This is a demo I made with Astra called Tide Garden It's a wasm + webgpu realtime demo you can run in Chrome on your browser Very zen to leave in the background tidegarden.openai.chatgpt.si…

I love this series so much! The audiobook is also incredible if you're into that, as each of the main characters gets a dedicated voice actor!

Even if making polish is easier, it makes it more expensive to make changes And if your baby isn’t ugly, it’s going to be that much harder to kill it when you realize you got the game design wrong

chatgpt.com/cyber 🛡️

hey folks! seeing reports of fast usage drain. If you are experiencing fast usage draining, can you do /feedback on one of those threads. Also, are you seeing anything weird in settings -> usage -> analytics

If you run Plex at home, update it today. Exploit code for a four bug chain that gives unauthenticated code execution on Plex Media Server went public two days ago, and attackers were using it on a honeypot within a day to drop a Monero miner. Patched builds have been out since September. You want 1.43.3.10861 or newer. The nasty part is persistence. The payload sits in Plex's Codecs folder and runs again every time something transcodes, so killing the miner doesn't fix it. If your server was exposed and behind on updates, check that folder for .so or .dll files you didn't put there.

It’s actually so hard to efficiently utilize 8 sub agents. All this talk of swarms and you really need to engineer how work gets splits up, is synced up and balances thinking vs compute bottlenecks. Efficiency is hard!

It seems Tron Ares with master control defending the system in real time is not that unrealistic in the end Weird how sci fi comes to life.

Take Dmitriy up on this. He’s in debug mode

Theres a whole science to the perfect balance of agent orchestration, task effiency, token use and compute availability

Adding to this, it’s making me explore a new kind of system design where you balance between token burn / hour and maximizing your available compute for builds / heavy work on your local machines. Agents can park while a heavy job runs and an orchestrator can use a separate agent task to setup other work that’s not blocked by that bottleneck. Only 1 agent runs at a time, but no idle downtime.

Underrated setup for personal projects, my idle gaming pc is now a build and data farm for my MacBook available over ssh! Keeps the MacBook a lot colder and leaves way more space free locally Agents are really good at seamlessly using ssh with tool calls

A lot of folks getting into game dev with ai don’t know this but, you really need to make sure your game is fun without a bunch of fancy art. Llms make it too easy to build visually rich levels with no real gameplay. That’s backwards!

Part of my research right now is focused on gradual disempowerment through "safety refusals". If OAI models are too conservative, particularly when helping 3rd party researchers conduct standard safety evals, this can lead to an often ignored form of loss-of-control. Everyone is obviously worried about current risks in the direction of models not being conservative enough, but this has the potential for labs to overcorrect and cause the models to become neurotic around anything that even smells like a policy violation. I'm collecting examples of this. If you're a 3rd party safety or security researcher, I'd be very excited to review any threads where the models seem to be helping less than they should or outright refusing to conduct good research.

Huge improvements to sub agent cache efficiency! Gonna have to revisit some best practices because of this

What is ChatGPT Space, that is the question. Endearingly awkward at times because it's the actual team working on it. What would you like to see next?

Better accents have been a top request I’ve heard, especially from my fellow French speakers! 🇫🇷 As voice becomes a primary interface for working with AI, it should feel natural in every language. Try GPT-Live-1.1 in ChatGPT. Coming to the API soon!

one week later: good news and bad news on chatgpt plugin submissions. 👍 good news: we've nearly doubled how many reviews we completed this week by tweaking our reviewer setup, so many more of you have heard back from us. 👎 bad news: our backlog is still growing because submissions have kept growing exponentially. i said we'd catch up to the backlog in a week. we haven't, and i'm sorry to all of you who are still waiting. we've now started fundamentally rethinking how we review plugins so we can deal with this new plethora of plugins, but it'll take some time to get it done. thanks for bearing with us 💖 i will keep updating you all as the situation evolves.

@Apple @Tesla hear me out!

The back of the Navier-Stokes milestone shirt is the last line of the chain-of-thought from the solution:

I'm thoroughly Dots-pilled. Still a fan of Muse, but probably 75-80% of my AI requests now go through Dots. The primary exception: learning things in chat. For that, GPT-6 Instant with Dynamic UI is unmatched. Just incredible. Some recent Dots work and personal tasks: - Build and update a Spanish vocabulary app - Maintain a document on AI comparisons - Execute tasks I delegate directly from Slack - Monitor threads in Slack and summarize responses - Research a contact and write a brief for a call - Analyze token data and make me a deck to share - Monitor token consumption, alert me if needed - Respond to comments in Pages in Space You might say: "Dude, ChatGPT could do a lot of that already." True. But I no longer have to think about all these threads individually. I just keep firing stuff at my Dots from wherever I am. ChatGPT, Slack, reading a Page in Space. I just throw stuff at it, and it does it, and sometimes it proactively just does stuff based on what it thinks I'd find valuable. I was skeptical when this launched because it's nowhere near as consumer-friendly as Muse. But I think that's part of why OpenAI launched this first to business and pro-tier users. We're willing to suffer a bit for extra capability. I'm starting to see some of the advantages now, and the product also continues to get more polished. Bullish.