@GergelyOrosz: I’m honestly grateful for VC funding for this kind of crazy experiment and @jsnnsa for documenting it It’s a wild read …
Summary
A commentator shares thoughts on a VC-funded experiment pushing state-of-the-art AI to ship code directly to production in a game environment where failures are tolerable.
View Cached Full Text
Cached at: 10/31/26, 03:23 AM
I’m honestly grateful for VC funding for this kind of crazy experiment and @jsnnsa for documenting it
It’s a wild read on what happens when you push SOTA AI as much as you can, in an environment where you let AI ship to prod where you can stomach if it breaks (eg this game)
Similar Articles
Vetted AI code is hard to justify
Andrew reflects on the burnout caused by vetting AI-generated code for a game optimization, comparing the time and mental cost to manual coding. He uses an interactive visualization to illustrate the trade-offs between AI-assisted development and traditional methods.
@arcane_bloom: https://x.com/arcane_bloom/status/2077733957995733062
Discusses a Latent Space podcast episode where Anjney Midha explains why AI labs with unlimited GPUs still fail, drawing on his experience at amppublic and a16z.
@mstockton: Kind of. If by vibecoding you mean that they built a set of robust evals to prove their re-write was correct, and that …
A developer discusses how Anthropic's backend rewrite to Rust involved building robust evals and parallel-running systems to verify correctness, arguing that constraining non-deterministic AI tools is the key challenge in AI-assisted coding right now.
@zodchiii: Three Anthropic engineers just spent 16 minutes on what makes AI agents actually succeed in production. If the people w…
Anthropic engineers share insights on making AI agents succeed in production, highlighting proven patterns from their work on Claude.
@GergelyOrosz: I asked myself "how does OpenAI move so quickly?" back 3 years ago, and did a writeup back then. How OpenAI worked when…
Gergely Orosz shares his earlier deep-dive on how OpenAI's Applied team ships ChatGPT so quickly, based on an exclusive interview with engineering lead Evan Morikawa. The article covers OpenAI's engineering culture, independent startup-like operations, tight research integration, and high talent density.