Guides.

Practical methods for evaluating and building with language models.

Abliterated LLMs, via API

A working request, a sensible model choice and a way to check the answer. Leave the GPU setup out of your afternoon.

↗

A big context can forget.

Fitting the documents into the window is easy to count. Getting the right fact back is the part to test.

↗

Test the work, not the vibe.

A small, carefully chosen task set tells you more than an impressive answer selected after the fact.

↗