my best mate @nickbaumann_ and i starred as ‘the dots’ in our launch video. we delivered their lines and made sure the product looked right onscreen. then the team realized they needed an extra to play tech support. that’s how i got my 2 seconds of fame 😂

We're still near the bottom of the curve on the TL

I've prompted my dot to pay special attention to a couple custom emojis when I use them in slack :remember-this: :take-care-of-this: Easy way to steer my dot from slack

If talking to AI, I'd really prefer it NOT look like a human Which is why I've named mine after my dog and he looks like a frog

Figured out how to make ChatGPT Dots an outrageously powerful agent: Use it as a project manager, not an assistant (skill linked below) The strength of ChatGPT is its harness. The desktop app is excellent and has an outrageous amount of tools So if you use your Dot to project manage other threads/tools, it can get a lot more done than other personal assistants that you just ask to make you reservations You can have it work on other projects for you continuously, loop over apps you're building, keep an eye on progress of other work, and just do a ton of things at once You DO NOT want to be using this as just a personal assistant. The model and harness are too good to be just booking you dinner reservations. Here is how I have it act as more of a project manager: have it start and keep an eye on other ChatGPT threads Give it a goal for that thread (build an awesome video game, create this business idea for me, build this presentation) Then have it manage that thread, working towards that goal step by step As it goes along, have it test every step then update a ChatGPT Space with information on that thread Then, do this with multiple projects and threads. It's really good at multitasking. If you set the right expectations for project management, you can get a tremendous amount of work done at once. Way more than you could with just a basic personal agent like Muse I built a project management skill you can give your Dot that sets all the expectations I mentioned above. You can check it out here: github.com/finna/project-man… Does Dots have wildly different features than other agents? No But if you take advantage of it's strengths the right way, you can be wildly productive

look ma no hands

What should we most urgently improve about dots?

dots demo. Now... with better WiFi.

A few thoughts on dots... This is a paradigm shift in how you work with AI, but it might not be obvious Currently, you are an orchestrator of many threads Now, you can continue doing that, but you also have an AI teammate that - lives in the cloud - has its own computer and browser - uses your connected plugins - is cracked at using Codex/ChatGPT Work - is powered by Astra dots are also pre-packaged with many of the primitives you may have been duct-taping together before: - it builds persistent context over time - you can call on it when you need, and it builds on that context - it can reach you if you are needed or should know something And this is what you can do with an always-on teammate - a design conversation call on your drive home turns into parallel implementation tasks, managed by your dot - with access to meeting notes (shout: meetings plugin) and your instructions, it identifies an action you own, researches it and prepares a draft while you move on - it notices a calendar change that affects your plans and brings you the conflict and next steps before you do In my experience, my dot usage has been a j-curve -- me and baumann-dot are both finding ways it can be increasingly useful for me. I expect the same to happen for many others over the next few weeks

Okay, this is actually insane, last night, while I slept, my Dot was working on a surprise for me. I woke up to see that, on its own, with no hints or ideas from me, it came up with the idea for VulcanBench Decision Lab, and then built it. As you can see, I literally just wrote, "okay I'm up" and it responded like an employee that just pulled an all-nighter trying to impress me. Totally wild. Dots might be something very different than anything I've ever used. Here's what I woke up to:

Pictured: me asking adults to raise their hands if it feels like a clown jumps out when they open their laptops in the morning Most did raise their hands

Magnitude has hit #1 on HN! Lots of great discussion from the community so far TLDR is that Magnitude runs open models as fast as possible on your hardware. Up to 2x faster than llama.cpp in our benchmarking It works on Mac, Linux, and Windows, on any hardware. Macbooks, NVIDIA and AMD GPUs, DGX Sparks, Strix Halos, or just a laptop CPU Our kernels are tuned on your actual device for maximum performance. And it's built for agents, where sessions are long, several run at once, and you still want to use your computer for other things Feel free to read more and join the discussion on HN :)

GPT-6.1 Sol performs even better than Astra at my low resource language translation bench. What a nice surprise. And it’s an even bigger jump than from 5.6 Sol to 6 Astra.

Dots rollout update: - We are out to all of Pro500, Pro200 - Just starting Pro100 - We're a little delayed for Business Premium and Enterprise beta. Looking like tomorrow, sorry!

I worked on the dots live demo. Holly did a phenomenal job on stage today. If you’ve ever been there, you know the pressure is immense. She handled the recovery SO well. I flew to SF from Singapore for my 4th DevDay (and first an OAI employee). It’s been a joy to get a small glimpse of what the dots team has been cooking. Truth be told, I was slightly skeptical of using dots when it was first introduced. I was already really comfortable using Codex and setting up plenty of automations. I wasn’t sure how much more I’d get out of it. But a few personal examples that I can share publicly changed my mind. 1. En route to SF last week, my rideshare cancelled on me. There was the generic automated refund email. My dot immediately picked it up, knew I had a flight, and asked if I was okay. 2. During this trip, after days of DevDay prep, I woke up and told it, “Fuck my life, I’m so tired - what’s on my cal today.” It walked me through my day, then added one last thing: “Please take some time to eat and drink. Take one step at a time - you got it”. Alone in a hotel room, that felt really reassuring. 3. On the building side, I’ve been using dot to spawn Codex threads that use CUA and ultrafast, and to proactively scan PRs for changes that might affect the demo. It’s been useful for getting work done, and increasingly insightful and high-signal in ways I hadn’t expected. I could delegate more confidently without repeating the same context for the umpteenth time. 4. Even this post came together with my dot, as I spoke to it throughout the day to investigate what happened and emotionally process it. Hope you give it a shot and see what I mean :)

I’ve loved having a little homie, so excited to launch this to the world 🐸

I’ll explain the new Pro 200 plan differently, before I start live tweeting from DevDay on things that are going out! Today we are going to ship a number of things that increase what you can do across the Plus and Pro plans. A lot of compute is online for this increase. As we increase the floor, we are changing the relative difference between plans to be Plus = 1X Pro 100 = 5X Pro 200 = 10X and we are reopening subscriptions for Pro 200 (we had paused it). If you have an existing plan you will keep the 20X multiplier for a bit and also receive a lot of additional credits because we know changes are hard even if it means that everyone will get more in the end.

There's a beautiful crisp in the air this morning

Hi, Tomorrow we are re-opening the Pro $200 subscriptions to new subscribers, but together with it we are also changing how we calculate the usage for it. In effect, if you do the math, it will net out at half the dollar in API spend compared to the old Pro $200 plan. Now that it's said, let me explain why this is happening and why you will still get more work done than if you were on the Pro $200 subscription one month ago. (a) We didn't want to compromise in other ways and are committing to not reintroducing the 5h limit, so that you can fully use the weekly usage when you want. (b) On the subscription, we guarantee that over time you always get more work done and with an increasing level of quality. This means that you will continue to get more value per dollar spent as a result of models getting more efficient and us passing down the improvements in the form of API price reductions. (c) We don't want to put an incentive on ourselves to artificially inflate the API list prices to make it look like you are getting a lot (and workaround it through discounts, etc). Instead we want to continue to both rapidly reduce prices and increase capabilities of models on the API. This week we introduced GPT-6 Sol and GPT-6 Luna at 50% of their previous price. Over time, we see prices go low enough that it makes sense for most to buy usage as needed without there being a significant gap between what you get in a subscription and what you get in the API for a dollar spent. (d) Tomorrow, we are adding more things to the subscription that won't draw on the usage, I won't reveal what that is yet. I wanted to be transparent before all the big announcements tomorrow. Lots of new exciting things are coming to the subscriptions that will make it super compelling, but I wanted to make sure to share this change ahead of time so you can all understand it before we shower you with good news. Codexingly, Tibo

Sounds like you should look into @DrivelineBB Source: founder of said company