Multiple studies cited by software developer and author Jason Gorman find that autonomous agent workflows decay geometrically in reliability over many steps, with no examples of complex, reliable soft…
Software developer and blogger Jason Gorman published a taxonomy of out-of-distribution (OOD) errors that automated quality gates miss in coding-agent workflows, extending his "Special Theory of Auton…
A blog post on autonomous agent reliability argues that fully autonomous agentic workflows are "extremely improbable" to be reliable, citing arXiv paper 2510.27630 showing reliability tends to stabili…
Software developer and blogger Jason Gorman argues that LLM-assisted and agentic code generation has raised output but not user engagement or the bottom line, because faster shipping degrades the feed…
A new analysis argues that the reliability of autonomous coding agents faces a fundamental wall, where improving from 90% to 99% reliability is a 10x improvement in difficulty, not a 9% gain. The arti…
A software engineering blog post argues that the reliability of agentic AI workflows decays rapidly with each step, and that human oversight remains essential. The author introduces a formula R = 1 – …
Anthropic, the AI company behind Claude, has demonstrated a lack of understanding of software engineering, as evidenced by issues on its Claude status page and Claude Code GitHub issues page. Despite …
Codemanship founder Jason Gorman is betting that software development fundamentals will remain relevant despite the rise of AI, predicting that LLMs will become just another tool and that the percenta…
A compilation of recent studies and industry data indicates that truly autonomous and reliable long-horizon agentic software development using large language models (LLMs) is essentially science ficti…
Mutation testing, which deliberately injects errors into code to reveal gaps in automated test suites, is gaining adoption as a stronger quality gate for agentic coding, according to a blog post by Co…