Here’s how I use LLMs to help me write code
Online discussions about using Large Language Models to help write code inevitably produce comments from developers who’s experiences have been disappointing. They often ask what they’re doing wrong—how come some …
Here’s how I use LLMs to help me write code Simon Willison’s Weblog Subscribe Sponsored by: Microsoft - Agent projects stall between demo and production. Microsoft's MVP checklist closes that gap. Try it Here’s how I use LLMs to help me write code 11th March 2025 Online discussions about using Large Language Models to help write code inevitably produce comments from developers who’s experiences have been disappointing. They often ask what they’re doing wrong—how come some people are reporting such great results when their own experiments have proved lacking? Using LLMs to write code is difficu
Explore this link on the map →saved by
related reading
- crawshaw - 2025-01-06crawshaw.io
- Best practices for Claude Code - Claude Code Docsanthropic.com
- A Guide to Claude Code 2.0 and getting better at using coding agents – sankalp's blogsankalp.bearblog.dev
- How I use LLMs as a staff engineerseangoedecke.com
- 2025: The year in LLMssimonwillison.net
- How I Use Claude Code | Philipp Spiessspiess.dev
- Scaling LLMs to larger codebases - Kieran Gillblog.kierangill.xyz
- GitHub - multica-ai/andrej-karpathy-skills: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. · GitHubgithub.com
- Designing agentic loopssimonwillison.net
- Tips and Code for Empirical Research Workflows — AI Alignment Forumalignmentforum.org
- Cheating is all you need | Sourcegraphabout.sourcegraph.com
- Don’t Outsource Your Thinkingteltam.github.io