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 quietly hand your question to a lite model and pad the answer. Berges AI runs a frontier open-weights reasoning model on every turn, lets you pick which one, and cuts the padding.
A frontier open-weights reasoning model answers every question, and you watch it think. Pick DeepSeek, GLM, Qwen or Kimi from the sidebar.
Pick a Berges interceptor: Reasoning, WebSearch, Brainstorm, or Empathy, to shape how the answer comes out.
Answer first. No filler. Prose first. Today's date on hand and pasted links read in full.
AI is great at some things. It's terrible at others. We've designed Berges AI to be honest about both.
Nothing is stored until you save a conversation. Saved 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.
Save a conversation and its messages and title are 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 saved conversation for good. No archived copy, no shadow record.
We run only open-weights models. Each one's license is on its model page.
Three tiers. Cancel anytime.
Most AI apps quietly hand your question to a lite model and pad the answer. Berges AI runs a frontier open-weights reasoning model on every turn, and two more layers sit on top: an interceptor you pick (Reasoning, WebSearch, Brainstorm or Empathy) that shapes how the answer comes out, and a set of house rules that keep it direct: answer first, no filler, prose first, today's date on hand, pasted links read in full.
No. A conversation is stored only when you save it, encrypted at rest (AES-256), and it is never used to train any model, ours or anyone else's.
You can still read your conversations. On a paid plan, new messages pause until your monthly limit resets, or you can move to a higher plan. Each plan also has a short-term cap over a rolling window of a few hours, so a heavy burst can pause you briefly even with monthly allowance left; the usage page shows when it resets. The free trial is a one-time allowance that does not reset: once it is used, pick a plan to keep chatting.
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.
Yes. The sidebar lists four open-weights reasoning models: DeepSeek, GLM, Qwen and Kimi. DeepSeek is the quickest; the larger ones go deeper on the hardest questions and cost more units per reply. Your choice is remembered across sessions, and your interceptor still applies.
Yes. Put a URL in your message and our server fetches the page and hands its main text to the model with your question, on any interceptor. A few links per message are fine, up to a size cap, and the page stays available for follow-ups in the same conversation. Pages behind a login or a paywall will not load. It is also the easy way past the message length limit.
Only when the content has that shape. Berges AI writes in prose by default, because formatting is where most AI padding hides. Steps come as a numbered list, code comes in a code block you can copy, and a comparison across the same points can come as a table. Short answers stay as plain sentences, and headings appear only in long answers with distinct sections. If you want a specific format, ask for it.
Plans are measured in units, not messages, and larger models use more units per reply. Each plan has a monthly allowance and a short-term cap over a rolling window of a few hours, so a burst of heavy use can pause you briefly. The usage page shows both as percentages with the time to the next reset.
Yes, with the WebSearch interceptor selected. The model decides per question whether to search or read a page, and every search and fetch shows as a badge on the reply, so you always know when it went to the web. Pick Reasoning, Brainstorm or Empathy for a chat that never leaves the model. Pasting a link works on any interceptor and fetches just that page.
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.