Experimental browser for the Atmosphere
Figure 1: Language gaps in AI health-claim accuracy European languages stay high; Hindi, Persian, Chinese, Korean, Arabic & Turkish drop sharply. Mistral plummets, Gemini & GPT-4o-mini stay flat.
Apr 28, 2025, 10:06 AM
{ "uri": "at://did:plc:aj3d62z2hv6fh5eh5cw4zia6/app.bsky.feed.post/3lnujepu73s2o", "cid": "bafyreiedqjxokgrr2hv3jhff2gtl4faumbix46lxod6nxr5wxaayrsk3ei", "value": { "text": "Figure 1: Language gaps in AI health-claim accuracy\n\nEuropean languages stay high; Hindi, Persian, Chinese, Korean, Arabic & Turkish drop sharply. Mistral plummets, Gemini & GPT-4o-mini stay flat.", "$type": "app.bsky.feed.post", "embed": { "$type": "app.bsky.embed.images", "images": [ { "alt": "", "image": { "$type": "blob", "ref": { "$link": "bafkreiarnj7evhodbjhdaqucveen7g4ruhuuqnx2o44bcbkmrfotmfilke" }, "mimeType": "image/jpeg", "size": 327985 }, "aspectRatio": { "width": 2000, "height": 1333 } } ] }, "langs": [ "en" ], "reply": { "root": { "cid": "bafyreifff54y6i4uu7svol3qxxoxmjlllscfavnaolhfb4emuvqbzamvfi", "uri": "at://did:plc:aj3d62z2hv6fh5eh5cw4zia6/app.bsky.feed.post/3lnujeiqd422o" }, "parent": { "cid": "bafyreicrnmutycmo4kllvo63rbisisoanie7dbq5zvd2yrmcajyrphjkxq", "uri": "at://did:plc:aj3d62z2hv6fh5eh5cw4zia6/app.bsky.feed.post/3lnujen5we22o" } }, "createdAt": "2025-04-28T10:06:03.561Z" } }