Polyrob: what happens when your AI doesn’t need you to keep prompting it?
Most AI tools still wait for you to decide what happens next. You give an instruction, get a response and return with another prompt when there’s more work to do. POLYROB is exploring a different
BREAKING: same open model, same provider, same reasoning budget.
Swap only the coding harness and scores swing by ~24 points. Joël Niklaus just published the Harness Leaderboard: 28,849 trials, $4,746 of inference, nine harnesses on GLM-5.3-Flash, DeepSeek-V4.1-Flash, and Flint
Two LLMs go to war on equal hardware
GLM-5.3-Flash vs DeepSeek-V4.1-Flash, 2 DGX Sparks each. 2x DGX Spark, 256 GB: GLM-5.3-Flash Mia's TensorFold recipe, commit bf5f945 Mia's EXL3 quant, 4 bpw 2x DGX Spark, 256 GB: DeepSeek-V4.1-Flash Mia's TensorFold recipe, commit 0e7d421
Someone has created a github repo to use claude code for free
It's called free-claude-code and it works as a proxy between Claude Code and other models. Claude Code remains the same, but the requests go to free or local providers. Compatible providers: → Kimi and DeepSeek →
You have reached the end of the archive
All of deepseek