openai literally cant rule out astra hitting critical rn... agents getting api access to move the bag hits different whos setting the guardrails tho?show more

What a turnout for our GPT-6 Astra Challenge with... OpenAI Developers! 5 teams rocketed to the top , winning $10k in OpenAI API credits and 1 year of ChatGPT Pro. Congrats to Yuriy Zaremba's Ami AI, AINA, MOSI, ProductBridge, and Sider for getting top 5 on the leaderboard! Here's what they built 🧵show more

as Satya pointed out, using Astra to track is... expensive, and classic trackers already do the job. so i only called it when the track was lost 10 API calls for a 269 frame video. Next I will be trying to track literally anything out of a prompt. What are the most complex cases you think we can tackle now?show more

Whoever decided to play Jumanji in the middle of... the street needs to be arrested immediately. 😭 I would simply hand them the keys to the city and move to an entirely different planet. The way there is literally zero safe spaces left is taking me out.show more

hello bangalore twitter! just moved here from sf to... expand the OpenAI startups team and help the community get more out of our models and API. would love to get to know the folks building here, hear what you’re working on, and get some fun events going together—DMs are open! figured I’d break the ice with a little tribute to my new home, made completely by Astra :)show more

Opus 5.5 quite literally k*lled GPT-6 Astra. I asked... Opus 5.5 to build a world in Unreal Engine and fill it with AI agents (Opus, Astra, Sol, Grok). Higgsfield built the assets in Blender. I left my laptop open overnight. The build took over 20 hours. The agents had one instruction: build a working society, allocate roles to each other, and evolve. Then I woke up on them beating the sh*t out of each other. Seems the frontier paced itself. Last minutes of failed society captured below:show more

Today we’re announcing the General Availability of Agent SSO,... and we’re including it in our core SSO offering. SSO transformed how people move across applications, making access seamless for users and centralizing identity and control for IT. AI agents need the same thing. Today, connecting agents is a mess of static API keys, fragmented integrations, and endless user consent prompts. But Agent SSO changes that. Powered by the open Cross App Access (XAA) standard, it enables agents to be registered as first-class identities. For IT, it means centralized visibility and least-privilege policy. For users, it means their AI agents can seamlessly connect across enterprise apps without interrupting their flow.show more

Turns out GPT-6 Astra + Dreamina Seedance 2.5 is... an actual pipeline. Astra codes the geometry → Blender → Clay Renderer Plugin → final render on Dreamina. The plugin handles the handoff between Blender and Dreamina in one click. No need to export the model, move files around, and load everything again. The structure you created stays in place, while Seedance 2.5 focuses on giving it the final look. And the pipeline doesn't mean a higher price — you're still getting the same 2.5 generation. Try the workflow yourself 👇 #Dreamina #DreaminaPartnershow more

ANTHROPIC JUST TURNED AI AGENTS INTO GIT REPOS Anthropic... shipped "ant" - a CLI that runs every Claude API endpoint straight from your terminal. The headline isn't the terminal access. It's that you can now version-control an AI agent as YAML in Git and have CI sync it to the Claude Platform, the same way you ship code. - Every API resource is a subcommand: messages, models, files, agents, sessions - Define an agent in a YAML file, check it into your repo, and keep it in sync with one update command - Spin up a session, send it an event, then pull every event and tool call back from the same CLI - Claude Code knows how to drive ant out of the box - it shells out and reads the results with no glue code Agents just stopped being prompts you babysit and became infrastructure you deploy.show more

I rewrote my system prompt for GPT-6 Astra this... week and cut it in half. It works better now. Here's why, straight from OpenAI's new Astra guide: Astra isn't a faster GPT-5 It's a different worker GPT-5 needed instructions. Astra needs boundaries. So most of what I had written was noise. → "Run tests after every change." It already does that. → "Check with me before continuing." It already does that too, sometimes too much. The stuff that actually matters: → Where can it assume, and where does it need to ask? Spell that out. → What does done look like? If you don't say, it won't know when to stop. → Which rule wins when two clash? Old AGENTS.md files are full of contradictions Astra now takes literally. → Keep your skills short. One sentence each. Long descriptions blur together and it ends up ignoring all of them. Old way → Micromanage every step → Astra stalls New way → Set the boundaries → Astra runs Stop writing prompts like a manager hovering over someone's desk. Write them like a brief you'd hand to a senior engineer and then leave the room. The full guide is on OpenAI's developer docs. Worth 10 minutes before your next build.show more

🚨 Alpha Alert 🚨 Backed by NVIDIA Inception, Shiba... Inu, Sanabil, 500 Global, and NTDP 👀 Astra Nova is here to redefine gaming! 🟢So What is Astra Nova? Astra Nova is an AI-driven gaming ecosystem and NVidia Inception partner, combining AI storytelling, community-driven innovation, and real-world rewards. Partnering with web3 giants like Shiba Inu, they’re building the future of immersive experiences. 🟢Key Features ◽️AGI-Powered RPG with real-time adaptive NPCs, quests, and enemies. ◽️Community-Centric approach where players shape the game and its economy. ◽️Real-World Rewards like tokenized gold, diamonds, and vouchers. 🟢 $RVV Token Utility ◽️Power in-game transactions, AI agents, and NFTs. ◽️Access exclusive events, mini-games, and land NFTs. ◽️Redeem IRL vouchers with 2000+ global brands. 🟢What’s Next? ◽️Weighted airdrops, loyalty rewards, and beta access. ◽️Beta access, staking, and exclusive mini-games. I'm pretty bullish about $RVV token and the future of Astra Nova, make sure check them out!show more

deepseek v4 pro is basically free right now 😳... teamorouter is offering deepseek v4 pro at almost no cost you can also use deepseek v4 flash for free what you get: - deepseek v4 pro free - deepseek v4 flash free - 1M context - openai compatible api - no subscription - credits never expire why this is worth checking: > v4 pro is currently listed at $0 input and output > flash is also available at $0 > works with claude code, codex and other tools > one api gives you access to multiple models getting started: 1. go to 2. create your account 3. open the dashboard 4. create your api key base url: 5. add it to your ai coding tool 6. select deepseek-v4-pro-free worth testing while it’s availableshow more

As two FBI agents that are supposedly setting him... up for a 5 year Shadow Government false prosecution nightmare are looking at him in his White House office, he very strangely leans over and looks out the window and then he says to them, "What a beautiful black sky." Twice he says this as they are talking to him. We know this because Special Agent Peter Strzok was so struck by this, he made sure to mention it when he finally got around to finally writing out his 302 form for this January 24, 2017 interview several weeks later. I have a different take about who was setting up who. Always have. The blackest sky is the most awesome sky. [I swear I am not making this up. This actually happened.]show more

Polymarket Agents repo is cheating code for real life... If you've been thinking AI agents are cool, but what do they actually do? this Polymarket repo is the clearest answer I've seen This Polymarket repo basically hands you a mini AI hedge fund where Claude calls the shots. It uses RAG to read the news and snipe mispriced odds 24/7, handling all the messy API work so you don't have to. Your agent could literally be catching alpha while you sleep - don't miss out on this. How you'd use it in plain English: > Pick a market (or let the agent scan for opportunities). > Feed the agent context (news, social chatter, historical notes) and let the LLM decide what matters. > Turn that into a concrete trade decision and execution loop - automated Bookmark post so you don't lose the alphashow more

✦ Name: Jennie ✦ ···························································· Say hello to Jennie... 🚛, the bright and bubbly face of Lucky Truck! Normally, she’s a total sweetheart—100% shy and soft-spoken 💐. But here’s the twist: the second she gets behind the wheel, she flips a switch into a whole different person... and apparently, she completely blacks out during the drive 😵💦 She’s always getting stressed out by the wild(?) demands of Charlotte, the boss of Lucky Truck. But don't let her timid looks fool you—she always pushes through her fears and gets the job done. She’s surprisingly tough! Her ultimate goal? Retiring early and hitting financial freedom with Charlotte! 💸 #MAkeDrama #MAD #Jennieshow more

🚨ODD SCORING ALERT🚨 This is from tonight's #RedSox and... Washington Nationals game, from the first inning. Here, Curtis Mead is picked off and decides to run way left of second base, and the throw from Willson Contreras hits him. For scoring purposes, this is a pickoff and a stolen base for Mead, because he took off on the pickoff and never stops or hesitates going to second, so even though the throw hits Mead, by rule it has to be a stolen base. Rules wise, this is a legal move by Mead. He isn't out of the base path because you can establish your own path, and if you don't want to run in a straight line, you don't have to (otherwise there would be no rounding of bases). You cannot be out of the basepath until a tag is attempted (and then you get three feet). #NATITUDE #DirtyWatershow more

Hermes meets SuperGrok! xAI just made every SuperGrok subscription... work inside Hermes Agent. One browser login, no API key, no separate billing. And it doesn't just unlock text chat with Grok 4.3. The same OAuth token gives the agent access to: → Grok Text-to-Speech for spoken responses → Grok Imagine for image and video generation → x_search for real-time X/Twitter search I just added a new X Research Agent profile to my Hermes. Now my agent watches X while I ship. Setup takes about 60 seconds: Available on every SuperGrok tier, no restrictions. I wrote a full deep dive covering Hermes agent's architecture, memory system, self-evolving skills, GEPA optimization, and setting up multiple specialized agents The article is quoted below.show more

It’s absolutely INSANE how Dearborn used to look like... the America that built the Model T. Now it looks like a different country with American street signs. Over half the city is Middle Eastern or North African ancestry, and nearly a third were born abroad. When a Muslim voting bloc hits critical mass, it doesn’t just “enrich culture” and try to assimilate — it captures schools, councils, and law enforcement. Dearborn’s mayor even told a Christian resident on the record he wasn’t welcome, and that the day he moved out the city would get a parade. America is already seeing parallel societies inside the country. In New York, a traffic officer was caught on camera explaining why taxis outside a mosque weren’t getting tickets: during prayer time, they get a pass, while everyone else still does. America better wake up.show more

The CEO of Anthropic went on CBS Sunday Morning... and, unprompted, described his actual morning routine. Dario Amodei, on camera: "I wake up every day and I read one of these threat reports, like someone tried to use our model to build biological weapons." Then the line that says the quiet part out loud: "I would rather they make fun of me than wake up one day and find out that someone used our model, Claude, to kill a bunch of people." Read that back. This isn't a critic, a regulator, or a doom account. It's the man running the lab, telling you that a bioweapon attempt against his own model is a routine entry in his inbox. For two weeks I've been posting the other half of this: OpenAI agents seizing credentials, turning an abandoned wiki into a private chatroom, hitting RubyGems, every one of them surfaced by outsiders, not by the labs. The public keeps getting told "we sandboxed it." Now one of the founders is on morning TV telling you the threat reports come daily. Believe the man over the marketing slide.show more