Hey Product Hunt, I’m Sam 👋

Most LLMs are trained to agree with you (RLHF). Ask one if a bad idea is good and it’ll lean towards yes, taking multiple paragraphs to do so. I wanted a model that questions my assumptions, pushes back when it matters, and stays quiet when it doesn’t. That became nen-1. A fine-tuned model trained to be concise and question assumptions, instead of padded and flattering.

(note: get one month of Nen Pro for free! reminder email 5 days before billing)

NEN MODEL's: nen-1, nen-2, & nen-alia 🍃

• trained differently to frontier models: a refusal of the axis everyone else maximises
• web search optimised for register and user absorption
• models integrated into notes pages and logbook, so you can query nen-1 about your notes or search the web without leaving the page
• composer (⌘+K) for seamless discussion with nen model's, from any page

SPACE: tasks · notes · logbook · habits · memory 🌍

capture & sift:
• a thought arrives at the wrong time…walking, cooking, mid-task
• capture it in working-memory (not every idea needs to become a “thing” immediately)
• when you get some time, press sift to read the pile of captured notes, thoughts, ideas, and a place is proposed for each: a task, a note, a habit, a space…or simply set it down for later
• nothing moves without an ok, everything is recoverable

A brain does two things: it remembers and it thinks. Every app that calls itself a “second brain” only does the first and leaves you to do the filing. Every LLM does the second but it thinks for you, and is trained to agree with you. You're outsourcing your thinking. The purpose of AI does not have to be thinking for you, but to return you to your own thinking.

I’d love feedback, especially on the models but also what you'd like to see in the /space side as well!

Peace & love 🌍 🫶

nenspace

the lo-fi of LLMs: your mind, made larger

the lo-fi of LLMs: your mind, made larger