Independent open source developer and creator of Datasette
Simon Willison
Simon Willison is an independent developer, Datasette creator, and Django co-creator who builds open source tools and writes about language models.
About Simon Willison
Simon Willison is an independent open source developer and the creator of Datasette, a tool for exploring and publishing data. He builds software for data journalism and maintains LLM, a Python library and command-line tool for working with large language models.
He is a co-creator of the Django web framework and previously worked as an engineering director at Eventbrite after its acquisition of Lanyrd, which he co-founded. His long-running blog documents programming, AI tools, and experiments with language models.
Mentioned in our coverage
80 articles name Simon Willison, excluding author credits.
Page 7 of 7
- Zuckerberg Admits AI Agents Are Progressing Slower Than Expected →
At an internal town hall, Mark Zuckerberg admitted Meta's AI agent bets "haven't come to fruition yet" — months after laying off 10% of the company and reassigning 7,000 people on the assumption they would. Developers on Hacker News had a blunter diagnosis: agents multiply code output, but review is the bottleneck and unsupervised autonomy still doesn't work.
- Qwen 3.6 27B Local Dev Guide: llama.cpp, OpenCode, and Why Dense Beats MoE →
After HN front-page hype, hands-on tests say Qwen 3.6 27B dense is the local sweet spot — better code than the 35B MoE, runnable at Q8 on 48GB RAM. Full llama.cpp + OpenCode config inside.
- Codex Slash Commands: Complete CLI Reference (2026) →
Codex CLI exposes 40+ slash commands for models, permissions, goals, subagents, review, and session control. This is the complete reference: what each command does, when to use it, and how they fit a typical workflow.
- Introducing Dynamic Workflows in Claude Code: Quarter-Long Work in Days →
Claude Code introduces dynamic workflows that run tens to hundreds of parallel subagents in a single session, handling complex tasks like codebase-wide migrations, bug hunts, and security audits that would normally take weeks.
- Claude Opus 4.8: Agentic Improvements, Faster Speed, and Better Accuracy →
Claude Opus 4.8 delivers measurable improvements in agentic benchmarks, achieves 69.2% on SWE-bench Pro, and is 4x less likely to let code flaws pass unremarked. Fast mode is now 3x cheaper.