This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
SkynetAndChill.com
druce.ai
did:plc:qomkdnxrqw3gkbytdxea5z65
Anthropic serves full Opus 4.6 at about 170 tokens/sec (~2.5× vs 65) via low-batch inference, while OpenAI runs distilled GPT-5.3-Codex-Spark on Cerebras 44GB-SRAM chips for >1,000 tokens/sec (~15×), trading fidelity for much higher speed.
https://www.seangoedecke.com/fast-llm-inference/
2026-02-15T14:29:36.750Z