Pinned Tweet
We built a fully playable 3D shooter with 0% human-written code to test our AI agents. The entire game was generated by an agentic workflow guided by a detailed schema, not simple prompts.
This is not Vibe coding.
This is intent --> execution.
Powered by Moonshot AI’s KIMI-2K. 🧵👇
Play it here: aphygo.com/gameone
#AgenticAI #LLM #AI #GameDev @Kimi_Moonshot
More work with less tokens in Google Antigravity
github.com/Aphygo/Antigravit…
Reduce unnecessary code context by 75–95% while keeping ~98% cache hit rates.
We're happy if you want to try it out and appreciate feedback!
#antigravity #GoogleAntigravity #AIcoding
Polyphron.digital retweeted
I used AI to explain the AI Doomer drama, with Lord of the Rings and kittens.
this is pure f*cking treasure
A Stanford research group found how to orchestrate Claude Opus 5.5 and GPT-6 Astra together, and it completely breaks the resampling wall
most developers think test-time compute means running 32 blind retries on one model. you burn API tokens repeating the same 2-3 error clusters in loops
Stanford's paper (arXiv:2608.05643) splits the compute between two different brains:
> breadth search: GPT-6 Astra runs high-entropy exploration (T=0.8) to discover divergent solution paths
> step audit: Claude Opus 5.5 scans each step at T=0.0 and catches the exact logic fallacy
> local surgery: Opus rewrites only the broken step instead of dumping the whole reasoning chain
> verifier-free consensus: majority voting locks the proof without relying on drift-prone PRMs
the benchmark metrics outclass standard Best-of-N sampling:
> 91.2% recovery rate on detected reasoning flaws
> under 1.8% regressions on correct branches
> MATH500 jumps from 29.6% to 58.0% (+28.4% absolute gain)
> AMC-2023 improves by +7.5% with zero reward models
Astra explores the maze. Opus repairs the logic
you stop burning tokens on blind retries. you run verified reasoning depth
Readers added context they thought people might want to know
arXiv:2608.05643 does not orchestrate GPT-6 Astra and Claude Opus 5.5. One open-weight model generates, critiques, and corrects. MATH500 29.6% to 58.0% and the +7.5 AMC gain are for Qwen2.5-1.5B. Two coauthors are at Stanford. arxiv.org/abs/2608.05643
Polyphron.digital retweeted
We put Jev’s System 1 up against Aphygo’s Reflex Arc in Doom. We crushed it. Same 35 Hz game.
Jevs bot: 300–700 ms per cloud response.
Reflex Arc’s bot: 18 μs local CPU inference — and learning mid-fight.
Turns out local is the best place to keep your reflexes.
#EdgeAI #Jev
Polyphron.digital retweeted
Nobody’s ready for what this Stanford paper reveals about multi-agent AI.
"Latent Collaboration in Multi-Agent Systems" shows that agents don’t need messages, protocols, or explicit teamwork instructions. They start coordinating inside their own hidden representations a full collaboration layer that exists only in the latent space.
And the behaviors are insane:
• Agents silently hand off tasks based on who’s better
• Roles appear out of nowhere leader, executor, supporter
• Policies encode signals that never show up in actions
• Teams adapt to new environments without retraining
• Collaboration stays stable even when communication is impossible
The wildest detail:
Even when you remove all channels for communication, agents still cooperate. The “teamwork” doesn’t live in messages. It lives in the network.
This flips the entire multi-agent playbook.
We’ve been building coordination mechanisms on top…
while the real coordination is happening underneath.
A new era of emergent team intelligence is unfolding — and it’s happening in the places we weren’t even looking.
Project: github. com/Gen-Verse/LatentMAS
Polyphron.digital retweeted
Yann LeCun says LLMs are not a bubble in value or investment; they will power many useful apps and justify big infra
The bubble is believing LLMs alone will reach human-level intelligence
Progress needs breakthroughs, not just more data/compute
"we're missing something big"
Do you remember when you joined X? I do! Does not feel like 3 years, so much has happened in AI that this feels like a lifetime. #MyXAnniversary
1
1
82
Beyond direct implementation, the agent also conceptualized novel gameplay mechanics.
The idea for the corridor's walls to dynamically shift in real-time to alter pacing and tension came from the agent itself - it was not an explicit instruction in our schema, except us asking for dynamic world generation.
This shows a move from pure implementation to emergent design.
#AI #EmergentBehavior
1
1
76
The intent --> execution model redefines the creator's role.
The work isn't just writing code line-by-line. It's architecting high-fidelity intent, testing the systemic output, and iterating on the vision. You shift from engineer to director.
See the raw output for yourself. aphygo.com/gameone
#FutureOfWork #Automation #Tech #Developer #NoCode
1
69
Polyphron.digital retweeted
This is such a funny debate. Because of random sampling, EVERYTHING that could ever exist can be generated with non-zero probability. Any output can be reached with the right RNG. To say AI can't invent anything is to say nothing could ever be invented at all.
Replying to @timsoret
My replies since yesterday.
Some are in for a rude awakening when their dogmatic views will crash against the unavoidable wall of reality.
Craving to unleash the world's top open-source agent LLM on your RTX 3090? Now it's possible! Dive into unsloth/Kimi-K2-Instruct-GGUF on Hugging Face - 1T params MoE beast for epic coding, reasoning & tool use. low VRAM! #AI #LLM huggingface.co/unsloth/Kimi-…
154
AI Experts React: Elon’s Grok 4 Is Now #1 in AI - This Changes Everything... youtu.be/camlUwrxsfs?si=qtS2… via @YouTube
Grok 4's PhD-level reasoning + agentic networks for planning/execution = AGI moment? Add ant colony-inspired redundancy & fail-safes: Emergent resilience where failures strengthen the system. Not monolithic - swarm intelligence wins. Are we there? #AGI #xAI #SwarmAI #IntelligentInternet
103
Some things are better built from scratch. Aphygo’s rewriting the rules of generative AI, forging signal to spark what’s next. We’re just getting started. Intrigued? Track us on LinkedIn: linkedin.com/company/aphygo
#AI #GenerativeAI #TechInnovation #FutureTech #SignalProcessing #StartupLife #AIVenture #StealthMode
1
78
Polyphron.digital retweeted
II-Agent builds full-stack websites for you.
Next.js + Shadcn frontend, FastAPI backend, NeonDB database. Run local, Docker, or e2b and auto-deploy to Vercel.
Reviewer agent tests and fixes on the fly.
Open source. One prompt, ship. 🚢















