{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreigan6mgejflsdi5rbhcbzqhmiitfjer5kbf4th4p6vtqxgkslju5i",
"uri": "at://did:plc:ctcqaqa3tlbhfwmfefti346h/app.bsky.feed.post/3mg77a5av7vu2"
},
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreidjw3csclw7o2ubnn7akc74dcy2hy5o3eabg777vrnf47yvpzh234"
},
"mimeType": "image/jpeg",
"size": 100692
},
"path": "/pro/rewriting-the-blueprint-not-removing-bricks-multiverse-computing-says-it-can-shrink-large-ai-models-and-cut-memory-use-in-half",
"publishedAt": "2026-03-04T01:20:00.000Z",
"site": "https://www.techradar.com",
"tags": [
"Pro"
],
"textContent": "Multiverse launches compressed OpenAI language model designed to cut memory needs and lower AI infrastructure costs.",
"title": "“Rewriting the blueprint, not removing bricks”: Multiverse Computing says it can shrink large AI models and cut memory use in half",
"updatedAt": "2026-03-04T01:20:00.000Z"
}