Search
Have an existing account?
Sign In
Tag: post-training
Perplexity teaches its agent by grading its own failed tool calls
A new post-training method trains Perplexity's computer agent on real sessions, including the ones that went wrong.
Deep Cogito banks $43M to push post-training further
San Francisco startup Deep Cogito raised $43 million to build tools that improve models after pre-training.
GLM-5.3 ships from Z.ai with an unplanned cyber edge
Z.ai's GLM-5.3 skips retraining and scales up post-training, with an unexpectedly strong cyber capability.