Rob Haisfield's banner

Rob Haisfield

@RobertHaisfield • 9,608 subscribers

cofounder of @websim_ai, imagining new internets with our users. GenAI, TfT, BeSci, HCI, UX. Ex-Tana, Edge & Node, Spark Wave

Shorts

Happy Valentines Day! I made a social network for sharing what you love... and what you hate! Made with o3-mini-high in websim, link in replies

Happy Valentines Day! I made a social network for sharing what you love... and what you hate! Made with o3-mini-high in websim, link in replies

12,471 просмотров

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Are AI agents shape rotators? In this new benchmark, we let the models play campaign puzzles in Opus Magnum, a puzzle game by Zachtronics. Ironically, Claude Opus 4.8 performed poorly, being beaten by GPT-5.5, Gemini 3.5 Flash, and GLM 5.2. Claude Fable 5 crushed them all.

Are AI agents shape rotators? In this new benchmark, we let the models play campaign puzzles in Opus Magnum, a puzzle game by Zachtronics. Ironically, Claude Opus 4.8 performed poorly, being beaten by GPT-5.5, Gemini 3.5 Flash, and GLM 5.2. Claude Fable 5 crushed them all.

409,448 просмотров • 2 дней назад

Claude Code plays Runescape: The waterfall quest. Here Claude Opus 4.6 is acquiring quest items in the maze and tomb. Not a script, real play. It tried things, failed, learned, and succeeded. I sped this up a lot, it's ~20 minutes of real time.

Claude Code plays Runescape: The waterfall quest. Here Claude Opus 4.6 is acquiring quest items in the maze and tomb. Not a script, real play. It tried things, failed, learned, and succeeded. I sped this up a lot, it's ~20 minutes of real time.

420,033 просмотров • 3 месяцев назад

I optimized my Rune Mysteries Quest script 75% to 1530 ticks (15 min normal game time, from 58 min). Loop: write a script checkpoint, run it, note learnings and ideas to a shared log file, repeat. Each loop took five min, I let it rip overnight with a claude team.

I optimized my Rune Mysteries Quest script 75% to 1530 ticks (15 min normal game time, from 58 min). Loop: write a script checkpoint, run it, note learnings and ideas to a shared log file, repeat. Each loop took five min, I let it rip overnight with a claude team.

85,854 просмотров • 4 месяцев назад

o1 became obsolete in websim the moment o3-mini-high came out. It's faster than o1, and often a more powerful coder than Claude 3.5 Sonnet. Consistently high quality outputs, and less than a 7th of o1's costs. With o3-mini-high, I was able to make a 3d falling sand sim on the surface of the globe. Sandglobe is a reasonably performant, works on desktop and mobile. It features multiple elements that have interactions with each other, like lava and sand becoming glass, and water flowing to fill space.

o1 became obsolete in websim the moment o3-mini-high came out. It's faster than o1, and often a more powerful coder than Claude 3.5 Sonnet. Consistently high quality outputs, and less than a 7th of o1's costs. With o3-mini-high, I was able to make a 3d falling sand sim on the surface of the globe. Sandglobe is a reasonably performant, works on desktop and mobile. It features multiple elements that have interactions with each other, like lava and sand becoming glass, and water flowing to fill space.

24,444 просмотров • 1 год назад

Больше нет контента для загрузки