The next step in Andrej Karpathy’s Software evolution: what happens when code is generated at runtime, executed once, and never saved…
Regenerative Software - The Phoenix Architecture
Home Page - Software Heritage
preserves software source code for present and future generations
The Case for Software Craftsmanship in the Era of Vibes
From the Zed Blog: Working toward genuine, quality software in an era where code production is not the constraint anymore.
Evaluations Are the Real Codebase - The Phoenix Architecture
Why behavior outlives implementations
Code Is Cheap Now. Software Isn’t.
The barrier to entry for building software has collapsed. The barrier to building something that matters hasn’t moved an inch.
Differ - Adaptive Software
Build software that adapts to each user — without forks or feature flags. One codebase, infinite variants.
Differ - Adaptive Software
Build software that adapts to each user — without forks or feature flags. One codebase, infinite variants.
Durable Execution Solutions
Build invincible apps with Temporal's open source durable execution platform. Eliminate complexity and ship features faster. Talk to an expert today!
When Science Goes Agentic
In a couple of years, we will inspect AI-generated source code about as often as we inspect the assembly output of a compiler. Which is to say, far less often—outside of high-stakes and adversarial settings. The trajectory is clear: vibe coding is not a fad but a transition, a stepping stone. Debugging AI-generated code will shrink dramatically for a lot of everyday software—not because the code will be flawless, but because the feedback loops between generation, testing, and correction will tighten until human inspection becomes the bottleneck rather than the safeguard. In this respect, requiring the co-generation, with code, of mechanically verifiable formal attestations can also improve the process.
Magicoder: Empowering Code Generation with OSS-Instruct
We introduce Magicoder, a series of fully open-source (code, weights, and data) Large Language Models (LLMs) for code that significantly closes the gap with top code models while having no more...
SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks
Software development is iterative, yet agentic coding benchmarks hide design issues through their single-shot setup. Recent iterative benchmarks attempt to remedy this but heavily constrain an agent's design decision space, making it impossible to faithfully measure how their decisions shape future extensions. We introduce SlopCodeBench, a benchmark of 36 problems and 196 checkpoints where agents repeatedly extend their own solutions. Unlike prior iterative benchmarks, our evolving specifications demand architectural decisions but leave internal structure to the agent. We measure two forms of degradation: structural erosion (concentrated complexity) and verbosity (redundant code). Evaluating 15 coding agents across open and closed models, we find that no agent fully solves any problem end-to-end, and the best agent passes 14.8% of checkpoints. Quality degrades across checkpoints, with structural erosion rising in 77% of trajectories and verbosity in 75.5%. Compared to 473 open-source Python repositories, agent code is 2.3x more verbose and 2.0x more eroded, and the human repositories degrade less often and by smaller margins across their git histories. Explicit quality guidance reduces initial verbosity and erosion by up to a third, without affecting degradation rates. SlopCodeBench provides the first measurement of code degradation under iterative extension, revealing that agents pass checkpoints while producing code that erodes and bloats with each turn.
Rabrg/artificial-life
A simple (300 lines of code) reproduction of Computational Life: How Well-formed, Self-replicating Programs Emerge from Simple Interaction
The New Software Lifecycle
I co-wrote a Google whitepaper about how AI is changing the software lifecycle. I'm not going to summarize the whole thing. Instead, here are the handful of ...
Flawless - Durable Execution Engine
Flawless is an execution engine for durable computation. It will run your code until completion even in the presence of hardware or software failure.
Code Is Cheap Now, And That Changes Everything | Pere Villega
AI coding agents have made code production nearly free. Drawing on insights from Kent Beck, Paul Ford, and Simon Willison, this post argues that the value has shifted from writing code to defining systems — contracts, invariants, SLAs, and verification.
