Submissions from simonwillison.net

		I ported JustHTML from Python to JavaScript with Codex CLI and GPT-5.2 in 4.5hrs (simonwillison.net)
		14 points by simonw 37 days ago \| past \| 3 comments
		2025 Word of the Year: Slop (simonwillison.net)
		2 points by vismit2000 37 days ago \| past \| 1 comment
		[dupe] Copywriters reveal how AI has decimated their industry (simonwillison.net)
		4 points by abdelhousni 38 days ago \| past
		JustHTML is an example of vibe engineering in action (simonwillison.net)
		5 points by lumpa 38 days ago \| past
		Willison on Merchant's "Copywriters reveal how AI has decimated their industry" (simonwillison.net)
		80 points by planckscnst 38 days ago \| past \| 92 comments
		What happens when the coding becomes the least interesting part of the work (simonwillison.net)
		6 points by mmaunder 39 days ago \| past \| 4 comments
		OpenAI are quietly adopting skills, now available in ChatGPT and Codex CLI (simonwillison.net)
		587 points by simonw 40 days ago \| past \| 324 comments
		Dark mode now available on Simon Willison's blog (simonwillison.net)
		1 point by macote 42 days ago \| past
		Useful patterns for building HTML tools (simonwillison.net)
		354 points by simonw 42 days ago \| past \| 94 comments
		The Resonant Computing Manifesto (simonwillison.net)
		2 points by mooreds 47 days ago \| past \| 3 comments
		DeepSeek-v3.2 (simonwillison.net)
		7 points by doppp 50 days ago \| past
		ChatGPT's Third Birthday (simonwillison.net)
		2 points by vismit2000 51 days ago \| past
		ChatGPT is three years old today (simonwillison.net)
		6 points by ingve 52 days ago \| past \| 2 comments
		ChatGPT prompt consumes equivalent to 10s of Netflix (simonwillison.net)
		8 points by makeavish 53 days ago \| past \| 4 comments
		Claude Opus 4.5, and why evaluating new LLMs is increasingly difficult (simonwillison.net)
		6 points by jonesn11 55 days ago \| past \| 1 comment
		Building Effective Agents (simonwillison.net)
		1 point by gearnode 56 days ago \| past
		Claude Opus 4.5, and why evaluating new LLMs is increasingly difficult (simonwillison.net)
		1 point by gingersnap 57 days ago \| past \| 1 comment
		Claude Opus 4.5, and why evaluating new LLMs is increasingly difficult (simonwillison.net)
		7 points by janpio 58 days ago \| past \| 2 comments
		Olmo 3 is a fully open LLM (simonwillison.net)
		5 points by lumpa 59 days ago \| past \| 2 comments
		LLM cmd, an LLM plugin to prompt and edit a shell command (simonwillison.net)
		2 points by skeledrew 61 days ago \| past
		The fate of "small" open source (simonwillison.net)
		2 points by synergy20 61 days ago \| past
		Nano Banana Pro is the best available image generation model (simonwillison.net)
		3 points by xnx 62 days ago \| past
		Google Antigravity (simonwillison.net)
		2 points by bilsbie 63 days ago \| past
		Google Antigravity (simonwillison.net)
		4 points by vismit2000 64 days ago \| past
		What happens if AI labs train for pelicans riding bicycles? (simonwillison.net)
		5 points by Jap2-0 64 days ago \| past
		Trying out Gemini 3 Pro with audio transcription and a new pelican benchmark (simonwillison.net)
		181 points by nabla9 64 days ago \| past \| 58 comments
		Netflix issues GenAI rules:no generative AI in final deliverables (simonwillison.net)
		3 points by isaacfrond 71 days ago \| past
		Reverse engineering Codex CLI to get GPT-5-Codex-Mini to draw me a pelican (simonwillison.net)
		168 points by simonw 73 days ago \| past \| 76 comments
		Using Codex CLI with GPT-OSS:120B on an Nvidia DGX Spark via Tailscale (simonwillison.net)
		4 points by kgwgk 75 days ago \| past
		Could LLMs encourage new programming languages? (simonwillison.net)
		3 points by coloneltcb 75 days ago \| past
		More