Changelog

Follow up on the latest improvements and updates.

RSS

There's a new UI for visualizing the number of chars, custom ai steps, and credit on your account accessible via Account Settings.
Recently, there have been a number of bugs with the text-to-speech (tts) option that have been fixed:

fixed

Small

Char counts

Previously, character counts were inaccurate, leading to general confusion regarding remaining characters left for generations. This issue has been fixed.
We've improved how prompts and activated context entries get budgeted, leading to better output for Dictionary-heavy Holos.
Changes made in January, published to change log in February
In December users reported intermittent downtime and general sluggishness. This has been fixed and as a bonus the site should be significantly faster.
Change made in January, published to change-log in February

fixed

Large

Model fixes

In January some users reported GPT-J as generating irregularly poor output. After a series of model changes and bug-fixes, we believe we have restored output quality.
Change made in January, published to change-log in February

new

Medium

Fairseq 13B

We’ve introduced a un-tuned Fairseq 13B model on our new $11.99/mo tier. We plan on releasing a new finetune for our GPT-J 6B model and 13B model at a later date.
Change made in January, published to change-log in February
We've added some keyboard shortcuts to make creating and choosing generations more efficient. You can now:
Two fixes/improvements:
We have provided more tool-tips and explanations in the Settings Panel, including all generation metadata settings.
Load More