News for hackers. Stuff that matters.
Re:Command A+: Making sovereign agentic capabilities availab... by james2doyle on Wednesday May 20, 2026 @01:58PM (#48211558)
I’m always surprised by how performant the Cohere models are. They output quick. I tested out the BF16 and it seems pretty good. I tried out the FP8 one and it did seem a bit dumber. Curious to see how this ranks in benchmarks
Re:Command A+: Making sovereign agentic capabilities availab... by tulpa on Wednesday May 20, 2026 @12:30PM (#48210309)
New open-source model from Cohere
Re:Command A+: Making sovereign agentic capabilities availab... by armcat on Wednesday May 20, 2026 @05:35PM (#48214466)
This person did a great comparison against Qwen models, and despite them having 8x less active params, they outperform the Cohere model in every category: https://x.com/DJLougen/status/2057196012918149368?s=20