new
Small
There's a new UI for visualizing the number of chars, custom ai steps, and credit on your account accessible via Account Settings.
fixed
Recently, there have been a number of bugs with the text-to-speech (tts) option that have been fixed:
- the button has been available for people on tiers that shouldn't have access to tts but didn't work when used
- Auto TTS upon generation selection was broken
fixed
Small
Previously, character counts were inaccurate, leading to general confusion regarding remaining characters left for generations. This issue has been fixed.
improved
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
improved
Medium
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
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
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
improved
We've added some keyboard shortcuts to make creating and choosing generations more efficient. You can now:
- use ctl+enterorcmd+enter(for mac) to generate in addition to the oldshift+tabshortcut.
- use your arrow keys to cycle through generations
- use enterto select a generation
- use escapeto close the generation window
improved
fixed
Two fixes/improvements:
- For a while you had to use your mouse to select a given tag, now the UI works with keyboard navigation.
- The Tag selection UI is much more compact and doesn't have it's own separate viewing window which should be more intuitive that previous versions
Load More
→