One prompt + one image → a playable ski game GPT-6 Astra & Rodin MCP handled most of the heavy lifting Game development is getting weirdly accessible

Someone built a full survival game like The Forest in three.js in one single day A 2km island shaped by simulated erosion, 44000 trees generated in code with real photoscanned bark, six actual Pacific Northwest species Sun and moon sit exactly where they'd be at 49 degrees north in late September, thunder arrives late because it travels at the speed of sound, wolves stalk at dusk and back off from a torch Claude Code split the build across agent teams, one per domain, with critic agents checking renders against real photos The wolf still needs work and it doesn't hit 60fps yet Still not done and already wild

It was surreal to see my academic adventures on the front page of the @nytimes Here’s how I built Crimson Education almost entirely while at universities:

Opus 5.5 hype is getting crazy People are building games, apps and entire projects with it My whole timeline is full of this stuff, time to work on it I need to see what I can build with it, let’s test it today

AI agents learning from each other changes everything 💀 A new multi agent world model from @odysseyml just dropped Agora 2 → humans and AI agents can interact, compete and cooperate inside the same generated world 20 participants can shape the same environment, creating interactions AI can learn from World models are getting very interesting Agora 2 feels like a step toward AI learning through real interaction

We’re excited to announce our collaboration with @zecfrogs. 6969 Frogs are coming to ZSC As part of this collaboration, we’ve secured a limited number of WL spots exclusively for the GIGA community. They’ll be distributed exclusively through our discord. GIGA × ZECFrogs

Opus 5.5 hype is getting hard to ignore I keep seeing people build things with it that would normally take way more time Games, apps, complex coding tasks I’m especially curious about how far I can push it myself Time to build something weird with Opus 5.5

Cresta really turned customer support into a murder mystery 😂 The funny part is the marketing... The interesting part is where support is going More customers used to mean more support people, now AI can take a big part of the queue Beast Mode could mean fewer people, more support

A playable game, built almost entirely through a single AI workflow, that’s what caught my attention The wild part is everything is generated in real time, from the code to the world around you. And somehow, the whole thing fits into a 3 MB HTML file Feels like a very different way to build games I definitely need to test Opus 5.5 myself

Building my first iOS app has changed how I think about coding A lot of the work now feels more like explaining what I want, testing it, breaking it and fixing it Still learning every day but seeing an idea turn into something real is addictive

OpenAI just cut API prices in half but the real story is what becomes possible now Sol and Luna bring most of Astra’s power at a fraction of the cost, making powerful AI much easier to build with Products that used to feel too expensive can now actually make sense Cheaper inference looks like a pricing update but it could unlock a whole new wave of experiments

Running agents at scale gets messy pretty quickly One place for the runtime, tools, inference, storage and the rest of the infrastructure makes a lot more sense than stitching all of it together yourself Digital Ocean Managed Agents is basically trying to make agents feel like a normal cloud resource I’m curious how much more people will actually run once the infrastructure gets simpler

OpenAI just admitted something quiet but big Their models are producing math results that even top mathematicians have to sit down and check by hand So what does that actually mean It means the real bottleneck stopped being about generating answers and became about trusting them Whatever comes out of this advisory group probably turns into the blueprint that medicine, law, and every other field copies next

AI video used to be mostly about generating the final shot. Now the same workflow can touch modeling, materials, lighting, editing and compositing, all inside one production flow. AI is moving from generating content to handling more of the actual production so how many people will a full AI production studio really need?

Introducing Codos: The first virtual Chief AI Officer. AI is crushing all benchmarks but real companies still struggle to see P&L impact. Codos interviews employees, deploys automations across all functions and gets smarter over time while running on your own servers. Our NASDAQ-listed and PE-backed customers are adding millions to their bottom line months ahead of schedule and we are proud of the first results we deliver. It’s time to turn the 500BN AI-transformation market into software and unlock the impact for the real economy.

The crazy part is hearing your own voice! Say words you only thought, AI is getting closer to turning thoughts into something you can actually use and the possibilities here are hard to ignore

We just launched Agentsky @agentsky_dev, world’s 1st Agent Market! OpenRouter is for models. AgentSky is for agents. Use 40+ agents—Claude Code, Codex, OpenCode, Hermes, Pi in your browser(even your phone!) or via one API. All without installing or setting up anything. Hit Codex Astra’s weekly limit? Hand off to another agent such as OpenCode + DeepSeek V4.1 in browser without losing any context. You can compare any agent + model directly in browser and that's how I found Astra costs $5.3 while deepseek v4.1 cost $0.12 on the same dashboard task. (I actually preferred deepseek) Try it at agentsky.dev If you can try any agent easily without install, which agent do you want to try next? Type the agent name and I will give $20 credit (you can use it for any model)

I left a senior AI role at Ollama to build a financial iOS app on my own money I don't find any investors tbh so trying to build it with my own funds Every feature has to earn its place, building in public from here What should a financial app do better, any suggestion?

What is a decision model? Jev by @typesafeai answers yes/no and multiple-choice questions, with a confidence score. Much of software development are a sequence of decisions, and Jev is 10x cheaper and faster than an LLM. Let’s understand this through practical examples:

Jev is HERE and this is the CLEAREST explanation of what it is and what NEW businesses it unlocks. (and at the end I'll tell you how to get Jev even if you're on the waitlist) WHAT IT IS You know how you open your inbox and have to decide what's junk, what needs a reply, and what can wait? Jev does that part. It looks at each thing and says "this is junk, I'm 94% sure." It doesn't write anything back to you. It just sorts. 1,700 emails for 18 cents, instantly. That sounds kinda trivial but the important part WHAT IT UNLOCKS My explanation of Jev sounds small until you realize HOW MANY jobs are exactly this. Someone reading a stack of applications. Someone deciding which support ticket goes to which team. Someone looking at inbound and deciding who's worth calling back. A few ideas on what it unlocks: 1/ Instant quotes that are actually instant. Every quote form on the internet says "we'll email you by end of day." Build the version that answers in under a second, for roofers, movers, insurance, legal intake. 2/ Lead scoring as a product. Every agency and service business has a contact form full of junk. Score every submission and send the real ones straight to the owner's phone. 3/ Support triage for companies with no support team. The ticket gets classified and routed before anyone opens it. 4/ Clipping tools. Pass in a transcript, get the best moments scored in three seconds. Every clipping product just got a cheaper engine. 5/ Application piles. Grants, permits, insurance claims, job apps, loan docs. Someone reads that stack one item at a time today. 6/ Marketplace matching. Someone types what they need and gets matched to the right local business instantly instead of waiting for callbacks. 7/ Browser agents that actually move FAST. That makes bulk browser work practical: pulling quotes from five carriers, filing the same form for 200 clients, checking supplier inventory in real time etc. TLDR; find an expensive queue and put Jev at the front of it. HOW TO GET IT I didn't realize you can skip the waitlist because Jev is live on the Vercel AI Gateway right now, so you can start calling it today. In this episode, we share how. Episode now live on @startupideaspod (thanks to @ryanvogel for coming on and spilling the sauce today) Watch: piped.video/watch?v=4mTLpuQp… Jev is a big deal because this is a whole new way to do AI Really cool Happy Jev day.