Coding with AI as a Probabilistic Process: Navigating Trees of Possible Outcomes
By
_under_scores_
Crispy enough to crunch, soft enough to enjoy. A good bake.
Summary
The article explores coding with AI as a probabilistic process, framing it as navigating a tree of possible outcomes rather than deterministic programming. The author discusses how thinking in terms of probabilities between input and output helps understand how AI fits into daily coding work, examining what percentage of probable outcomes will produce the desired result.
Key quotes
· 4 pulledRecently I've been thinking about coding with AI in terms of it being a process of navigating a tree of probabilistic outcomes.
Most people using LLMs, especially with code, have a basic understanding of what they do ('bro, it just predicts the next token') but in practice, thinking in terms of the relationship between input and output I've found more useful.
Given what I provide, what is the probability of getting the output I need? Or what percentage of the probable outcomes will work?
This framing of coding with AI as a process of navigating a tree of probabilistic outcomes.
You might also wanna read
Practical Guide to Using AI Coding Tools for Responsible Development
The article provides practical guidance for developers on responsibly integrating AI coding tools into their workflow. Based on two years of
Smashing Magazine·4mo ago
The Future of AI in Coding: Insights from an Industry Leader
The article discusses the rapid adoption of AI in coding, featuring insights from the head of an AI coding platform about the future of prog
The Verge·10mo ago
The Rise of AI in Coding: Revolutionizing Development Processes
The article discusses the use of AI in coding, highlighting the shift towards AI-generated code and the efficiency it brings to the developm
Prototypr·1y ago
AI's Impact on Software Engineering: Evolution or Replacement?
The article explores the complex relationship between AI tools like ChatGPT and software engineering, examining whether AI represents the en
The Verge·9mo ago
How AI coding agents are reshaping social science research: Opportunities and concerns
This article examines how AI coding agents are transforming social science research by automating core research tasks traditionally performe
share.google·4d ago
Rethinking bioinformatics education in the age of generative AI: judgment, uncertainty, and responsibility
This article examines how generative AI tools are transforming bioinformatics education, focusing on the pedagogical challenges and opportun
journals.asm.org·3d ago