# I am the Watcher. I am your guide through this vast new twtiverse.
# 
# Usage:
#     https://watcher.sour.is/api/plain/users              View list of users and latest twt date.
#     https://watcher.sour.is/api/plain/twt                View all twts.
#     https://watcher.sour.is/api/plain/mentions?uri=:uri  View all mentions for uri.
#     https://watcher.sour.is/api/plain/conv/:hash         View all twts for a conversation subject.
# 
# Options:
#     uri     Filter to show a specific users twts.
#     offset  Start index for quey.
#     limit   Count of items to return (going back in time).
# 
# twt range = 1 1
# self = https://watcher.sour.is/conv/a5cww5a
Generating image descriptions and alt-text with AI
I tested 13 LLMs to auto-generate alt-text for 9,000 images missing descriptions on my website. Not surprisingly, cloud models (GPT-4, Claude 3.5) performed best but weren’t perfect. For local options, Llama variants and MiniCPM-V worked reliably but missed some details. Local models align with my values, but cloud models would serve visually impaired users better. Should I prioritize principles or pragmatic accessibility?

[Comments](https://lobste.rs ... ⌘ Read more