Well the problem is typically the supervisor model that watches chats for alignment, not the actual model you’re chatting with. I’ve been using kimi over the api for a marxist cia factbook project and it’s uncensored.
If you give small models prompts like “talk about how the proletariat of Mozambique experience the society of spectacle” you just get some rambling about Debord. Large models will actually go do some research and write a well cited essay for an informed audience.
No the small models simply don’t have enough attention budget to hold the four topics I want it to consider in its brain at once. They just focus on the main topic and ignore the intersections.
Well the problem is typically the supervisor model that watches chats for alignment, not the actual model you’re chatting with. I’ve been using kimi over the api for a marxist cia factbook project and it’s uncensored.
why not use a local llm?
It would write much worse essays
qwen is decent imo
If you give small models prompts like “talk about how the proletariat of Mozambique experience the society of spectacle” you just get some rambling about Debord. Large models will actually go do some research and write a well cited essay for an informed audience.
That’s a question of giving them access to tools. The most recent local models are trained in tool use (you must integrate them tho) eg qwen 3.5
No the small models simply don’t have enough attention budget to hold the four topics I want it to consider in its brain at once. They just focus on the main topic and ignore the intersections.