The assistant axis: situating and stabilizing the character of LLMs
https://www.anthropic.com/research/assistant-axis
#HackerNews #assistant #axis #LLMs #AI #research #character #stability #Anthropic
Mastodon•ART 🎨 Curator
boosted
PLP316: Lobstered Garlic #art #MastoArt #DigitalArt #DigitalPainting #Photoshop #sketch #Stylized #Fantasy #Character #Armor #Spade
PLP316: Lobstered Garlic #art #MastoArt #DigitalArt #DigitalPainting #Photoshop #sketch #Stylized #Fantasy #Character #Armor #Spade
Mastodon•ART 🎨 Curator
boosted
halcy :icosahedron:
boosted
#heavy #inktober #day9
Again something a little more surreal ... 😊
#inktober #inktober2025 #inktober25 #rendertober #rendertober2025 #rendertober25 #3DRender #render #RenderedArt #Xanathon #Apple #DAZStudio #DAZ #DAZ3D #Character #Atlas #Eye #Surreal
#heavy #inktober #day9
Again something a little more surreal ... 😊
#inktober #inktober2025 #inktober25 #rendertober #rendertober2025 #rendertober25 #3DRender #render #RenderedArt #Xanathon #Apple #DAZStudio #DAZ #DAZ3D #Character #Atlas #Eye #Surreal
wakest ⁂ FOSDEM
boosted
Each time i use https://shapecatcher.com
I'm gratefull to #BenjaminMilde to have build it and keep it running.
"You know what some #character looks like, but you've forgotten its name or its #Unicode code point. Now what do you do? #Shapecatcher is a new website, that helps you to find specific Unicode characters, just by #sketching their shape. Currently about 10000 of the most important Unicode characters are compared to your sketch and are analysed for similarities.
Under the hood, Shapecatcher uses so called " #shape contexts" to find similarities between two shapes. Shape contexts, a robust mathematical way of describing the concept of similarity between shapes, is a feature descriptor first proposed by #SergeBelongie and #JitendraMalik."
4 media
Each time i use https://shapecatcher.com
I'm gratefull to #BenjaminMilde to have build it and keep it running.
"You know what some #character looks like, but you've forgotten its name or its #Unicode code point. Now what do you do? #Shapecatcher is a new website, that helps you to find specific Unicode characters, just by #sketching their shape. Currently about 10000 of the most important Unicode characters are compared to your sketch and are analysed for similarities.
Under the hood, Shapecatcher uses so called " #shape contexts" to find similarities between two shapes. Shape contexts, a robust mathematical way of describing the concept of similarity between shapes, is a feature descriptor first proposed by #SergeBelongie and #JitendraMalik."
4 media