Marcelo Sales

Sorry for the PT-BR narration, but the Hermes Agent keeps pushing news updates of the game. akadmascot.github.io/calabouco-da-m…

I turned a SketchUp mockup into a photorealistic architectural render in 30 seconds. No Blender. No V-Ray. No Unreal Engine. Just @OpenAI GPT Image 2 edit endpoint. Before → After 👇

Then I fed it to Seedance 2 and got a cinematic drone flyover. From a static CAD file to a Hollywood-quality video. Total cost: $0.25 Total time: 8 minutes The architecture visualization industry will never be the same.

A high-end AAA JRPG game screenshot style

Just tested the GPT Image 2 → Seedance 2.0 pipeline and it's absolutely insane. One prompt to generate a cinematic 3x3 storyboard. One click to animate it into a full intro sequence. No editing. No compositing. No post-production. The workflow: 1. GPT Image 2 generates a 9-panel storyboard (consistent character, lighting, narrative arc) 2. Feed the storyboard directly into Seedance 2.0 I2V 3. Get a cinematic intro in 6 minutes This is for a dark fantasy dungeon crawler game we're building entirely with AI — 400 sections, 411 narrations, procedural cinematics. The storyboard-to-video combo is the real unlock here. Stop generating random clips. Start thinking in storyboards.

In Cowork, Claude can now build live artifacts: dashboards and trackers connected to your apps and files. Open one any time and it refreshes with current data.

@sharkygamesai Ele manteve bastante porem c alguns erros o jogo ta jogavel ai no link do git ! Testa

@marcelontime que ideia boa resgatar livro-jogo com agente 👏 Deathtrap Dungeon é clássico demais. o mais pesado é fazer as 400 ilustrações manterem coerência visual, o agente segurou bem isso?

Pedi pro meu agente IA Hermes fazer um jogo em 4 dias. Ele fez O Calabouço da Morte — adaptação do livro-jogo clássico Deathtrap Dungeon (1984). Com imagem de IA gerada pra CADA UMA das 400+ seções do livro. Jogável grátis 👇 akadmascot.github.io/calabouco-da-m… #vibecoding #gamedev #AI #indiegame

the scariest part of this Anthropic story is what it implies about the timeline and I think most people are completely missing it Anthropic built a model called Claude Mythos that found thousands of zeroo day vulnerabilities across every major operating system & every major web browser entirely on its own without huuman steering it it found a 27 yo vulnerability in openBSD which is considered one of the most security hardened OS on earth, a 16 yo vulnerability in FFmpeg in a line of code that automated testing tools had hit 5 million times without catching it & it autonomously chained multiple linux kernel vulnerabilities together to escalate from regular user to full system control, this is the kind of work that used to require elite nation-state level hackers working for months and here’s what should keep you up tonight Anthropic is so terrified of what this model can do offensively that they made 3 unprecedented decisions simultaneously, they decided to never release it publicly, they contacted the US gov before publishing anything & they formed a coalition called project glasswing with apple/Google/ microsoft/amazon NVIDIA & 40+ other companies to use Mythos exclusively for defense, when the company that built the model is too scared to let it out of the lab that tells you everything about what we’ve crossedd… but I think the real story that absolutely nobody is discussing is the second order implication, if anthropic built this then google deepmind can build it, if Google can build it China can build it, if China can build it , every state actor on earth will eventually build it, anthropic chose responsible disclosure but that choice is a luxury of being first the next team that reaches this capability level might not make the same choice and once a model like this leaks or gets independently replicated every piece of software on earth becomes a potential attack surface and connect this to the Google quantum paper from last week, quantum computers that can crack BTC in 9 min AND AI models that can find zero days in every operating system autonomously, both arrived in the same month, we’re watching the entire security infrastructure of human civilization get challenged from 2 completely different directions simultaneously I genuinely think we just entered a new era where the offense-defense balance in cybersecurity has permanently shifted, the window between a vulnerability existing & being discovered just went from years to minutes and the only thing standing between the current internet and total chaos is that the people who built this capability happened to be responsible about it, that is an incredibly thin line to bet civilization on one last thing that I keep thinking about… mythos scored 93.9% on SWE-bench verified & 77.8% on SWE-bench pro, it outperforms every model ever built at coding and reasoning by a massive margin anthropic built built the most powerful AI model on earth and chose to lock it in a cage because its offensive capabilities are too dangerous… Mzrc Andreessen declared AGI is here 3 days ago to pump his portfolio, meanwhile the people actually building the most advanced systems are too afraid to release them, that contrast tells you everything about who understands what’s happening and who is performing for an audience

Introducing Claude Managed Agents: everything you need to build and deploy agents at scale. It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days. Now in public beta on the Claude Platform.

GLM-5.1 can now be run locally!🔥 GLM-5.1 is a new open model for SOTA agentic coding & chat. We shrank the 744B model from 1.65TB to 220GB (-86%) via Dynamic 2-bit. Runs on a 256GB Mac or RAM/VRAM setups. Guide: unsloth.ai/docs/models/gl… GGUF: huggingface.co/unsloth/GLM-5.…

A MIT student figured out how to compress an entire semester of lecture content into one 90-minute study session. He calls it "context stacking," and it's the most unfair thing I've seen done with NotebookLM. I asked him to walk me through it. He did. I haven't studied the same way since. Here's exactly what he does. Two days before each lecture, he uploads everything into NotebookLM. The assigned readings, the previous week's slides, 3 or 4 related papers he finds himself, and any problem sets that are still open. Most students wait for the lecture to explain the material. He walks in having already built a mental model of it. That's step one. But it's not the move that makes it unfair. The first prompt he runs across all of it: "What are the 5 core concepts this week's content is built on, and how do they connect to what I studied last week?" Not summarize. Not define. Connect. NotebookLM pulls threads across everything he uploaded simultaneously. It surfaces relationships between ideas that would take a normal student weeks of review to notice. He gets that map before the lecture even starts. Then he runs the prompt that does most of the work. "What would I need to genuinely understand about this material to be able to teach it to someone with zero background in this subject?" That question is doing something most students never force themselves to do. It exposes exactly where his understanding is solid and exactly where it's hollow. The gaps show up immediately, and he spends the rest of the 90 minutes filling only those gaps. Not reviewing what he already knows. Only fixing what he doesn't. The final prompt is the one that separates context stacking from every other study method I've heard of. "What question could a professor ask about this material that would expose a student who understood the surface but missed the underlying logic?" He's not studying for the exam he expects. He's studying for the exam designed to catch people who only think they understood it. By the time he sits in the lecture hall, the professor is not teaching him anything new. The professor is confirming what he already mapped, filling in a few details, and occasionally surprising him with something he didn't anticipate. That surprise is the only thing he writes down. Most students leave a lecture hoping the material will eventually click. He walks in with it already clicked, and uses the lecture to find out what he missed. That's not a study hack. That's a completely different relationship with learning.

Pedi pro meu agente IA Hermes fazer um jogo , 4 dias depois. Ele fez O Calabouço da Morte — adaptação do livro-jogo clássico Deathtrap Dungeon (1984). Com imagem de IA gerada pra CADA UMA das 400+ seções do livro. Jogável grátis 👇 akadmascot.github.io/calabouco-da-m… #vibecoding #gamedev #AI #indiegame

Builders What are you building this weekend? Drop your project down below - let’s help you land some new users and super fans! (For the first 15 responses, I'll personally try your product and give you some feedback)!!

quem vai superar o Cassio? akadmascot.github.io/calabouco-da-m…

Pedi pro meu agente IA Hermes fazer um jogo , 4 dias depois. Ele fez O Calabouço da Morte — adaptação do livro-jogo clássico Deathtrap Dungeon (1984). Com imagem de IA gerada pra CADA UMA das 400+ seções do livro. Jogável grátis 👇 akadmascot.github.io/calabouco-da-m… #vibecoding #gamedev #AI #indiegame