Dataset wars, Bark, Kent Beck needs to recalibrate, StableLM & blind prompting is not prompt engineering
The dataset wars are heating up, Bark is a transformer-based text-to-audio model that can generate highly realistic, multilingual speech as well as other audio, Kent Beck needs to recalibrate after using ChatGPT, the team behind Stable Diffusion release a new open source language model & Mitchel Hashimoto weighs in on prompt engineering.
The dataset wars are heating up, Bark is a transformer-based text-to-audio model that can generate highly realistic, multilingual speech as well as other audio, Kent Beck needs to recalibrate after using ChatGPT, the team behind Stable Diffusion release a new open source language model & Mitchel Hashimoto weighs in on prompt engineering.
Changelog++ members support our work, get closer to the metal, and make the ads disappear. Join today!
Sponsors:
- Sentry – Session Replay! Rewind and replay every step of the user’s journey before and after they encountered an issue. Eliminate the guesswork and get to the root cause of an issue, faster. Use the code
CHANGELOGand get the team plan free for three months.
Featuring:
Show Notes:
All links mentioned in this episode of Changelog News (and more) are in its companion newsletter.
Something missing or broken? PRs welcome!
Timestamps:
(00:00) - Intro
(00:47) - Dataset wars
(02:05) - Bark
(03:07) - Kent Beck
(04:12) - StableLM
(05:05) - Sponsor: Sentry
(06:10) - Blind prompting
(07:12) - Outro