for 90 days. you don't need a smarter model. you need an instruction file that still describes how you actually work. listen to the podcast for the framing. open the article for the script that does the optimization.

@sairahul1 @readwise save

Karpathy just described what hiring looks like in 2026: "Build a large project with Claude Code — like a Twitter clone. Make it secure. Have real agents using the platform doing stuff. The interviewer uses parallel agents trying to break in to verify security." One person. Multiple agents. Shipping and defending production code simultaneously. This is not a future job description. This is happening right now. The founders who get there first are not the smartest ones in the room. They are the ones who stopped doing everything themselves and built agents to do it for them. Here is the complete playbook — 13 agents, exact prompts, 90-day build plan ↓ Read this before your competition does.

@kimmonismus @readwise save

So OpenAI literally kill*d many fintech startups today OpenAI launched a personal finance feature in ChatGPT for Pro users in the US. You connect your bank accounts via Plaid, get a spending dashboard, and can ask GPT-5.5 questions grounded in your actual transaction data - balances, spending patterns, subscriptions, investments. It can't see full account numbers or move money. Intuit integration is coming for things like tax estimates and credit card applications. Financial memories store context like savings goals across conversations. Plus users get it later, free tier eventually. They built an internal benchmark with 50+ finance professionals and say GPT-5.5 Thinking scores 79/100, GPT-5.5 Pro 82.5/100 on complex personal finance tasks.

@OpenAIDevs @readwise save

We’re having way too much fun working through your feedback. (Please, keep it coming.) Keyboard shortcuts are now customizable. Set Codex up around how you actually work, then tweak shortcuts from settings instead of adapting to our defaults.

@BenjaminBadejo @readwise save

It’s here: Try VoiceClaw Realtime on iOS and watchOS now! Download TestFlight for free on iOS, then use the link in the replies to download the latest beta via TestFlight, as well as the macOS Companion app. To get started after downloading TestFlight and installing the app: Add an optional OpenAI API key in the macOS Companion app or directly in the iOS app. Even better, if you have OpenClaw installed, no API key is needed; you can connect VoiceClaw Realtime to OpenClaw’s OpenAI connection via the macOS Companion app simply by entering the path to your “~/.openclaw” directory. It’ll generate a connection token that your phone can use to reach OpenAI models and automatically use your OpenAI ChatGPT Plus/Pro subscription via OAuth. Sync your settings from the macOS Companion app to the iOS app via the iOS in-app QR code reader. If you also want to try the Apple Watch app, which installs automatically or via the iOS Watch app, make sure to sync your settings to the watch app via the in-app “Sync to iPhone” button. Enjoy real-time conversations with GPT-Realtime-2, GPT-5.5-Instant, and OpenClaw on both iOS and watchOS now. VoiceClaw Realtime is likely coming to the App Store soon, so download the beta now while it’s free. On iOS, the OpenClaw modes (“iPhone”) route your requests from GPT-Realtime-2 to OpenClaw if you have Tailscale installed on your phone and macOS device, enabling full OpenClaw capabilities. GPT-Realtime-2 has been enhanced with lots of direct, on-device iOS features, so ask it what it can do on your phone, even without contacting OpenClaw. Also try GPT-5.5-Instant mode by going to the iOS app settings and choosing “Instant” in the route options. It gives you lightning-fast, in-depth responses from a hybrid GPT-Realtime-2 conversation partner that uses GPT-5.5-Instant, for when you just need good answers (including from Instant's web-search capabilities) but don’t want to connect to your OpenClaw agent. Please provide feedback here on X, via the iOS TestFlight app, or by email. See the link in my bio. Feedback is strongly encouraged. And please comment in the replies to let me know you’re trying it out! P.S.: Version 1.4.45 is available now, and an even better beta, version 1.4.58 / 1.4.59, will be available via TestFlight at the same link by 3:00 PM ET.

@_vmlops @readwise save

OPENAI MADE AI AGENTS REUSABLE codex now supports "skills" folders of instructions & scripts that agents can pick up & use on their own you write a skill once and it works across any project... no rewriting the same logic every time system skills come pre-installed & you can add more with a single command think of it like a package manager, but for ai agent capabilities github.com/openai/skills