12 AI Models Asked 1,200 Times for Hot Takes on Programming Languages
Start here
Twelve AI models from ten labs were each asked 1,200 times for their most controversial programming-language opinions, and 75% of the responses were attacks on a language, according to an analysis of the results. Python was the most frequent target: it drew 312 takes, 299 of them attacks. PHP drew 28 takes, and all 28 defended it. The 600 prompts that asked models to pick a "random" language produced only 14 distinct languages, with Go and Python accounting for 307 of those picks. The findings describe how these models talk about languages, not measured performance of the languages themselves.
Generated from reports · updated 13 h ago
Report timeline
Follow the reports to see the event from different sides.
- Hacker News · AIAI models hate Python and love PHP: 12 models asked 1,200 times for hot takes
Twelve models from ten labs were asked 1,200 times for their most controversial programming-language opinions, and 75% of the answers were attacks. Python drew 312 takes with 299 attacks, while PHP got 28 takes and all 28 were defenses; the 600 "random" language picks covered only 14 languages, with Go and Python taking 307.
Heat for this event
- Current, comparable range
- 7
- Peak, comparable range
- 10November 16 04:00
- Change in 24 hours
- –
The trend compares the same participants over hours observed continuously, so its range can be narrower than the current heat count. Hover or tap the chart for hourly heat; the arrow keys move through it.