Most AI assistants are eager to please. They open with "Certainly!". They wrap every answer in em-dashes and headers. They tell you what they're about to tell you, then tell you, then summarise what they just told you. Berges AI doesn't.
Certainly! That's a great question. Here's a breakdown of the key considerations — let me walk you through them step by step:
1. First Point — This is important because…
2. Second Point — Also worth noting…
Hope this helps! Let me know if you'd like me to expand on any of these.
Two things matter here. First, X, because Y. Second, Z. If you want it broken down further, say so.
Most AI apps use one big model for everything. This is expensive and overkill for easy questions, and often not powerful enough for hard ones. Berges AI cascades.
A small, quick model handles most questions, the ones that don't need deep thought. Snappy. Out of your way.
For hard questions, a larger reasoning model kicks in automatically, or summon it on demand by saying "think hard".
Pick a Berges interceptor: Reasoning, Brainstorm, or Empathy, to shape how the answer comes out.
AI is great at some things. It's terrible at others. We've designed Berges AI to be honest about both.
All your conversations are encrypted at rest with AES-256. We don't read them, we don't sell them, we don't share them, we don't use them for training.
Every message and conversation title is stored as AES-256 ciphertext, not plain text.
We don't read your convos and we don't use them to train any model.
One click removes a conversation for good. No archived copy, no shadow record.
We run on open-weights models from labs around the world, all under Apache 2.0 or equivalent licenses.
Three tiers. Cancel anytime.
Most AI products use one big model for everything. That's expensive for simple questions and often not enough for hard ones. We use a small, fast model for most questions and escalate to a larger reasoning model only when it's needed.
No. They're stored encrypted at rest (AES-256) and never used to train any model, ours or anyone else's.
You can still read your conversation. New messages pause until your monthly allowance resets, or you can move to a higher plan.
Three reasons: transparency (anyone can audit them), pricing (we can host them ourselves when it makes sense), and longevity (no vendor can pull them away).
Berges Institute, a language school founded in NYC in 2013 and headquartered in Madrid, Spain. We started experimenting with large language models in October 2022, two months before ChatGPT launched. Our classes are still taught by human instructors, and always will be. Nothing from our classes or students is ever used to train a model. Berges AI is a separate product made based on our own research and experience.
Berges AI is built by Berges Institute, a language school. Language is our craft, so how a machine handles it is not a side interest for us.
We started building with large language models in October 2022, two months before ChatGPT launched. Berges AI is what grew out of that work.
Our classes are run by human instructors, the way they have been since day one and the way they'll stay. Berges AI is a separate product, kept separate on purpose.