{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreicztra44aqw4ja23warl5ith4d6c4sxdib4fcp2o36hjcioytbthq",
"uri": "at://did:plc:bbwgwecw2vdijmj42eealwtt/app.bsky.feed.post/3mnlqlufsrzd2"
},
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreidmo2c4trg34yshabc6j34e7be6d5fhtrwl2e7ovfn6xejzzgrczy"
},
"mimeType": "image/jpeg",
"size": 84591
},
"path": "/anthropic-started-red-teaming-new-mythos-models-first-results/",
"publishedAt": "2026-06-05T13:27:26.000Z",
"site": "https://www.testingcatalog.com",
"tags": [
"Claude News",
"AI Rumours",
"Latest AI News"
],
"textContent": "Anthropic is preparing to release the Claude Mythos model from a new \"Oceanus\" checkpoint, surfaced in early June, with a focus on reasoning, coding, and cybersecurity tasks.",
"title": "Anthropic started red teaming new Mythos models, first results"
}