Meta AI adds interleaved image-and-text input to its text box
ezyang · x · 2026-07-22
Meta AI’s text input now supports interleaved images and text.
The post points out a small but meaningful UI change: instead of treating images as separate attachments, users can now mix images directly into the prompt flow. The author describes this as a cleaner interaction model and says Meta AI is currently ahead here, at least in this specific UX detail.
The attached screenshot shows the new inline image-and-text input behavior.
Related event: Meta AI Adds Interleaved Text and Image Input(3 posts)→
More from Apps
- Fleetbase: open-source modular logistics OS for delivery tracking and fleet management — tom_doerr · 2026-09-11
- AI Is Tracking You to Set Personalized Prices — Use VPNs to Exploit Regional Pricing Gaps — DavidLinthicum · 2026-09-11
- Non-coder builds full-featured Android ComfyUI client with ChatGPT, submits to Google Play — ComfierUI · 2026-09-11
- Fully local voice assistant on an RTX 3060 replicates the GPT Live demo in 6.5 minutes — liampetti · 2026-09-11
- Amazon and Google sold 600M+ smart speakers, so why no AGI-era successor? — julianlehr · 2026-09-11
- Internet Archive indexed 4.43M TV broadcasts since 2009 — now you can full-text search what TV said — moonsandhues · 2026-09-11