{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreibx6om3o56veten5tptkmtn4jcwxqtwgaqv4xzetwmtqvo6kuyuem",
"uri": "at://did:plc:mxzzpugn7bprjjrszwkbez3u/app.bsky.feed.post/3ml3f3hybcr52"
},
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreibhtc4twtk7kcm5omqjj5qihpm6mgiskg47o72s5m7tmwylceznma"
},
"mimeType": "image/jpeg",
"size": 161506
},
"path": "/news/2026-05-simple-physics-ai.html",
"publishedAt": "2026-05-05T00:00:01.000Z",
"site": "https://techxplore.com",
"tags": [
"Computer Sciences"
],
"textContent": "Artificial intelligence systems based on neural networks—such as ChatGPT, Claude, DeepSeek or Gemini—are extraordinarily powerful, yet their internal workings remain largely a \"black box.\" To better understand how these systems produce their responses, a group of physicists at Harvard University has developed a simplified mathematical model of learning in neural networks that can be analyzed mathematically using the tools of statistical physics.",
"title": "A simple physics-inspired model sheds light on how AI learns"
}