|
|
|
|
|
|
by driesbuytaert
505 days ago
|
|
|
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? |
|
|