ATProto Browser

Experimental browser for the Atmosphere

Post

Interesting new benchmark that aims at evaluating the safety of LLMs in conversational AI. Google Gemma 2 9b, an Open-Weights model achieved "Very Good" rating. Note: AILuminate has a limited scope and it compares models of varying accessibility and scale. ailuminate.mlcommons.org

Dec 7, 2024, 1:05 PM

Loading post...

Record data

{
  "uri": "at://did:plc:uavs3b5de27ki26k5usmqtxz/app.bsky.feed.like/3lcvhl2eey62f",
  "cid": "bafyreid7chl4mcpp5hohkapa4l7snp77v7bl67wd7uoem424yqgqb4lc3y",
  "value": {
    "$type": "app.bsky.feed.like",
    "subject": {
      "cid": "bafyreif7irdtvvq7phcqnn56gx3mmzakpusnromkyne5wyymspo5q4k3nm",
      "uri": "at://did:plc:x6m5zvil3cirjfu3co4uf2gb/app.bsky.feed.post/3lcpr6uqgic2p"
    },
    "createdAt": "2024-12-09T19:29:27.933Z"
  }
}