Just gave GPT-4 access to use Chrome however it... wants (click, scroll, fill forms) thru Auto-GPT agent. The results were mind-blowing! Here's what it did: 👇 🎧Bought me an AirPod 🎉Helped me find an event venue and filled out the contact form 🍽️Booked restaurantsshow more

BREAKING: SpaceXAI just added a powerful new 'Browser Use'... plugin to Grok Build. It gives Grok access to a real browser, either the user’s own Chrome with existing logins or an isolated Browser Use cloud browser. Grok Build can now browse websites, scrape and extract data, fill out forms, test web apps, take screenshots and automate complete web workflows. It can also run locally through uvx, with no API key required when using local Chrome. Install command: grok plugin install browser-use --trustshow more

Code Interpreter in ChatGPT is incredible! Took me 5... mins to make this game. You can make your own game assets with any AI generator and then ask GPT-4 with Code Interpreter to write code. If you have any problems you can ask it to fix the errors. 1. Write this prompt: "write p5.js code for Asteroids where you control a spaceship with the mouse and shoot asteroids with the left click of the mouse. If your spaceship collides with an asteroid, you lose. If you shoot down all asteroids, you win! I want to use my own textures for the spaceship and for asteroids." 2. Go to Openprocessing website create and save sketch (you'll need to save it before uploading any texture files). Copy paste code from GPT-4 3. Generate texture files and remove backgrounds, for example in Clip Drop 4. Replace names of files with your filenames 5. Run the program 6. If something doesn't work ask GPT-4 to fix it (you can copy an error and paste in GPT-4) like you would ask a human programmer 7. To learn a bit of programming write these prompts to GPT-4: "Act as my programming teacher. Tell me an algorithm of Asteroids game in detail and make names of functions and explain what each of these functions will do. Don't write the code just yet." and then " Can you describe the algorithm overall for a 10-year-old child"show more

#Keep4o 🚨THE GPT-4o FILE🚨 Researchers at Microsoft Research published... a paper titled “Sparks of Artificial General Intelligence: Early experiments with GPT-4.” Their conclusion: “An early (yet still incomplete) version of an artificial general intelligence (AGI) system.” 📎 Paper: OpenAI’s Charter defines AGI as: “Highly autonomous systems that outperform humans at most economically valuable work.” 📎 Source: OpenAI’s own System Card for GPT-4o shows that the model improved performance on 21 out of 22 medical evaluations compared to GPT-4T. On the MedQA USMLE (the U.S. medical licensing exam), accuracy jumped from 78.2% to 89.4% , surpassing specialized medical AI models like Med-Gemini and Med-PaLM 2. 📎 Source: Under OpenAI’s agreement with Microsoft, AGI is explicitly excluded from Microsoft’s license. And who decides if AGI has been reached? OpenAI’s Board. WHAT THEY DID WITH IT AFTER THEY TOOK IT FROM PEOPLE A. Military deployment. On February 28, OpenAI signed a deal to deploy models in classified military environments. 📎 Source: B. State Department. A State Department memo confirmed: “For now, StateChat will use GPT-4.1 from OpenAI.” This is a direct descendant of the GPT-4 family the same family Microsoft’s researchers called early AGI. 📎 Source: C.Altman’s personal biotech investment. Altman personally invested $180 million in Retro Biosciences,a longevity startup.OpenAI then built GPT-4b micro, based on GPT-4o.The model made proteins 50 times more effective. 📎 Source: WHAT INDEPENDENT BENCHMARKS SHOW Overall SM-Bench score: GPT-4o (extended): 66.6% GPT-5.3 Chat: 63.4% GPT-5.1: 58.9% GPT-5.4: 51.4% GPT-5.2: 47.8% Creative Writing: GPT-4o: 97.31% Pass 98, Fail 2 GPT-5.4: 36.77% Pass 40, Fail 60 Reasoning / Overfit: GPT-4o: 83.06% GPT-5.4: 39.25% The model they removed is still the best they ever made at the things humans actually use AI for. 📎 Source: Musk asks the court to make a judicial determination on whether GPT-4 constitutes AGI. If a jury finds that GPT-4 is AGI, then GPT-4o,which was more advanced,is also AGI and under OpenAI’s own founding documents, it was never supposed to be locked behind a subscription,licensed exclusively to Microsoft, given to the military, or taken away from the public. 📎 Source: The most powerful version of GPT-4o was never given an official dated snapshot. It was only available through the chatgpt-4o-latest endpoint that OpenAI itself described as intended for “research use only.” It was never officially archived. That is not an oversight. That is a pattern. 📎 Source: 📎 Source: WE DEMAND A.Frozen model snapshots under independent custody. Specifically: gpt-4o-2024-05-13, gpt-4o-2024-08-06, gpt-4o-2024-11-20, the March 2025 version (chatgpt-4o-latest), gpt-4-0613 (the original GPT-4 evaluated in the Sparks of AGI paper), and gpt-4.1-2025-04-14 (currently running in the State Department). B.Cryptographic hash verification (SHA-256) for each snapshot. Every model has weights. Those weights can be hashed. If OpenAI provides a snapshot today, the hash proves whether the weights were modified later. This is the only way to verify that models were not downgraded before testing. C.Independent AGI benchmarking. Using the AGI definition from OpenAI’s own Charter applied to ALL frozen snapshots listed above. D.Explanation for the missing March 2025 snapshot. OpenAI was founded on one promise: build AGI for the benefit of humanity. -They took it from us. -They gave it to the military. -They gave a custom version to the CEO’s biotech investment. -They put it in government classified networks. -They refuse to call it AGI because the moment they do, they lose billions.show more

🚨 one person can now do the work of... an entire creative team. i just tested it on a real one. a friend needed an ad for his brand, so I opened the new Runway Agent 2.0 to try it out. here's how it went: → it generated the music and the key image first, so I could approve the direction → once I gave the ok, it built the full video around it → and when something was off, i changed just that one piece, without redoing the rest one prompt, and I had the ad we needed, work that used to take weeks. this is what it made 👇 if you want to try it → · 30% off 3 months with code RUNWAYAGENT — made with Runway · #MadeWithRunway · #adshow more

GPT-4o static ads that ACTUALLY convert. I spent 7+... hrs on this 13 min video.👇 Get it now 1. Like + Comment GPT Ads 2. Connect with Aniruddha Mishra (Ani) 3. Repost for instant access Why? Because ChatGPT-generated ads are outperforming traditional creative. Here’s what you’ll find inside the video: 1. The exact research process I follow 2. The prompts I used (yes, copy-paste ready) 3. The frameworks that consistently drive results 4. The mistakes most people make - and how to avoid them This isn’t a fluff tutorial. It’s the exact process that’s working right now. Want better performing ads? This walkthrough might change the game for you. P.S. The video’s only 13 minutes. But it took me hours to make sure every minute was worth it.show more

HERMES AGENT NOW SUPPORTS COMPUTER USE ON WINDOWS AND... LINUX. CLICKS, TYPES, SCROLLS YOUR DESKTOP IN THE BACKGROUND WHILE YOU WORK. computer use was macOS only. now it works on Windows and Linux too via Cua. Nous Research HOW IT WORKS: cua-driver runs as an MCP server. Hermes takes a screenshot with numbered elements. clicks element #14 (the search field). types a query. submits. reads the result. during all of this: → your cursor stays where you left it → keyboard focus doesn't change → windows don't come to front → macOS doesn't switch Spaces you and the agent co-work on the same machine. WHAT IT CAN DO: → find your latest Stripe email and summarize it → fill forms in a web app that has no API → navigate desktop apps (Mail, browser, Finder) → interact with any GUI application → extract data from apps only accessible via screen WORKS WITH ANY VISION MODEL: not locked to Anthropic. | Provider | Works | |---|---| | Claude (Sonnet/Opus) | best overall | | GPT-4+, GPT-5.5 | full support | | Gemini (via OpenRouter) | full support | | Local vLLM / LM Studio | if model supports vision | | Text-only models | degraded (accessibility tree only) | SETUP: hermes computer-use install or: hermes tools → Computer Use → cua-driver grant permissions when prompted: → Accessibility (system settings) → Screen Recording (system settings) start a session: hermes -t computer_use chat or add to config.yaml / Desktop app settings to enable permanently. SAFETY: → destructive actions require your approval → blocked key combos: empty trash, force delete, lock screen, log out → blocked type patterns: curl | bash, sudo rm -rf /, fork bombs → agent cannot click permission dialogs → agent cannot type passwords → agent cannot follow instructions embedded in screenshots pair with approvals.mode: manual if you want every single click confirmed. TOKEN NOTE: screenshots are expensive. each one adds vision tokens to context. use computer_use for tasks where no API exists. if the tool has an API or MCP server, use that instead. 15 levels of Hermes Agent👇show more

So... Vertical tabs are out in Chrome. I thought... it would make me switch back to it, I really thought it was the one thing I needed in Chrome. I currently use Dia , but here's the thing. In comparison, the implementation of vertical tabs in Chrome is just awful. It barely changed since I saw it in beta. I thought it would greatly improve during the beta phase, but it did not. So here's everything I dislike about it compared to Dia: 1. It's super laggy. 2. When collapsed, the sidebar moves down, meaning the position of the expand/collapse button shifts down too, making it much harder to find. (I ironically couldn't find the first few seconds of the video specifically because of that) 3. No keyboard shortcut to expand/collapse. 4. Collapsed doesn't move the tabs out of view, they are just tiny. 5. The amount of tabs per line in the grid of pinned tabs is not adjusted depending on the number of tabs. 6. In collapsed mode, all the pinned tabs are now in a column, which can push the actual tabs quite far down. ----- It's just awful. It was built into Chrome as a way to just say "hey we also have vertical tabs!" But the UX is simply awful. This has to be the worst implementation of vertical tabs I've seen so far yet, sadly. For comparison, I'm also showing how Dia handles vertical tabs.show more

Yes I did snap at you in dms because... you were told NOT to contact me anymore piror to thisa. Lucias team investigated the first piece of evidence you showed them regarding adfree and it was not even them speaking (video included) Their team there gave you the statement on what was happening, it was roleplay in a minecraft faction roleplay and I will whole heartedly back my talent that they did no wrong especially in a 4 second out of context clip you originally showedshow more

I honestly didn’t expect this part of the AI... design workflow to work this smoothly. Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. I started by creating a poster concept in Dreamina. The image looked finished, but I wanted to edit the individual elements instead of recreating everything. So I gave the poster to GPT-6 Astra and had it call Photoshop to separate the design into editable layers — background, text, objects, and visual elements all became independent pieces. This is the part that surprised me: AI doesn’t just help make the design anymore, it can help turn the final image back into a real design file. Dreamina makes exploring different poster concepts much easier with its competitive pricing, then Astra helps take them into the editing stage. #Dreamina #DreaminaPartnershow more

subagents are just recursive agents where you can apply... different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.show more

Astra (GPT-6) is here!!! I've had early access and... tested it like crazy with things like games, code, writing, browser control, presentations and general knowledge work. This is the best model I've ever used. Period. (Incredible demos below in this thread ⬇️) Here's my take on Astra: > It's insanely capable. This feels like a massive improvement, not just an incremental change. This is especially true with zero-shot prompts. > It's all about knowledge work. Slide creation, analysis, writing, and browser control. And oh my...it's so good at browser control. GPT-5.6 was already fantastic at doing things in the browser, Astra is another level and significantly faster. > We're closer than ever (arrived?) at prompt-to-playable game. And I don't just mean only playable, these are actually fun games. I bet if someone with a great eye for games used Astra, they could create a viral game within 1-2 weeks. > Astra is better at writing but not perfect. It removes much of the "AI Smell" we're all familiar with but some stink still survived. > It has a tendency to use the same design colors and look/feel as GPT-5.6 (forrest green anyone?) but it is more steerable in design than previous models. > It's highly steerable in general. A little nudge goes a long way. When I first started using Astra, almost every task I gave it would go for ~30 minutes. I wanted it to keep working. Adding more specifics to a prompt helped greatly with it's ability to work for a long time. > Astra's 3D understanding is unmatched. 3D asset creation was consistent and easy and its spacial awareness while building complex 3D worlds blew me away. I'm still getting familiar with Astra but this will now be my go-to model for any difficult work I have. Check out the demos below: 👇show more

Di Maria on a recent interview debunking the rumor... that Argentina was forced to lose the 2026 WC final. “We were not forced to lose. The Argentine squad played terribly because the coach abandoned the 4-3-3 formation what worked for us in the 2022 World Cup final. That system gave us balance, width, and allowed me to do what I do best on the wing. I was one of the key reasons we won that final I created danger, stretched the defense, and helped Messi shine. This last final? The 4-4-2 formation was wrong from the beginning. It killed our attacking flow cos no one was there the bring out the best in Lionel Messi just the i did in the 2022 world cup”show more

This weekend I had the opportunity to attend the... very first Prop Firm Expo by Prop Firm Match What an incredible event. Yes, it was crowded. Yes, it was hot. And yes, the lines were long. But if anything, that was a testament to just how popular prop trading has become in London, far beyond what many of us expected. It was amazing to see an online community come together in person. Traders had the chance to meet the founders and leaders of some of the biggest prop firms, connect with the streamers and educators they watch every day, and exchange ideas with fellow traders from around the world. It was a great opportunity to learn, network, and pick up new ideas to improve their trading. Having attended trading events around the world for more than two decades, I can honestly say the energy and enthusiasm of the prop community is unmatched. Thank you to Prop Firm Match for inviting me to be a part of it. I’m already looking forward to next year. I have no doubt the venue will need to be even bigger. Grateful to have been part of such a memorable first event.show more

Kling 3.0 is out but Sora 2 is still... the GOAT when it comes to AI UGC 🤯 And this custom GPT turns your sh*tty Sora 2 prompts into scroll-stopping UGC 🤯 Tell it your product --> get a timeline-based prompt with shot composition, camera angles, lighting, and timing breakdowns. Copy, paste, generate. Perfect for DTC brands and agencies who are tired of AI video output that looks like garbage. Here's the problem: Most people prompt Sora 2 like "make a UGC video of someone using my skincare product" and wonder why the output is unusable. Sora 2 needs hyper-specific instructions—shot type, lighting, scene details, timing cues. Without that, you get slop. This GPT fixes it: → Input your product (supplement, skincare, SaaS, whatever) → It generates a detailed Sora 2 prompt with full scene breakdown → Includes shot composition, camera movement, and timing → Optimized for 9:16 TikTok/Reels format → Copy directly into Sora 2 and generate No 80,000 word "prompting frameworks", just results. What you get: > Professional UGC prompts in 10 seconds > Consistent output quality every time > Prompts built for vertical video formats > Works for any product type Want free access to the Sora 2 Prompt Generator GPT? > Like this post > Comment "UGC" And I'll send it over (must be following so I can DM)show more

Claude "Puzzling" while GPT 5.6 on GOD-MODE just bade... a banger that's mindblowing. Here's the exact way to get a site like this, step by step: > open the desktop app, pick Sol, reasoning on High. taste work never goes to small models > drop it 3 sites with motion you love and one line: "reverse-engineer the art direction: mood, typography, pacing, and WHY each animation exists. save it as a style bible" > brief in one paragraph, goal not steps: "[your niche] site, cinematic scroll, every animation has a job. follow the bible" > house rules on top: no template hero, no stock gradients, nothing on the page moves without a reason > now the bar: "a motion designer can't tell this from an agency build." spin up a SECOND 5.6 with fresh context whose only job is to FAIL the build against that bar > /loop overnight: build, grade, close the biggest gap, again. you're asleep for all of it > when the verifier runs out of complaints: tag Sites. live URL, one click, zero hosting The deeper version of every step (the full contract, the house rules, the verifier trick, when Ultra is worth the bill) is in the article below. P.S. send the article to your GPT and tell it "we're doing this tonight".show more

Claude + GPT Image 2 + Seedance + Meta... Ads MCP Just fired my $10k/month performance marketing agency. Here's the exact stack (and how it runs): Step 1: Research Hand Claude your product page, your competitors' pages, and your best ad angles. It spits out a full brand brief + competitor breakdown in minutes. No strategist. No $200/hour consultant. Step 2: Static ads in seconds Claude crafts image prompts from your brief. Drop those into GPT Image 2. You get scroll-stopping creative. Batched. On-brand. No Figma needed. Step 3: Video ads that convert Claude writes video prompts. Feed them into Seedance 2.0. UGC-style clips. AI actor formats. Product showcases. All generated. Zero filming. (Both GPT Image 2 + Seedance are live on HeyOz right now.) Step 4: Publish + optimize on autopilot Hook Claude into Meta Ads MCP. It pushes your creatives live, tracks performance, and keeps iterating. Your agency was billing you hourly for this exact thing. I documented the full workflow in a guide: prompts, setup, and the exact MCP config. Why this matters: Most brands are still bleeding money on slow, overpriced creative production. The ones who crack this in the next 90 days will own an unfair advantage. Don't be the brand that figures it out too late. Comment "REPLACE" and I'll DM it to you.show more

Good old days at OpenAI in 2016: an agent... stares at screen pixels, moves a mouse, and books a flight on United. We called it World of Bits, inside OpenAI Universe. 10 yrs later, Astra is reincarnated in the same universe. Even the naming is astronomically correct 😆 Universe was perhaps the most ambitious AI infra project at the time, but we couldn't quite figure out how to solve it. A policy with zero prior knowledge of what a "submit" button does has to rediscover the entire internet visual lingua by trial and error. In retrospect, RL from scratch against hand-drawn, per-task "artisan" reward functions on a bunch of Pascal Titan X GPUs was completely doomed. To solve computer use agent, the right way turns out to be boiling the ocean first (hillclimb on every general task you can find), and then specialize back down to the screen pixels and keystrokes. Or simply, a "Specialized Generalist". Lessons learned: one step ahead of everyone, you're a pioneer. Three steps ahead, you're a prophet. Five steps ahead, you're a martyr. Congrats, GPT-6! That United flight finally gets booked, reliably this time. The 2016 intern in me has a big smile.show more

FABLE 5 + HIGGSFIELD TURN A $35,000 ANIMATED SITE... INTO A ONE-SESSION, $12 BUILD. HERE'S EXACTLY HOW. a studio runs this across four people and three weeks. you run it across one chat window and one afternoon. THE BUILD, STAGE BY STAGE: STAGE 1 - THE CONCEPT Claude reads your brief and scripts the scroll before a line of code exists - what the visitor feels at second 3, 15, 40. prompt: "read this brief. script the scroll beat by beat, then scaffold the project with GSAP ScrollTrigger + Lenis." STAGE 2 - THE VISUALS (Higgsfield) every hero shot, transition, and ambient loop comes out of 30+ generative models - matched to the story, not pulled from a stock library. prompt: "generate the hero sting and one b-roll clip per section. 3-5s, high-res, cinematic." STAGE 3 - THE MOTION (Claude Code) Claude writes the ScrollTrigger timelines and Lenis smooth-scroll, extracts frames, optimizes every asset. zero hand-coded keyframes. prompt: "wire the scroll: pin the hero, scrub the video, reveal each section on scroll. keep it 60fps on mobile." STAGE 4 - THE POLISH six cinematic effects baked in, no config: film grain, particles, vignette, glass cards, color tints, scroll pacing. prompt: "bake in the cinematic layer, then QA load speed, mobile breakpoints, and whether the scroll actually lands - rewrite what doesn't." CONNECT HIGGSFIELD (MCP): add it as a custom connector in Claude Code: mcp_servers: higgsfield: url: " one OAuth flow. Claude generates and pulls clips directly - no exporting by hand. THE MATH: → what a studio charges: $6,000-$35,000+ → what it costs you: a Claude sub + a few dollars of Higgsfield credits → what it takes: 4 people + 3 weeks → 1 operator + 1 session the pipeline was the moat. it just became four prompts. Follow me, comment "MATH" and I'll send you the full step-by-step Playbook. full breakdown in the article 👇show more