| | Unauthorized Experiment on CMV Involving AI-Generated Comments (simonwillison.net) |
|
41 points by pavel_lishin 12 hours ago | past | 13 comments
|
|
| | Unauthorized Experiment on CMV Involving AI-Generated Comments (simonwillison.net) |
|
2 points by imichael 21 hours ago | past | 1 comment
|
|
| | The GeoGuessr StreetView meta-game (simonwillison.net) |
|
4 points by ulrischa 1 day ago | past | discuss
|
|
| | Not all AI-assisted programming is vibe coding (but vibe coding rocks) (simonwillison.net) |
|
1 point by Anon84 1 day ago | past | discuss
|
|
| | Watching o3 guess a photo's location is surreal, dystopian and entertaining (simonwillison.net) |
|
932 points by simonw 1 day ago | past | 412 comments
|
|
| | Not all AI-assisted programming is vibe coding (but vibe coding rocks) (simonwillison.net) |
|
1 point by badmonster 2 days ago | past | 1 comment
|
|
| | Not all AI-assisted programming is vibe coding (but vibe coding rocks) (simonwillison.net) |
|
3 points by misonic 2 days ago | past | discuss
|
|
| | A swan won't prevent a hurricane; Google AI hallucinates meaning and sources (simonwillison.net) |
|
2 points by isaacfrond 3 days ago | past | 1 comment
|
|
| | A5: Like Uber's H3 but a bit weirder and more fun (simonwillison.net) |
|
3 points by pheelicks 3 days ago | past | discuss
|
|
| | AI assisted search-based research works now (simonwillison.net) |
|
280 points by simonw 6 days ago | past | 145 comments
|
|
| | Maybe Meta's Llama claims to be open source because of the EU AI act (simonwillison.net) |
|
28 points by code_reader 7 days ago | past | 14 comments
|
|
| | Maybe Meta's Llama claims to be open source because of the EU AI act (simonwillison.net) |
|
4 points by gslin 8 days ago | past | discuss
|
|
| | Ultrathink is a Claude Code magic word (simonwillison.net) |
|
113 points by ghuntley 8 days ago | past | 39 comments
|
|
| | Gemma 3 QAT Models (simonwillison.net) |
|
4 points by mdp2021 8 days ago | past | 3 comments
|
|
| | Image segmentation using Gemini 2.5 (simonwillison.net) |
|
2 points by simonw 9 days ago | past | discuss
|
|
| | CaMeL offers a promising new direction for mitigating prompt injection attacks (simonwillison.net) |
|
17 points by birdculture 14 days ago | past | 3 comments
|
|
| | CaMeL offers a promising new direction for mitigating prompt injection attacks (simonwillison.net) |
|
5 points by simonw 16 days ago | past
|
|
| | Model Context Protocol has prompt injection security problems (simonwillison.net) |
|
4 points by gregorymichael 16 days ago | past
|
|
| | Model Context Protocol has prompt injection security problems (simonwillison.net) |
|
6 points by simonw 18 days ago | past | 8 comments
|
|
| | Long context support in LLM 0.24 using fragments and template plugins (simonwillison.net) |
|
1 point by simonw 20 days ago | past
|
|
| | Initial Impressions of Llama 4 (simonwillison.net) |
|
4 points by ode 21 days ago | past
|
|
| | Incomplete JSON Pretty Printer (simonwillison.net) |
|
2 points by tosh 22 days ago | past
|
|
| | Not all AI-assisted programming is vibe coding (simonwillison.net) |
|
5 points by wslh 23 days ago | past
|
|
| | LLM Schemas (simonwillison.net) |
|
5 points by pchristensen 28 days ago | past | 1 comment
|
|
| | Incomplete JSON Pretty Printer (simonwillison.net) |
|
2 points by soheilpro 30 days ago | past
|
|
| | Putting Gemini 2.5 Pro through its paces (simonwillison.net) |
|
2 points by karma_daemon 32 days ago | past
|
|
| | Putting Gemini 2.5 Pro through its paces (simonwillison.net) |
|
5 points by LyalinDotCom 33 days ago | past
|
|
| | The interesting ideas in Datasette (2018) (simonwillison.net) |
|
1 point by Tomte 33 days ago | past
|
|
| | Qwen2.5-VL-32B: Smarter and Lighter (simonwillison.net) |
|
3 points by thunderbong 33 days ago | past | 2 comments
|
|
| | The think tool: Enabling Claude to stop and think in complex tool use situations (simonwillison.net) |
|
4 points by andai 34 days ago | past
|
|
|
|
More |
