Richard Gill
@richardgill.org
Building llm-ui.com and limitphone.com.
richardgill.org
richardgill.org
LLMs are currently kind of slow.
OpenAI's new gpt-oss 120b is a pretty capable model in the benchmarks (maybe ~1 year behind the state of the art)
If you run it on Cerebras you can glimpse the speed improvements that are coming.
OpenAI's new gpt-oss 120b is a pretty capable model in the benchmarks (maybe ~1 year behind the state of the art)
If you run it on Cerebras you can glimpse the speed improvements that are coming.
August 7, 2025 at 5:49 PM
LLMs are currently kind of slow.
OpenAI's new gpt-oss 120b is a pretty capable model in the benchmarks (maybe ~1 year behind the state of the art)
If you run it on Cerebras you can glimpse the speed improvements that are coming.
OpenAI's new gpt-oss 120b is a pretty capable model in the benchmarks (maybe ~1 year behind the state of the art)
If you run it on Cerebras you can glimpse the speed improvements that are coming.
limitphone.com/demo now has a proper video player (planning to put this video on the homepage).
Now I just have to figure out why creating a youtube-ish player is so bloody difficult in 2025!
Now I just have to figure out why creating a youtube-ish player is so bloody difficult in 2025!
May 1, 2025 at 8:42 PM
limitphone.com/demo now has a proper video player (planning to put this video on the homepage).
Now I just have to figure out why creating a youtube-ish player is so bloody difficult in 2025!
Now I just have to figure out why creating a youtube-ish player is so bloody difficult in 2025!
Just shipped a new version of Limit Phone which allows users to customize their website blocks 🌐
March 27, 2025 at 5:45 PM
Just shipped a new version of Limit Phone which allows users to customize their website blocks 🌐