| 31. | | GPT-5 Thinking in ChatGPT (a.k.a. Research Goblin) is good at search (simonwillison.net) |
| 361 points by simonw 5 months ago | past | 255 comments |
|
| 32. | | Nothing to see here (it was Cloudflare crawler hints) (simonwillison.net) |
| 15 points by simonw 6 months ago | past | 2 comments |
|
| 33. | | Vibe code is legacy code (val.town) |
| 758 points by simonw 6 months ago | past | 454 comments |
|
| 34. | | The best available open weight LLMs now come from China (simonwillison.net) |
| 13 points by simonw 6 months ago | past | 4 comments |
|
| 35. | | My 2.5 year old laptop can write Space Invaders in JavaScript now (GLM-4.5 Air) (simonwillison.net) |
| 577 points by simonw 6 months ago | past | 396 comments |
|
| 36. | | Using GitHub Spark to Reverse Engineer GitHub Spark (simonwillison.net) |
| 7 points by simonw 6 months ago | past | 4 comments |
|
| 37. | | Vibe scraping and vibe coding a schedule webapp for a conference on my phone (simonwillison.net) |
| 19 points by simonw 7 months ago | past | 13 comments |
|
| 38. | | Grok: Searching X for "From:Elonmusk (Israel or Palestine or Hamas or Gaza)" (simonwillison.net) |
| 734 points by simonw 7 months ago | past | 546 comments |
|
| 39. | | AI agent lethal trifecta: private data, untrusted content, exfiltration vectors (simonwillison.net) |
| 7 points by simonw 8 months ago | past | 1 comment |
|
| 40. | | Design Patterns for Securing LLM Agents Against Prompt Injections (simonwillison.net) |
| 110 points by simonw 8 months ago | past | 28 comments |
|
| 41. | | The last six months in LLMs, illustrated by pelicans on bicycles (simonwillison.net) |
| 7 points by simonw 8 months ago | past |
|
| 42. | | Show HN: My LLM CLI tool can run tools now, from Python code or plugins (simonwillison.net) |
| 529 points by simonw 8 months ago | past | 165 comments |
|
| 43. | | Watching o3 guess a photo's location is surreal, dystopian and entertaining (simonwillison.net) |
| 987 points by simonw 9 months ago | past | 433 comments |
|
| 44. | | AI assisted search-based research works now (simonwillison.net) |
| 283 points by simonw 10 months ago | past | 147 comments |
|
| 45. | | Image segmentation using Gemini 2.5 (simonwillison.net) |
| 2 points by simonw 10 months ago | past |
|
| 46. | | CaMeL offers a promising new direction for mitigating prompt injection attacks (simonwillison.net) |
| 5 points by simonw 10 months ago | past |
|
| 47. | | Model Context Protocol has prompt injection security problems (simonwillison.net) |
| 6 points by simonw 10 months ago | past | 8 comments |
|
| 48. | | Long context support in LLM 0.24 using fragments and template plugins (simonwillison.net) |
| 1 point by simonw 10 months ago | past |
|
| 49. | | Here's how I use LLMs to help me write code (simonwillison.net) |
| 68 points by simonw 11 months ago | past | 4 comments |
|
| 50. | | Structured data extraction from unstructured content using LLM schemas (simonwillison.net) |
| 3 points by simonw 11 months ago | past |
|
| 51. | | Claude 3.7 Sonnet, extended thinking and long output (simonwillison.net) |
| 3 points by simonw 11 months ago | past |
|
| 52. | | Run LLMs on macOS using LLM-mlx and Apple's MLX framework (simonwillison.net) |
| 6 points by simonw on Feb 15, 2025 | past |
|
| 53. | | Ask HN: Is your company running any "agents", Jan 2025 edition |
| 5 points by simonw on Jan 30, 2025 | past |
|
| 54. | | Qwen2.5-7B-Instruct-1M and Qwen2.5-14B-Instruct-1M (simonwillison.net) |
| 98 points by simonw on Jan 26, 2025 | past | 2 comments |
|
| 55. | | Anthropic's New Citations API (simonwillison.net) |
| 4 points by simonw on Jan 24, 2025 | past | 1 comment |
|
| 56. | | Generative AI – The Power and the Glory (bnef.com) |
| 4 points by simonw on Jan 12, 2025 | past | 1 comment |
|
| 57. | | Agents – Adapted from the AI Engineering Chapter by Chip Huyen (huyenchip.com) |
| 5 points by simonw on Jan 11, 2025 | past |
|
| 58. | | Things we learned about LLMs in 2024 (simonwillison.net) |
| 984 points by simonw on Dec 31, 2024 | past | 582 comments |
|
| 59. | | My Approach to Building Large Technical Projects (2023) (mitchellh.com) |
| 2 points by simonw on Dec 28, 2024 | past | 1 comment |
|
| 60. | | Trying out QvQ – Qwen's new visual reasoning model (simonwillison.net) |
| 236 points by simonw on Dec 24, 2024 | past | 82 comments |
|
|
| More |
