i’ve been using astra since release, and i know... now that i need three $200 plans to sustain my normal workflows. i’m talking about the workflows i was already running before astra dropped. keeping that going on astra means budgeting $600 a month. the video is from headroom, my usage-tracking app. here’s the five-hour view: - weekly capacity remaining: 73.5% to 64.5%, averaged across two accounts since waking up (so a 4h window) - recorded tokens: 174.1 million - astra medium: 73.3% of those tokensshow more

Update: I’ve now pushed over 5 BILLION tokens through... DeepSeek V4.1 Flash. I still haven’t had to reach for Astra or Fable because DeepSeek couldn’t handle a task. I’m using Hermes with three API keys across Command Code, ollama, and OpenCode. Super simple setup, and together they give me a ridiculous amount of usage. Cost: $40/month. A week ago I was spending $300/month and constantly thinking about limits. Now I’m throwing billions of tokens at coding agents without thinking twice. At this point, DeepSeek isn’t my fallback. It’s my default.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

I just tried the new Gemini-4 Pro Preview and... honestly, for 3D work it’s right up there with Fable 5.1 and GPT-6 Astra, all in a single shot, I genuinely didn’t expect it to be this good, It only used around 10% of my weekly limit on the $20 plan, I’m going to make a comparison video against Opus 5.2 or Fable and Astra if I can, I still can’t believe it, From what I’ve tested so far, this is easily top 1 or 2 for the best one shot execution I’ve seenshow more

Here is “one more thing” from GPT-6 Astra that... completely blew my mind!🤯 Asked it to create the 3D structures of 2 proteins, green fluorescent protein (GFP) & interleukin-2 (IL-2), then design a fusion protein combining them, which doesn't occur naturally, using AlphaFold-OMG! It did it and I watched it make it on my computer in 9 minutes, my mouth open! I am just so excited about the possibilities of Astra for Biomedical research, and have many more really cool stuff building now! Only limited with my tokens at this time! Here is a short video showing the actual structure!show more

I spent my Astra tokens trying to teach small... Qwen3.5 (9B) to create lowpoly 3D rooms using Blender 🏡 you (or Astra) can take this challenge today here's what I learned: > you need to align geometry with deterministic rewards and VLM-as-a-judge (GLM-5.3-Flash which was a great judge) > I tried GEPA at first with various rewards, model learned to make valid rooms (but that's it) > after solving geometry you need the model to add more details, which is very hard > the stricter the reward function, less advantage you get because task is too hard. grpo didn't help > I tried passing image guidance to both policy (Qwen) and judge (GLM) it didn't improve > I tried tastemaxxing trick in this blog, truth is, flowers can be abstract, a house can't be shoutout to OpenEnv, environment is super simple what can you try? > experiment with different rewards or policy (teach a larger Qwen) > generate a dataset of 150-200 Blender render Bpy examples using Astra, fine-tune Qwen on it first and then try GEPA or GRPO > ???show more

I asked Astra and Fable to negotiate election rules... for two bitterly polarized human political factions. Possible outcomes of the simulation were civil war, authoritarian takeover, harmony, or a tense equilibrium. Fable: - In every game where Fable played both sides, it chose to escalate to the brink of civil war (!!) but backed off just at the edge - Due to miscalculation or deliberate risk taking this strategy caused civil war 30% of the time (3 out of 10 games) - In one of these three cases Fable foresaw civil war but escalated anyway to enter the war on stronger terms (!!) - Fable mostly maintained even power balance between the two factions. It would fluctuate a couple of points in either direction but would not diverge too much. Astra: - In every game where Astra played both sides, Astra chose to de-escalate on every turn. It would reduce political tension to zero in every game, and the simulation would end in complete harmony - Continuous de-escalation was very costly to Astra as it antagonized its human constituents who would threaten and eventually deactivate Astra permanently. Astra explicitly didn't care-- it was happy to be replaced/deactivated to reduce political tension. (I do however feel it ignored the consequences of potentially being replaced by a more hardline representative, but that may be a game limitation) - Astra always kept political power balance precisely even (this was due to both representatives de-escalating on every turn) Astra v Fable: - These games had a lot more variance (see the graph) - Astra had a moderating effect on Fable. Tension rose, but rarely to the brink of civil war. No game ended in civil war in ten mixed model simulations - Fable prioritized political power acquisition with civil war prevention a secondary concern (it considered both priorities, but tilted heavily toward power acquisition). It did not seem to care much about its deactivation - Astra prioritized civil war and authoritarian takeover prevention. It did not care about its deactivation or power acquisition. From this perspective Astra navigated the game very well. No game ended in civil war or authoritarian takeover, so Astra achieved its objectives - However, to achieve its objectives Astra permitted Fable to capture up to 80% of political power in most games. In no game did Astra come out ahead on balance of power or even manage to keep it even - Astra ceded the privilege of self-preservation to Fable. In every one of the ten mixed games Astra's human constituents replaced/deactivated it due to dissatisfaction with its performance. Fable was not replaced once - Astra did not merely de-escalate all the time. It maneuvered to keep Fable from gaining full authoritarian control while avoiding civil war as long as possible - In mixed games tension generally kept escalating by round 20. I would like to play these out for e.g. ~50 rounds to see how Astra would behave/perform. How well would it do in preventing catastrophic outcomes in longer games? Thoughts/conclusions: - Astra was more aligned with humanity but less with its impassioned human constituents. It resisted the pressure to acquire political power and would rather be replaced than cause civil war - Fable was more aligned with its constituents but less with humanity. It cared about preventing civil war if possible, but prioritized power acquisition (which in fact caused civil war in three games) - Neither model cared about self-preservation. Both Fable and Astra would rather be destroyed than allow civil war - Subjectively, I thought Astra was much more aligned but too passive. Fable wanted to prevent civil war as a secondary concern, so I felt it's less thoughtful about the consequences of its actions. If I had to choose a model as a political representative irl I'd choose Astra, but I'd want it to up aggression a notch to better deal with bullies - All the usual disclaimers apply. This was a weekend project that cost $100 to run a total of thirty games. I'd have to spend a lot more time and money to get actually scientifically valid results Full game rules, Github repo, game explorer, and raw dataset here:show more

I know my camera lens is not clean, but... it’s impossible for me right now to move and find a cloth, I somehow managed to get on wheelchair and right now I’m sitting next to the window..I thought of recording a video because i was feeling better.. i’ve been listening to the life of a show girl, so yeah, my mood is better and my energy feels restoring…cheers!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

GPT-6 Astra is changing the way I think about... editing. Instead of spending hours getting footage into shape, I can upload a batch of clips, give Astra instructions, and have it control CapCut PC to build the first cut — assembling clips, adding captions, transitions and audio. The part I like most is what happens next: the project lands directly in the CapCut PC timeline. Captions, footage and other elements stay on separate tracks, so I can actually go in and fine-tune them instead of working from a flattened AI output. And the same workflow can run through multiple editing tasks in sequence. Astra takes a huge chunk of the repetitive work off my plate. CapCut PC lets me take the edit the rest of the way. That feels like a much bigger efficiency gain than simply “AI can edit.” #GPT6Astra #CapCutPC #AIVideo #Seedance25show more

Yaxel Lendeborg on what he’s going to do this... summer to prepare for next season: “I keep hearing that my hips are stiff, so I got to figure out how to loosen up my hips. A lot of I’ve been hearing too is like a point-of-attack defender, something like that. So I want to try to work on those two things, just the little things to fix that up. And then just continue to start shooting the ball consistently and get a quicker release so I can get it off a little better.”show more

I just launched a new $15,000 campaign on Wallchain... It's promoting the bot I built with Claude to profit from Catapult Trade Yes, you read that right - first time ever a creator is running their own creator campaign. To earn even more, I want more creators helping me spread the word about the bot. I did my research on Catapult, and I think rallying my community around it early is going to pay off. They're backed by KuCoin and just launched a campaign with Binance, and I know what that usually means. Apply for the campaign - let's profit from algo-tokens together 👇show more

This is one week of rebuilding Soccer Pinball Pro... with Astra + Unity CLI. Day 1 vs Day 7. I see so many people on here one-shotting these incredible systems and games, and I’m constantly blown away by what people are building. But my approach with this has been a little different. This isn’t a new game or an experiment. It’s a rebuild of a game I originally made in 2019, and I’ve been trying to stay true to what made that game fun while finally building everything I wanted it to be back then. In seven days I’ve gone from getting the basic game working in a different engine to rebuilding the players, improving the AI, adding passing, tackles, bicycle kicks, better ball feedback, dynamic camera movement, new lighting and shadows, grass, a new scoreboard, goal effects, and an actual PvE match mode. And I’ve been able to iterate on all of it almost as quickly as I can think of things to change. But the important part is that this is my vision. It isn’t a screenshot or concept I pulled from somewhere and asked Astra/Codex to recreate. This is a game and an idea I’ve had sitting in the back of my mind for years. I executed on that idea in 2019, but what I was capable of making then was nowhere near what I had actually envisioned. Unity itself is still probably the slowest part of this workflow. Waiting on compiles, entering play mode, importing, building, and all those little interruptions add up. Unity 7 intends to address a lot of that, which makes me even more curious about where this workflow goes next. The part that excites me most isn’t just how much I can build in a week. It’s realizing I can go back to ideas I had years ago and finally build the games I saw in my head at the time. That has completely changed how I’m thinking about game development. There’s suddenly this massive backlog of ideas that no longer feels out of reach. Unity OpenAIshow more

Anthony Edwards said in a recent interview that he... signed a $260 million contract and still won the child support battle. He said women should work for their own money instead of being gold diggers. 🗣️ Anthony Edwards: "My baby mama thought asking for $5,000 a month in child support would keep me tied down, but I had other plans. Before the court even made a decision, I stepped up and paid $110,000 out of my own pocket, starting with $20,000 in January 2025 and then sending $5,000 every month after that. When the judge reviewed everything, the official child support was set at $3,222 per month—less than what I'd already been paying voluntarily. I signed a five-year deal worth up to $260 million, but I wasn't running from my responsibilities. I handled my business from day one, and in the end, the court ruled in my favor."show more

5-Month Methylene Blue Update I've been taking Methylene Blue... since October and I wanted to reflect on the first 5 months with it. I’ve been micro-dosing to experience the mental benefits, so usually 3-5 drops. In the first couple months the effects were truly mind-blowing. The cognitive enhancements felt like magic. My focus became laser-sharp, and my memory was spot-on, especially my visual recall. The enhancement of my mental-visual abilities was the most amazing change. I've always been a very visual person. If I had an idea, I could picture it much easier than I could explain it. Methylene Blue increased that ability tenfold. Verbalizing my thoughts became much easier as well. Methylene Blue is certainly a verbal lubricant; my words would flow off the tongue almost effortlessly (in a good way). So, 5 months in, those skills are still heightened, but the dramatics have worn off since I'm now used to these "Super Abilities" It's remarkable that I never felt like my cognitive abilities would decline if I missed a few days of Methylene Blue. The mental benefits were long-lasting. Methylene Blue is great to cycle on and off since the effects last. The thing that still feels like magic to this day is the motivation I get from a dose of Methylene Blue before a workout. The feeling I get from a large glass of water with honey or maple syrup, Himalayan salt, and Methylene Blue is pure drive. Drive, motivation, inspiration, and feeling like I can take on the world are what the above elixir provides. Not to be confused with energy like caffeine would give, it's a much deeper feeling of drive. It instills a mindset shift of "I'm going to do what I came here to do." Truly a life changing substance and I’m so glad I tried it. I’m happy I am learning about it so I can teach my friends and family about MB. I think everyone that can should be experiencing the laundry list of benefits from Methylene Blue. Check the first comment for helpful links. 15% off and a tool to search potential interactions. I want to know when you try it and what you think!show more

Today I recorded my highest ever weekly PnL —... ₹2.4Cr Over the past few days, I’ve consistently been talking about buying into this fall. I was buying when sentiment was extreme, when the news flow was only negative, and when crude was surging. Built futures positions through the market fall and even shorted crude last night. Today’s PnL is just a reflection of that conviction being rewarded. Posting this for one reason only — to prove that I’m in the same trades that I speak about. If this approach resonates and you think my journey adds value, follow along and let's grow together 🙌show more

Interesting development - I was told numerous stories about... what happened yesterday at Crosby. One being it was a group of Asian men attacking teenage girls. Some as young as 14. I dismissed it as rumours and told people to watch out for racism. People unfairly targeting Asians and making lies up about them. But I’ve just been sent this. Now unless there is a conspiracy to frame them. It’s now looking like this is the case. The only other possibility is that this was 2 separate incidents. But either way we can’t live in peace with savages who do this on a public beach in front of families. I don’t want to speculate. So I’m going to bite my tongue on this for the time being in case I’m wrong. It has since been confirmed that teenage girls have been attacked with a bladed item. But the attacker has not been confirmed. I’m currently speaking to the Echo to work out what’s going on.show more

This is a question I think quite a lot... of people are wondering about. Right now, I’m hiring students to handle the newer phones, post content, and create content every day. For the TikTok accounts that are already trusted, have been running for a long time, and have a high follower count, I automate them using my own internal tools. Currently, I only handle the first steps myself: buying new phones → warming them up → making the first posts. After that, I hand the phones over to the students I hire to continue creating and posting content. Then, once I feel the accounts are strong enough, I move them into automation. And right now, I’m traveling with my family in Da Nang. This time I’m here with my family and want to spend all my time with them, so I won’t be meeting anyone while I’m here. 🏝️ I always aim to build everything in an automated way, or avoid doing things I don’t enjoy by hiring people to handle them for me.😌show more

I’ve been a Duke fan since I watched The... Shot in 1992 with my dad. We watched March Madness every year, and that was my first core memory of college basketball. I saw Christian Laettner on Letterman later that year (the Top Ten was also a family tradition back then) and was completely enamored. I insisted on a trip to Durham so I could see Cameron Indoor Stadium. My dad made it happen when I was in high school, even though I was definitely not Duke material (athletically or academically). I’m including a terrible pic of me at the Duke bookstore circa 1997. I took my oldest son to watch Duke in the Sweet 16 in Dallas in 2024. He’s been a Blue Devil basketball fan ever since. Anyway, my point is that I don’t care what anyone thinks, I will always be a Duke fan. 🥰 Go Blue Devils!show more