this is pure f*cking treasure before refreshing the feed... for Sam Altman’s next announcement, look at what a better workflow did with GPT-3.5. 95.1% on HumanEval with an agentic workflow. 67.0% for GPT-4 answering in one pass. results reported by Andrew Ng, reproduced in this independent guide. four patterns behind the approach: > reflection: draft, check, revise > tools: retrieve information and test > planning: split the task into steps > collaboration: assign distinct responsibilities the diagram connects architect, tech lead, and developer through handoffs and feedback. that’s what i want around GPT-6 Astra: clear roles, verification, and a path to fix failed work. full breakdown below.show more

Wait… why did nobody tell me AI-generated posters could... go back into an actual Photoshop workflow? Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. I generated a poster in Dreamina first, then sent it to GPT-6 Astra. Astra used Photoshop to break the image apart into separate layers, so I could finally adjust the background, typography, and individual elements instead of being stuck with one flat image. For designers, this feels like a missing step between AI generation and professional editing. And because Dreamina keeps the creation cost competitive, I can test multiple poster ideas before deciding which one deserves a full edit. This workflow is kind of a game changer for rapid design exploration. #Dreamina #DreaminaPartnershow more

This is probably the closest I've gotten to going... from ""rough idea"" → ""actual product"" without touching a traditional design workflow. Turns out GPT-6 Astra + Dreamina Seedance 2.5 is an actual pipeline. I made the initial product draft in Dreamina, then gave it to GPT-6 Astra. Astra took the visual direction, generated the realistic product, and turned the result into a clean product detail page. Dreamina being cost-efficient makes the first stage even better - I can test multiple product concepts before committing to one. Pretty wild how short the path is now. #Dreamina #DreaminaPartnershow more

GPT-6 Astra rigged and animated a mech with digitigrade... legs walking in Godot from one prompt in 30 minutes, handling a joint setup that every other model failed to figure out, with the full workflow being a Midjourney concept, Meshy 7 for the 3D model and one prompt to Astra. → Rigging normally means building a skeleton, assigning bone weights and hand animating the walk cycle, usually weeks of work → Digitigrade is the hard version, the backwards knee setup seen on dogs and raptors → Walk cycle is not perfect but imagine what a couple more prompts would doshow more

this AI engineering breakdown from IBM Technology is pure... f*cking treasure it explains the role as a connected system 01 Python and APIs give you the surface to build on: services, data, integrations, and the software around the model 02 RAG and embeddings solve the context layer: finding the right information before the model has to reason about it 03 agents turn that context into work: they choose tools, run steps, and move toward an outcome 04 observability closes the feedback loop: traces, metrics, failures, latency, and the evidence needed to improve the system 05 deployment is where the system becomes real: reliability, constraints, and the conditions that let people actually depend on it the model sits inside this architecture the AI engineer connects every layer into one operating loop: build → retrieve → act → observe → ship save this, then build your solo business with an AI employee ⭣show more

this is pure f*cking treasure these 10 agent skills... have 3.49M combined downloads and form a complete working stack planning. react performance. databases. ideation. interface systems. branding. visual polish. search. browser work. production UI 01 grill-with-docs ▸ 02 vercel-react-best-practices ▸ 03 supabase-postgres-best-practices ▸ 04 brainstorming ▸ 05 ui-ux-pro-max ▸ 06 brandkit ▸ 07 impeccable ▸ 08 seo-audit ▸ 09 browser-use ▸ 10 shadcn ▸ the stack covers the full product loop: pressure-test the plan ⮕ shape the system ⮕ build the interface ⮕ harden the database ⮕ polish the experience ⮕ audit discovery ⮕ run the workflow in a real browser save this, then select your gpt-6 astra use case ⭣show 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

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

all GPT models and DeepSeek 4.1 are FREE on... ZansLab right now an Indonesian AI gateway just unlocked free access to every GPT model plus DeepSeek 4.1 for vibe coding, no top-up needed, just sign up what you get: > GPT-6 Astra free > GPT-6 Sol free > GPT-6 Luna free > GPT-5.6 Sol free > DeepSeek 4.1 free > and Claude models also available on the platform how to claim (under 2 min): step 1: go to step 2: sign up with email and password no card, no top-up needed step 3: create an API key from the API Keys page step 4: set base URL to works in any OpenAI-compatible client, Cursor, Claude Code, Codex, custom scripts step 5: pick a model and start vibe coding important: > this is a third-party proxy so don't send any sensitive data through it > free access reportedly lasts until next week per the source > these free tiers rarely stick around, grab it while it's upshow 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

I think the real productivity test for AI editing... is what happens when you have 30 videos to cut, not one. GPT-6 Astra can control CapCut PC and handle the repetitive first-pass work across editing tasks, turning a workflow that normally has to be repeated manually into something much easier to scale. I can upload the footage, provide the editing instructions, and let Astra process the task — assembling clips, making cuts, adding captions, transitions and audio. Then each project lands as an editable CapCut PC timeline. I can still adjust individual clips, change pacing, and edit captions separately because the elements can stay on different tracks. Edit Pilot gives me another way to handle post-editing changes. Astra makes the repetitive workflow scalable. CapCut PC makes the output customizable. If AI can remove the repetition from editing, maybe the next bottleneck isn't editing speed anymore — it's creative direction. #GPT6Astra #CapCutPC #AIVideo #Seedance25show more

I'm building my game with GPT-6, and color correction... has become one of my favorite uses for it. When I generate assets separately, I can like each one on its own and still end up with a scene where the colors don't belong together. A castle looks fine in isolation, then turns greenish against the terrain. Its swords and shields disappear into the background. Getting those things to match used to mean a lot of repainting and trying different textures. Now I've built a workflow where GPT-6 takes screenshots in Unity, inspects the object's color textures, and helps bring them closer to the look I want. I can give it the terrain or tree textures as color references. It can prepare masks, send the relevant textures through Image Edit, then put the result back into the game for another look. Editors such as GPT Image 2 Edit or Nano Banana Edit can be part of that workflow. This is also why I keep pushing for properly prepared 3D models. If the parts are separated logically, you get much more control later. We could work on the swords and shields without changing the whole castle. The stone could stay dark while the equipment became easier to read. The latest pass on my game covered the overall post effects and the skeleton castles. We matched the castles to the surrounding terrain, adjusted the equipment colors, and added a subtle moving highlight. The first stronger color pass went too far. I asked for the accents to move about 30% closer to gray, and that got them where I wanted: visible, without pulling all the attention. I'm so happy with the difference. The video shows the before and after across the map and on the castles. Being able to give feedback on the actual scene and keep refining it this way feels great.show more

this is f*cking gold Google engineers explained how to... make AI rewrite an agent’s system prompt against failing tests. a failed check becomes the next repair job. the regression suite watches for whatever that repair breaks. even the instructions become something you can test and improve. Agent = Model + Harness. the independently compiled page here maps the broader system into six parts: guides carry project rules, constraints and lessons from past failures > sensors check the work through tests, linters and validators > the loop runs the task, checks the result, retries within limits and escalates > memory preserves state, artifacts and decisions across runs > permissions control tools, writes and actions requiring approval > observability records what happened, what it cost and where it failed an agent changes a build file and announces “done.” the check looks for evidence that it actually ran the validator. if that behavior is missing, you have a specific failure to target. adjust the instructions. rerun the evaluations. check whether the improvement holds without breaking existing behavior. now a prompt change has a test history. a recurring mistake has a regression check. the next model upgrade has something concrete to pass. bookmark the diagram. give “done” a test it has to pass.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

Beauty ads just changed forever. Free Claude Opus 4.8... + GPT Image 2 + Seedance 2.0 workflow to spin up 100s of video ads. No studio, no model, no macro lens, no shoot day. Here's what nobody in beauty marketing wants to say out loud. That glossy lip shot. The droplet hitting the surface in slow motion. The whip-pan into the next scene. The crystalline product splash. All the stuff that used to need a real set, a real camera op, and a full shoot day. You can generate every frame of it from a text prompt now, and stitch it into a finished ad before your coffee goes cold. The workflow is almost stupidly simple: → Tell Claude Opus 4.8 the beauty shot you want (dewy skin macro, gloss-on-lips contact, ripple transition, the works) → Claude turns it into a shot-by-shot storyboard plus a prompt for every frame → GPT Image 2 generates the photoreal stills, frame by frame → Seedance 2.0 animates each one into a clip with that buttery slow-mo glide → You drop the clips into HeyOz and assemble the full ad in one place The real unlock is volume. This isn't one hero video. Once the workflow is dialed, you spin up hundreds of variations. Different shades, different models, different hooks, different transitions. The exact creative volume Meta rewards, minus the production cost that used to make it impossible. Old way: one shoot, one look, $10k+, weeks of waiting. New way: a hundred angles, any look, a few dollars each, same afternoon. I wrote up the entire workflow. The Claude storyboard prompt, the GPT Image 2 frame prompts, the Seedance motion settings, the full assembly flow. Completely free, no email gate. Want it? Comment "GLOSS" and I'll send it straight over. (make sure you're following so it can actually reach you)show more

We may be overestimating the importance of the generation... step in AI video. Getting a model to produce a beautiful 10-second clip is impressive. But filmmaking has never been just about producing footage. It’s about deciding what happens before the camera rolls, controlling the shot, and shaping the material afterward. That’s why this workflow is interesting: GPT-6 Astra establishes the 3D space and camera + character movement in the Viewport. The scene is manually brought into CapCut PC. Seedance 2.5 renders the video. Then CapCut PC takes the result through post-production. Generation becomes one stage in a larger pipeline rather than the finish line. Maybe that’s the direction AI video needs to take if it’s going to move beyond “cool clips” and toward actual filmmaking workflows. And CapCut PC is a pretty natural place to experiment with that full process. #CapCutPC #GPT6Astra #AIVideo #Seedance25show more

HONESTLY, THIS IS HOW I WANT AI VIDEO TOOLS... TO WORK TOGETHER. Not one model trying to do everything. One stage understands the space. One stage turns the scene into video. Then the creator gets to shape the result. GPT-6 Astra handles the spatial planning, including the 3D environment and Viewport-based camera + character paths. I manually bring that scene into CapCut PC, use Seedance 2.5 for the render, then keep working on the footage in CapCut PC. That last part matters. Because a generated clip isn't necessarily a finished video. The more interesting future might be AI helping across the entire filmmaking pipeline while the creator still decides what the final piece should be. And this is definitely one of those workflows I'd want to try hands-on in CapCut PC. #CapCutPC #GPT6Astra #AIVideo #Seedance25show more

I GAVE JEV A CRAWLER + ONE GPT AGENT... AND ASKED WHERE THE ONLINE MONEY IS RIGHT NOW it read 5,137 open jobs and found 3 niches where clients pay and almost nobody bids everyone asks chatgpt for side hustle ideas everyone gets the same 10 answers so i made it read what clients are actually paying for this week a crawler is a bot that reads the internet for you jev is the ai that answers every question with a number, under a second, under a cent gpt is the expensive brain, it only gets called when jev says a niche is worth it the crawler reads, jev decides, gpt researches honestly gpt alone just guesses, jev is what turns 5,137 jobs into 3 answers what the three of them did: -> crawler read all 5,137 open jobs on freelancer, budgets, skills, how many people already bid -> jev checked every one: real job? doable online by one person? 684 got cut -> gpt named 30 niches from 600 of them, jev sorted all 4,453 into those niches -> jev looked at each niche's numbers and sent only 12 to gpt -> gpt researched those 12 on the open web: other platforms, real prices, how crowded it is -> 3 came back with real demand and fewer bids than the typical job (14): 01 chrome extension · 85 jobs this week · median $545 · 11 bids each · ~$4,671/mo 02 tiktok shop setup · 91 jobs this week · median $232 · 6.5 bids each · ~$1,984/mo 03 notion setup · 95 jobs this week · median $181 · 3 bids each · ~$1,551/mo potential = your fair share of this week's jobs (budget ÷ (bids + 1)), max 2 jobs a week not every pick held up, excel dashboards looked great on freelancer but gpt found it crowded everywhere else jev made 9,617 calls for $0.13, gpt on every job would have cost ~$58.66, the whole run cost $6.53 i wrote up why the cheap brain decides and the expensive one only gets called when it's worth it, it's below ↓ costs nothing bookmark this, empty niches don't stay empty show this to the one friend who keeps asking chatgpt for side hustle ideas should i run it on upwork next, or is chrome extension the one?show more

omni motion control is f*cking cracked the left clip... is the original. the right is 100% ai, same video, one prompt i grabbed a weight loss transformation off tiktok, gave omni a single image of a totally different girl, and it rebuilt the whole clip around her. she copies the original move for move, down to the dumbbells and the timing. and she doesnt exist and i barely lifted a finger. this was the entire prompt, word for word: "replace the person in the video attached with the person attached in the image, make sure the weight loss transformation is exactly the same from fat to fit" gpt image 2 made the character and omni did the rest. thats it brands pay creators to reshoot the same winning ad with different people just to split test. now you film it once and swap the face for cents. one video turns into 50 i wrote up the full setup: > the prompt method that transfers motion without breaking > how to find reference videos that work > how to batch this out at scale comment "MOTION" and ill send it overshow more

I’m joining OpenAI Codex to work on the future... of agentic development! At Cursor, I got to see the shift from autocomplete to agents. The next step isn’t a better IDE. It’s an Agent Development Environment (ADE): systems and tools for orchestrating agents, reasoning over their outputs, and making them autonomous enough to reliably complete ambitious work. After chatting with Alexander Embiricos and Tibo, it was clear that Codex is the best place to realize this vision. The team has consistently shipped SOTA models for agentic coding (check out gpt-5.3-codex) and I’m pumped for the future that the new Codex App points to. What I’m most excited about is the broader mission: accelerating the knowledge work economy. All agents are coding agents, and we’re already seeing Codex used across every job function within organizations. I’m extremely grateful for my time at Cursor, working with the incredible team, and I’m proud of what we built together. I’m excited to take an even bigger swing with Codex. If you’re curious to get a glimpse of where we are headed, download the Codex App! If you want to work on this mission, please apply or reach out - we are hiring across all functions! You can just build things.show more

I went a little overboard with Codex last week... and burned through my entire weekly allowance in two days. Luckily, my quota reset today. Otherwise, I’m not sure what I would’ve done. It got me thinking: instead of asking one large model to handle everything from start to finish, why not let a stronger model plan the project and review the work, while a model built for execution handles the day-to-day implementation? So I tried it. The result was better than I expected. I used GPT-5.6 Sol in Codex as the decision-maker, then ran Ling-3.0-flash from Ant Ling inside OpenCode as the execution engine. Together, they built a small 3D farming game. Before writing any code, I had Codex create four documents: SPEC.md defined the product scope and the lines we couldn’t cross. ARCHITECTURE.md laid out the isometric coordinate system, state machine, and module boundaries. TASKS.md broke the project into small jobs Ling could tackle one at a time. ACCEPTANCE.md explained how each step would be tested and what “done” actually meant. Then I gave Ling a very straightforward role: You are the execution model for this project. Read all four documents before you begin. Work only on the task assigned for this round. When you’re done, run typecheck, test, and build. If anything fails, read the error, fix it, and run the checks again. Do not move on to the next task early. Ling handled dependency installation, project structure, strict TypeScript configuration, test setup, and a production build in 6 minutes and 3 seconds. It ran into issues with the Vite test config, a TS6310 error, and a missing jsdom dependency along the way. Instead of stopping at the first error, it kept reading the logs and fixing the problems until all three checks passed. The speed was honestly hard to believe. If you exclude the time spent waiting on tools, it was producing more than 100 tokens per second. That made the whole development loop feel noticeably faster. After this experiment, I’m planning to keep using the same workflow. If the task is small, there’s no reason to call an expensive planning model for every single step. If the task is large, handing the entire project to a Flash model in one prompt isn’t a great idea either. The setup that makes more sense to me is: Use a more capable model such as Codex to explore the project, make architectural decisions, and break the work down. Put the constraints into specs, schemas, types, and tests instead of leaving them buried in chat history. Give Ling-3.0-flash a steady stream of clear, verifiable implementation tasks. Report bugs with structured context and actual error logs, rather than saying, “It still doesn’t work.” Bring Codex back in for architecture reviews, visual checks, and changes that affect multiple parts of the project. The point of this setup isn’t to give AI a big “build the whole project” button. It’s to turn software development into a pipeline with a much more sensible cost structure: Codex figures out the plan, sets the boundaries, and catches problems. Ling-3.0-flash moves quickly, calls tools reliably, and works through well-defined tasks at scale. For agent workflows that involve lots of repetitive edits, production tasks, and tool calls, this may be a more practical answer than simply using the biggest model for everything.show more