news.ycombinator.com
Show HN: A Multi-agent system where LLMs challenge each other's answershttps://news.ycombinator.com/item?id=46435835Hey HN,I've been experimenting with forcing multiple LLMs to critique each other before producing a final answer.In practice, I kept working around single-model limitations by opening multiple tabs, pasting the same question into different models, comparing responses, and then manually challenging each model with the others' arguments. (Maybe some of you can relate.) It worked sometimes, but it was cumbersome, slow, and hard to do systematically and efficiently.Based on my own experiments, a few things seem to drive why different models arrive at different responses: they have different guardrails, different tendencies encoded in their weights, and different training data. And the biggest kicker of all: they still hallucinate. The question I wanted to test was whether making those differences explicit, rather than relying on one model to self-correct could reduce blind spots and improve the overall quality of the answer.So I built Consilium9.The problem: When a single LLM answers a conDec 30, 2025 5:41 PM
spacenews.com
The space stories that will shape 2026https://spacenews.com/the-space-stories-that-will-shape-2026/In this episode of Space Minds, host Mike Gruss is joined by SpaceNews journalists Jason Rainbow, Sandra Erwin, Jeff Foust and Debra Werner for a wide-ranging conversation on the space stories that will define the year ahead. The post The space stories that will shape 2026 appeared first on SpaceNews.Dec 30, 2025 2:55 PM
spacedaily.com
Space-traveled mouse gives birth as China names pioneering "flying mice" crewhttps://www.spacedaily.com/reports/Space_traveled_mouse_gives_birth_as_China_names_pioneering_flying_mice_crew_999.htmlTokyo, Japan (SPX) Dec 30, 2025 Of the four mice that recently flew aboard China's space station, one female has now given birth to healthy offspring on Earth, in a mission that also saw the public help name the pioneering "flying mice" crew. The Technology and Engineering Center for Space Utilization (CSU) under the Chinese Academy of Sciences (CAS) said the experiment marks China's first full-cycle mammalian space study, froDec 30, 2025 7:17 AM
beautyarena.vercel.app
Show HN: Beauty Arena – An Elo-based experiment to measure aestheticshttps://beautyarena.vercel.appHi HN,I built Beauty Arena to solve a data problem I've always found annoying: absolute rating scales (1-10) are terrible for subjective data. They suffer from massive inflation and inconsistent user baselines (one person's 7 is another person's 5).I wanted to test if pairwise comparison (1v1) could produce a cleaner, strictly relative dataset.Instead of asking "How beautiful is this person?", the system asks a simple question: "Who do you choose?". It uses a ranking system inspired by competitive games (Elo/Glicko) under the hood. As users vote, a global ranking emerges based on win/loss ratios against others rather than accumulated points.I'm curious about the "wisdom of the crowd" limits here. Does a pairwise sort actually converge on a clear consensus, or does it cycle indefinitely due to intransitive preferences (A > B, B > C, but C > A)?I'd love feedback on the ranking methodology and the overall UI.Dec 30, 2025 12:56 AM
news.google.com
PlayStation 5 review: Is the bestselling console worth your money?https://news.google.com/rss/articles/CBMivgFBVV95cUxQdFVXV1JNalNxXzRvZUk3amkwUEo2SG9ZODQtMV9zWkpEWTNRYlpYRU5MTXlVY2VQOGgzWFJYMk5RekNkbm1wdFB0bm5kYXNJSmdYM3YtLTJUTFp4Xy1PQWlSNFpRWTEyZlpVUDdxd19QbVRJMFF0c3B3bTBCSUpzSFpDeFBFYzJvYlJHdWNZdjBFQVBWRlFOUFFJa0k1V1lWX3I4cFpRWHBzNEhKYi1XcDJfeXJkNERodm5wdklR?oc=5PlayStation 5 review: Is the bestselling console worth your money? The IndependentDec 29, 2025 8:00 AM
news.google.com
What we know about the US air strikes in Nigeriahttps://news.google.com/rss/articles/CBMiV0FVX3lxTFBxaENSX2YwMkdyYWkzemhtY2Q2eVdPejN3RUNQTGhSSlhoTzk1UEpJQXhRXzRBUVZ5cEJreDlFU0k0SUtSeXdoT1JqUF8wS2g3Z3FHblh1dw?oc=5What we know about the US air strikes in Nigeria Bangladesh Sangbad Sangstha (BSS)Dec 27, 2025 8:00 AM
nasa.gov
Studying Physics in Microgravityhttps://www.nasa.gov/image-article/studying-physics-in-microgravity/In this Oct. 20, 2025, photo, tiny ball bearings surround a larger central bearing during the Fluid Particles experiment, conducted inside the Microgravity Science Glovebox (MSG) aboard the International Space Station’s Destiny laboratory module. A bulk container installed in the MSG, filled with viscous fluid and embedded particles, is subjected to oscillating frequencies to observe […]Dec 26, 2025 4:27 PM
bing.com
PubMed has competition from Germany. That’s a very good thinghttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85dbc773874382b709cf8414e74939&url=https%3a%2f%2fwww.statnews.com%2f2025%2f12%2f26%2fpubmed-zb-med-scientific-repository-livivo%2f&c=8551604424114525670&mkt=en-usRubinelli is professor of health communication and vice-dean of health sciences at the faculty of health sciences and medicine of the University of Lucerne. Ivic is associate dean of research and ...Dec 26, 2025 5:48 AM
bing.com
PubMed has competition from Germany. That’s a very good thinghttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85cd0f373e4fe496d2a7c1628d0ece&url=https%3a%2f%2fwww.statnews.com%2f2025%2f12%2f26%2fpubmed-zb-med-scientific-repository-livivo%2f&c=8551604424114525670&mkt=en-usRubinelli is professor of health communication and vice-dean of health sciences at the faculty of health sciences and medicine of the University of Lucerne. Ivic is associate dean of research and ...Dec 26, 2025 5:48 AM
bing.com
PubMed has competition from Germany. That’s a very good thinghttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85d5ba008b422fa1891d6f308f8b98&url=https%3a%2f%2fwww.statnews.com%2f2025%2f12%2f26%2fpubmed-zb-med-scientific-repository-livivo%2f&c=8551604424114525670&mkt=en-usRubinelli is professor of health communication and vice-dean of health sciences at the faculty of health sciences and medicine of the University of Lucerne. Ivic is associate dean of research and ...Dec 26, 2025 5:48 AM
bing.com
PubMed has competition from Germany. That’s a very good thinghttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85d38f480940159618ce4f5a950386&url=https%3a%2f%2fwww.statnews.com%2f2025%2f12%2f26%2fpubmed-zb-med-scientific-repository-livivo%2f&c=8551604424114525670&mkt=en-usRubinelli is professor of health communication and vice-dean of health sciences at the faculty of health sciences and medicine of the University of Lucerne. Ivic is associate dean of research and ...Dec 26, 2025 5:48 AM
bing.com
PubMed has competition from Germany. That’s a very good thinghttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85d9ab50584c4a882b30920461d578&url=https%3a%2f%2fwww.statnews.com%2f2025%2f12%2f26%2fpubmed-zb-med-scientific-repository-livivo%2f&c=8551604424114525670&mkt=en-usRubinelli is professor of health communication and vice-dean of health sciences at the faculty of health sciences and medicine of the University of Lucerne. Ivic is associate dean of research and ...Dec 26, 2025 5:48 AM
bing.com
PubMed has competition from Germany. That’s a very good thinghttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85e224f14a4b7ea20d9b65fc0178a9&url=https%3a%2f%2fwww.statnews.com%2f2025%2f12%2f26%2fpubmed-zb-med-scientific-repository-livivo%2f&c=8551604424114525670&mkt=en-usRubinelli is professor of health communication and vice-dean of health sciences at the faculty of health sciences and medicine of the University of Lucerne. Ivic is associate dean of research and ...Dec 26, 2025 5:48 AM
bing.com
PubMed has competition from Germany. That’s a very good thinghttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85dde40370418e86f3d16783334c85&url=https%3a%2f%2fwww.statnews.com%2f2025%2f12%2f26%2fpubmed-zb-med-scientific-repository-livivo%2f&c=8551604424114525670&mkt=en-usRubinelli is professor of health communication and vice-dean of health sciences at the faculty of health sciences and medicine of the University of Lucerne. Ivic is associate dean of research and ...Dec 26, 2025 5:48 AM
bing.com
PubMed has competition from Germany. That’s a very good thinghttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85cf2073f744d8adbeb2b16257d85d&url=https%3a%2f%2fwww.statnews.com%2f2025%2f12%2f26%2fpubmed-zb-med-scientific-repository-livivo%2f&c=8551604424114525670&mkt=en-usRubinelli is professor of health communication and vice-dean of health sciences at the faculty of health sciences and medicine of the University of Lucerne. Ivic is associate dean of research and ...Dec 26, 2025 5:48 AM
bing.com
PubMed has competition from Germany. That’s a very good thinghttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85e663e77c4411b75edb4c2240e026&url=https%3a%2f%2fwww.statnews.com%2f2025%2f12%2f26%2fpubmed-zb-med-scientific-repository-livivo%2f&c=8551604424114525670&mkt=en-usRubinelli is professor of health communication and vice-dean of health sciences at the faculty of health sciences and medicine of the University of Lucerne. Ivic is associate dean of research and ...Dec 26, 2025 5:48 AM
bing.com
PubMed has competition from Germany. That’s a very good thinghttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85d14ca214442ea5c02f0a958664c7&url=https%3a%2f%2fwww.statnews.com%2f2025%2f12%2f26%2fpubmed-zb-med-scientific-repository-livivo%2f&c=8551604424114525670&mkt=en-usRubinelli is professor of health communication and vice-dean of health sciences at the faculty of health sciences and medicine of the University of Lucerne. Ivic is associate dean of research and ...Dec 26, 2025 5:48 AM
bing.com
PubMed has competition from Germany. That’s a very good thinghttp://www.bing.com/news/apiclick.aspx&aid=&tid=6a85e43e215f4d74b88718a0c51dea92&url=https%3a%2f%2fwww.statnews.com%2f2025%2f12%2f26%2fpubmed-zb-med-scientific-repository-livivo%2f&c=8551604424114525670&mkt=en-usRubinelli is professor of health communication and vice-dean of health sciences at the faculty of health sciences and medicine of the University of Lucerne. Ivic is associate dean of research and ...Dec 26, 2025 5:48 AM
news.ycombinator.com
80.1 % on LoCoMo Long-Term Memory Benchmark with a pure open-source RAG pipelinehttps://news.ycombinator.com/item?id=46369736I just pushed the current SOTA on the LoCoMo long-term memory benchmark for agents: 80.1 % accuracy using only: -BGE-large-en-v1.5 (1024d) + FAISS-Custom “MCA” gravitational ranking (keyword coverage + importance + frequency)-BM25 sparse retrieval-Direct Cross-Encoder reranking (bge-reranker-v2-m3) on the full union (~120-150 docs)-Gpt-4o-mini only for final answer generation and judging (everything else is open weights or classic)Repo: https://github.com/vac-architector/VAC-Memory-System Key tricks that finally broke 80% :-MCA-first filter (coverage ≥ 0.1 → top-30) — catches exact-keyword questions early-Feeding the entire union straight into Cross-Encoder (112–135 documents) instead of pre-filtering-Proper query instruction for BGE-large (the classic “Represent this sentence for searching relevant passages”)The whole pipeline runs in < 3s per query on a single RTX 4090. LoCoMo is currently the hardest public long-term memory benchmark (5.880 real human–agent conversations, multi-hop,Dec 23, 2025 9:34 PM
science.nasa.gov
Keeping Up with PACE: Summary of the 2025 PAC3 Meetinghttps://science.nasa.gov/science-research/earth-science/keeping-up-with-pace-summary-of-the-2025-pac3-meeting/Introduction Launched in Feb. 2024, NASA’s Plankton, Aerosol, Cloud, ocean Ecosystem (PACE) mission is a cornerstone of Earth system science designed to deepen our understanding of how these environmental and biological components come together to influence our climate, carbon cycle, and ecosystems. PACE has funded three supporting components: the PACE Postlaunch Airborne eXperiment (PACE–PAX), the […]Dec 22, 2025 7:57 PM
