Fighting Medical LLM Hallucinations with a Grounded RAG System
Hi HN, We've been frustrated with how confidently LLMs hallucinate—a dangerous flaw in high-stakes domains like health and medicine. The standard "I am not an expert" disclaimer feels insufficient since we all ignore those statements. Our approach is a RAG/agentic system built to solve this. It runs on ~40M+ scientific papers, but goes beyond simple retrieval. A multi-agent workflow decomposes queries, cross-references claims against multiple sources, and synthesizes answers, ensuring every key statement is cited directly from the literature. Beyond the literature, our agent system has…
What it does
In the maker’s words, at launch
Hi HN, We've been frustrated with how confidently LLMs hallucinate—a dangerous flaw in high-stakes domains like health and medicine. The standard "I am not an expert" disclaimer feels insufficient since we all ignore those statements. Our approach is a RAG/agentic system built to solve this. It runs on ~40M+ scientific papers, but goes beyond simple retrieval. A multi-agent workflow decomposes queries, cross-references claims against multiple sources, and synthesizes answers, ensuring every key statement is cited directly from the literature. Beyond the literature, our agent system has tools to access the internet, databases, and social platforms, with dedicated review agents to ensure proper citation and reduce hallucinations. This is just the start. Our long-term goal is building health superintelligence by integrating multiscale data—from the genomic and cellular level all the way up to clinical studies in humans. To achieve this, we're exploring SFT, RL, and self-improvement techniques like GEPA to create models that can evolve their own scientific reasoning and to pioneer new standards for accuracy/hallucination mitigation. We plan to rigorously benchmark our work and share the data publicly. We'd love specific feedback on: Our RAG/agentic architecture—what failure modes are we missing? On building superintelligence—beyond SFT/RL/GEPA, what other techniques should we be exploring for a model to truly understand multiscale biology/health/medicine? Evaluation—what are the best benchmarks for medical/health AI trustworthiness today? The site itself—any thoughts on the UI/UX, quality of the responses, or other features? You can see the current system here: https://www.my-openhealth.com/
Does the same job
all alternatives →- OSOpen-source model and scorecard for measuring hallucinations in LLMs2023 · vectara.com · ▲65
Hi all! This morning, we released a new Apache 2.0 licensed model on HuggingFace for detecting hallucinations in retrieval augmented generation (RAG) systems. What we've found is that even when given a "simple" instruction like "summarize the following news article," every LLM that's available hallucinates to some extent, making up details that never existed in the source article -- and some of them quite a bit. As a RAG provider and proponents of ethical AI, we want to see LLMs get better at this. We've published an open source model, a blog more thoroughly describing our methodology (and…
- TATurn any website into a knowledge base for LLMs2024 · embedding.io · ▲305
I built this tool because I wanted a way to just take a bunch of URLs or domains, and query their content in RAG applications. It takes away the pain of crawling, extracting content, chunking, vectorizing, and updating periodically. I'm curious to see if it can be useful to others. I meant to launch this six months ago but life got in the way...
- FAFactual AI Q&A – Answers based on Huberman Lab transcripts2022 · huberman.rile.yt · ▲120
This is a quick prototype I built for semantic search and factual question answering using embeddings and GPT-3. It tries to solve the LLM hallucination issue by guiding it only to answer questions from the given context instead of making things up. If you ask something not covered in an episode, it should say that it doesn't know rather than providing a plausible, but potentially incorrect response. It uses Whisper to transcribe, text-embedding-ada-002 to embed, Pinecone.io to search, and text-davinci-003 to generate the answer. More examples and explanations here:…
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 · 27d ago · cactuscompute.com
Launched alongside, August 2025
the whole month →
- IS
I built the world's most impractical 1000-pixel display and anyone in the world can draw on it. It draws a single pixel at a time and takes 30-60 minutes to complete a single image. Anyone can participate in the project by voting for the next image to be drawn, and submitting images. https://kilopx.com/
Work · 2025 · benholmen.com
- KT
Kitten TTS is an open-source series of tiny and expressive text-to-speech models for on-device applications. We are excited to launch a preview of our smallest model, which is less than 25 MB. This model has 15M parameters. This release supports English text-to-speech applications in eight voices: four male and four female. The model is quantized to int8 + fp16, and it uses onnx for runtime. The model is designed to run literally anywhere eg. raspberry pi, low-end smartphones, wearables, browsers etc. No GPU required! We're releasing this to give early users a sense of the latency and voices…
Dev tools · 2025 · github.com
- IW
I was wondering how I can arrange objects along a spherical helix path, and read some articles on it. I ended up learning about parametric equations again, and make this visualization to document what I learned: https://visualrambling.space/moving-objects-in-3d/ feel free to visit and let me know what you think!
Life & fun · 2025 · visualrambling.space
- TC
For HTML Day 2025 [1], I made a web service that displays the current sky at your approximate location as a CSS gradient. Colours are simulated on-demand using atmospheric absorption and scattering coefficients. Updates every minute, without the use of client-side JavaScript. Source code and additional information is available on GitHub: https://github.com/dnlzro/horizon [1] https://html.energy/html-day/2025/index.html
Dev tools · 2025 · sky.dlazaro.ca