Pontus the Zero Trust AI Layer
Hi HN, We’re @sumants and @rmehtany, working on Pontus. Pontus makes it easy to use AI with privacy embedded. We were concerned about the volume of personal data that goes to large LLM models without protection. We tried find an easy solution where didn’t change the simple apis given by LLM providers. However, most required you to invest significant engineering effort. We wanted privacy and LLMs to be easy, so we built Pontus. Through a declarative YAML, we orchestrate a microservice with the most common element of the LLM stack. - Anonymize Prompts before it hits LLMs, yet keeps context on…
What it does
In the maker’s words, at launch
Hi HN, We’re @sumants and @rmehtany, working on Pontus. Pontus makes it easy to use AI with privacy embedded. We were concerned about the volume of personal data that goes to large LLM models without protection. We tried find an easy solution where didn’t change the simple apis given by LLM providers. However, most required you to invest significant engineering effort. We wanted privacy and LLMs to be easy, so we built Pontus. Through a declarative YAML, we orchestrate a microservice with the most common element of the LLM stack. - Anonymize Prompts before it hits LLMs, yet keeps context on your servers - Secure RAG that embeds documents safely - Semantic Cache that doesn’t store PII at Rest We did this not only because it is the right thing to do, but the regulation landscape makes it critical to build with privacy first. Recently, many companies have been fined and forced to delete their AI models [1][2] For us, Privacy is by design, not an afterthought. Please visit us here Our Open Core Repo: https://github.com/PontusAI/Pontus Our Website: https://pontus.so [1] https://www.ftc.gov/news-events/news/press-releases/2023/05/... [2] https://techcrunch.com/2023/05/10/clearview-ai-another-cnil-...
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
