Salesforce's SRD distills hindsight into foresight, rescuing agent RL when rewards vanish and lifting success from 0% to 60.6 ...
A 5 November post says Claude Sonnet 5.5 at Extra effort is serving the next Claude model. Both its tests pass on the model Anthropic already ships.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results