Collective Intelligence Project (@collect_intel) 's Twitter Profile
Collective Intelligence Project

@collect_intel

collective intelligence for collective progress.

donate: cip.org/donate

ID: 1559026473285083136

linkhttp://cip.org calendar_today15-08-2022 03:57:43

631 Tweet

4,4K Takipรงi

143 Takip Edilen

Zarinah Agnew (@zarinahagnew) 's Twitter Profile Photo

Over in Global Dialogues Collective Intelligence Project is asking the a global sample of the world: "๐–ฏ๐–พ๐—‹๐—Œ๐—ˆ๐—‡๐–บ๐—…๐—…๐—’, ๐—๐—ˆ๐—Ž๐—…๐–ฝ ๐—’๐—ˆ๐—Ž ๐–พ๐—๐–พ๐—‹ ๐–ผ๐—ˆ๐—‡๐—Œ๐—‚๐–ฝ๐–พ๐—‹ ๐—๐–บ๐—๐—‚๐—‡๐—€ ๐–บ ๐—‹๐—ˆ๐—†๐–บ๐—‡๐—๐—‚๐–ผ ๐—‹๐–พ๐—…๐–บ๐—๐—‚๐—ˆ๐—‡๐—Œ๐—๐—‚๐—‰ ๐—๐—‚๐—๐— ๐–บ๐—‡ ๐– ๐–จ, ๐—‚๐–ฟ ๐—๐—๐–พ ๐– ๐–จ ๐—๐–บ๐—Œ ๐–บ๐–ฝ๐—๐–บ๐—‡๐–ผ๐–พ๐–ฝ

Divya Siddarth (@divyasiddarth) 's Twitter Profile Photo

As we do societal evals at CIP โ€”public health, AI relationships, democracy, etc. across regional languages we've spent a lot of time dealing with how brittle LLM judge pipelines are. Stoked to share an open-source test suite (blog + code) weโ€™ve built to stress-test ours before

As we do societal evals at CIP โ€”public health, AI relationships, democracy, etc. across regional languages we've spent a lot of time dealing with how brittle LLM judge pipelines are. 

Stoked to share an open-source test suite (blog + code) weโ€™ve built to stress-test ours before