Automating AI Away
A software developer discusses the inherent clumsiness of LLMs and proposes a 'sandwich' architecture to mitigate their non-deterministic nature. By wrapping LLMs in deterministic tools and formal workflows, developers can automate repetitive tasks while maintaining system reliability.
Why it matters
This approach offers a practical framework for integrating unpredictable AI models into production-grade software engineering environments.
A. Karpathy once said that OpenAI researchers are effectively "automating themselves away" by improving their AI. Right now I develop Beagle SCM with Anthropic's Fable and it is of course a brilliant model able to spot nits in a mountain of code, file tickets, make fixes. Still, yesterday it managed to commit the build/ dir into a project, twice. It is brilliant, but clumsy.
The article is a technical opinion piece focused on software architecture without political or social bias.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in