Sup AI
Hi HN. I'm Ken, a 20-year-old Stanford CS student. I built Sup AI. I started working on this because no single AI model is right all the time, but their errors don’t strongly correlate. In other words, models often make unique mistakes relative to other models. So I run multiple models in parallel and synthesize the outputs by weighting segments based on confidence. Low entropy in the output token probability distributions correlates with accuracy. High entropy is often where hallucinations begin. My dad Scott (AI Research Scientist at TRI) is my research partner on this. He sends me papers…
Sup AI launched on April 7, 2026 with 103 votes, #396 of 21,248 launches that month and more than 95% of that year's launches. The site was not reachable when checked in September 2026.
In plain words
Sup AI combines multiple AI models running in parallel and weights their outputs based on confidence levels in their predictions. The system is designed for users who need more reliable answers by leveraging the fact that different models tend to make different errors. It identifies high-confidence segments by analyzing entropy in token probability distributions, treating high entropy as a potential indicator of hallucinations. Built by a Stanford computer science student in collaboration with an AI researcher, Sup AI achieved 52.15% accuracy on Humanity's Last Exam benchmark.
written from the facts on this page · September 2026
From the sources
Every LLM hallucinates. They just don't hallucinate the same things. Sup AI runs multiple LLMs (out of 339) in parallel, then synthesizes answers by measuring confidence on every segment. High entropy = likely hallucination, downweighted. Low entropy = likely accurate, amplified. Result: 52.15% on Humanity's Last Exam, 7.41 points ahead of any individual model. $10 starter credit. Card verified. No auto-charge.
In the maker’s words, at launch
Hi HN. I'm Ken, a 20-year-old Stanford CS student. I built Sup AI. I started working on this because no single AI model is right all the time, but their errors don’t strongly correlate. In other words, models often make unique mistakes relative to other models. So I run multiple models in parallel and synthesize the…
Does a similar job
all alternatives →
Open-source model and scorecard for measuring hallucinations in LLMs2023 · vectara.com · ▲65Hi 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…
- 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:…
Entropy-Guided Loop – How to make small models reason2025 · github.com · ▲33TLDR: A small, vendor-agnostic inference loop that turns token logprobs/perplexity/entropy into an extra pass and reasoning for LLMs. - Captures logprobs/top-k during generation, computes perplexity and token-level entropy. - Triggers at most one refine when simple thresholds fire; passes a compact “uncertainty report” (uncertain tokens + top-k alts + local context) back to the model. - In our tests on technical Q&A / math / code, a small model recovered much of “reasoning” quality at ~⅓ the cost while refining ~⅓ of outputs. I kept seeing “reasoning” models behave…
Hallucination-Proof AI Course Creator2025 · minicoursegenerator.com · ▲63Turn PDFs into courses with AI without irrelevant additions
I ran a language model on a PS2Mar 2026 · github.com · ▲46The Emotion Engine has 32 MB of RAM total, so the trick is streaming weights from CD-ROM one matrix at a time during the forward pass — only activations, KV cache and embeddings live in RAM. This means models bigger than the RAM can still run, they just read more from disc. Had to build a custom quantized format (PSNT), hack endianness, write a tokenizer pipeline, and most of the PS2 SDK from scratch (releasing that separately). The model itself is also custom — a 10M param Llama-style architecture I trained specifically for this. And it works. On real hardware.
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Product Hunt launch ↗ · launch text quoted in part
Launched alongside, April 2026
the whole month →
- AG
Thought the resources for GPU arch were lacking, so here we are
Life & fun · Apr 2026 · jaso1024.com
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
AI · Apr 2026 · github.com
I made a laptop stand out of solid concrete, in the style of brutalist architecture, with themes of urbex and urban decay
Life & fun · Apr 2026 · sam-burns.com
With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.
AI · Apr 2026 · text.blogosphere.app