Show HN: Maestro – A Framework to Orchestrate and Ground Competing AI Models
6 by defqon1 | 0 comments on Hacker News.
ive spent the past few months designing a framework for orchestrating multiple large language models in parallel — not to choose the “best,” but to let them argue, mix their outputs, and preserve dissent structurally. It’s called Maestro heres the whitepaper https://ift.tt/XuFsdlH (Narrative version here: https://ift.tt/eC9LBx6... ) Core ideas: Prompts are dispatched to multiple LLMs (e.g., GPT-4, Claude, open-source models) The system compares their outputs and synthesizes them It never resolves into a single voice — it ends with a 66% rule: 2 votes for a primary output, 1 dissent preserved Human critics and analog verifiers can be triggered for physical-world confirmation (when claims demand grounding) The feedback loop learns not only from right/wrong outputs, but from what kind of disagreements lead to deeper truth Maestro isn’t a product or API — it’s a proposal for an open, civic layer of synthetic intelligence. It’s designed for epistemic integrity and resistance to centralized control. Would love thoughts, critiques, or collaborators.
6 by defqon1 | 0 comments on Hacker News.
ive spent the past few months designing a framework for orchestrating multiple large language models in parallel — not to choose the “best,” but to let them argue, mix their outputs, and preserve dissent structurally. It’s called Maestro heres the whitepaper https://ift.tt/XuFsdlH (Narrative version here: https://ift.tt/eC9LBx6... ) Core ideas: Prompts are dispatched to multiple LLMs (e.g., GPT-4, Claude, open-source models) The system compares their outputs and synthesizes them It never resolves into a single voice — it ends with a 66% rule: 2 votes for a primary output, 1 dissent preserved Human critics and analog verifiers can be triggered for physical-world confirmation (when claims demand grounding) The feedback loop learns not only from right/wrong outputs, but from what kind of disagreements lead to deeper truth Maestro isn’t a product or API — it’s a proposal for an open, civic layer of synthetic intelligence. It’s designed for epistemic integrity and resistance to centralized control. Would love thoughts, critiques, or collaborators.
Why the Original Macintosh Had a Screen Resolution of 512×324
5 by ingve | 0 comments on Hacker News.
5 by ingve | 0 comments on Hacker News.
In Vietnam, an unlikely outpost for Chicano culture
5 by donnachangstein | 1 comments on Hacker News.
5 by donnachangstein | 1 comments on Hacker News.
Show HN: My LLM CLI tool can run tools now, from Python code or plugins
16 by simonw | 3 comments on Hacker News.
16 by simonw | 3 comments on Hacker News.
Ask HN: Decided I no longer want to be a SWE – what next?
22 by leeroihe | 11 comments on Hacker News.
I recently spent the past six months working on a startup. We had a fair bit of momentum coming out of a well known accelerator and an idea with traction, but unfortunately the money just didn't quite show up for the seed. At 30, doing this without pay (and expenses covered) seemed like an ok idea, at least for a few months. But at this point I'm kind of done. Co-founder didn't understand why I wasn't interested working without salary anymore... there were other signs the relationship had broken down etc. Planning on letting him know I'm out near the end of this week. I started interviewing when these feelings started to get to me and... the VC from the accelerator ratted to my co-founder that they'd "heard from recruiters". This was effectively the most unprofessional breach of privacy I've ever experienced and as a result I think I'm done working in software (don't even ask me my opinion of SF). I've been doing this six years, clearly I'm not good enough (tech screens these days are ridiculous) and even as a founder of multiple previous companies (with one exit) and lots of SWE experience I'm no longer attractive for roles that pay well. I've come to realize I don't really even enjoy programming or prepping for interviews - it all feels grating and makes me feel like an idiot. That said, I have no idea what to do next and feel inexplicably lost. My age doesn't help this, but I'm fully drawing a blank. I don't really have money to go to grad school and it appears that dev roles are just getting more competitive. Maybe I was an ok engineer for a while, but I just feel lost and scared. At 30 I don't care about clout anymore, most of my friends make way more money than me or have families. Being an adult here seems like acknowledging doing startups is maybe the dumbest thing I could've done with my life. This probably sounds like a lot, but it's the first time I've run up against this many things going wrong in my life at once. Anyone else pivot away from tech and still make half-decent income?
22 by leeroihe | 11 comments on Hacker News.
I recently spent the past six months working on a startup. We had a fair bit of momentum coming out of a well known accelerator and an idea with traction, but unfortunately the money just didn't quite show up for the seed. At 30, doing this without pay (and expenses covered) seemed like an ok idea, at least for a few months. But at this point I'm kind of done. Co-founder didn't understand why I wasn't interested working without salary anymore... there were other signs the relationship had broken down etc. Planning on letting him know I'm out near the end of this week. I started interviewing when these feelings started to get to me and... the VC from the accelerator ratted to my co-founder that they'd "heard from recruiters". This was effectively the most unprofessional breach of privacy I've ever experienced and as a result I think I'm done working in software (don't even ask me my opinion of SF). I've been doing this six years, clearly I'm not good enough (tech screens these days are ridiculous) and even as a founder of multiple previous companies (with one exit) and lots of SWE experience I'm no longer attractive for roles that pay well. I've come to realize I don't really even enjoy programming or prepping for interviews - it all feels grating and makes me feel like an idiot. That said, I have no idea what to do next and feel inexplicably lost. My age doesn't help this, but I'm fully drawing a blank. I don't really have money to go to grad school and it appears that dev roles are just getting more competitive. Maybe I was an ok engineer for a while, but I just feel lost and scared. At 30 I don't care about clout anymore, most of my friends make way more money than me or have families. Being an adult here seems like acknowledging doing startups is maybe the dumbest thing I could've done with my life. This probably sounds like a lot, but it's the first time I've run up against this many things going wrong in my life at once. Anyone else pivot away from tech and still make half-decent income?
OpenTPU: Open-Source Reimplementation of Google Tensor Processing Unit (TPU)
9 by walterbell | 1 comments on Hacker News.
9 by walterbell | 1 comments on Hacker News.
Starship Flight 9 launches successfully, booster explodes on impact [video]
28 by onzeinternets | 12 comments on Hacker News.
28 by onzeinternets | 12 comments on Hacker News.
A UEFI app that sends LLDP-MED pkt at boot to negotiate PoE+ power before the OS
27 by pietrushnic | 0 comments on Hacker News.
27 by pietrushnic | 0 comments on Hacker News.
Look Ma, No Bubbles Designing a Low-Latency Megakernel for Llama-1B
29 by ljosifov | 3 comments on Hacker News.
29 by ljosifov | 3 comments on Hacker News.
Using Postgres pg_test_fsync tool for testing low latency writes
9 by mfiguiere | 0 comments on Hacker News.
9 by mfiguiere | 0 comments on Hacker News.
Show HN: AutoThink – Boosts local LLM performance by 43% with adaptive reasoning
19 by codelion | 2 comments on Hacker News.
I built AutoThink, a technique that makes local LLMs reason more efficiently by adaptively allocating computational resources based on query complexity. The core idea: instead of giving every query the same "thinking time," classify queries as HIGH or LOW complexity and allocate thinking tokens accordingly. Complex reasoning gets 70-90% of tokens, simple queries get 20-40%. I also implemented steering vectors derived from Pivotal Token Search (originally from Microsoft's Phi-4 paper) that guide the model's reasoning patterns during generation. These vectors encourage behaviors like numerical accuracy, self-correction, and thorough exploration. Results on DeepSeek-R1-Distill-Qwen-1.5B: - GPQA-Diamond: 31.06% vs 21.72% baseline (+43% relative improvement)- MMLU-Pro: 26.38% vs 25.58% baseline- Uses fewer tokens than baseline approaches Works with any local reasoning model - DeepSeek, Qwen, custom fine-tuned models. No API dependencies. The technique builds on two things I developed: an adaptive classification framework that can learn new complexity categories without retraining, and an open source implementation of Pivotal Token Search. Technical paper: https://ift.tt/WqaK0hF Code and examples: https://ift.tt/PUboNrj... PTS implementation: https://ift.tt/SnpeTvX I'm curious about your thoughts on adaptive resource allocation for AI reasoning. Have you tried similar approaches with your local models?
19 by codelion | 2 comments on Hacker News.
I built AutoThink, a technique that makes local LLMs reason more efficiently by adaptively allocating computational resources based on query complexity. The core idea: instead of giving every query the same "thinking time," classify queries as HIGH or LOW complexity and allocate thinking tokens accordingly. Complex reasoning gets 70-90% of tokens, simple queries get 20-40%. I also implemented steering vectors derived from Pivotal Token Search (originally from Microsoft's Phi-4 paper) that guide the model's reasoning patterns during generation. These vectors encourage behaviors like numerical accuracy, self-correction, and thorough exploration. Results on DeepSeek-R1-Distill-Qwen-1.5B: - GPQA-Diamond: 31.06% vs 21.72% baseline (+43% relative improvement)- MMLU-Pro: 26.38% vs 25.58% baseline- Uses fewer tokens than baseline approaches Works with any local reasoning model - DeepSeek, Qwen, custom fine-tuned models. No API dependencies. The technique builds on two things I developed: an adaptive classification framework that can learn new complexity categories without retraining, and an open source implementation of Pivotal Token Search. Technical paper: https://ift.tt/WqaK0hF Code and examples: https://ift.tt/PUboNrj... PTS implementation: https://ift.tt/SnpeTvX I'm curious about your thoughts on adaptive resource allocation for AI reasoning. Have you tried similar approaches with your local models?
Ask HN: Is anyone using AI conversation partners?
6 by rickcarlino | 1 comments on Hacker News.
I'm obsessed applying LLMs in language learning software. One thing I am not-so-obsessed with is a wave of conversational chat apps that many startups have begun offering. Having tried them myself, I find them to be quite bland ("Tell me about your day!" ) and often use a speech style that uses direct translation of English phrases into the target language. I see plenty of potential for LLMs in this space, but the conversation bhat bots I have seen so far are too open ended and seem half baked. For users: Is anyone finding these tools helpful? For the people building them: Are people actually returning to the product?
6 by rickcarlino | 1 comments on Hacker News.
I'm obsessed applying LLMs in language learning software. One thing I am not-so-obsessed with is a wave of conversational chat apps that many startups have begun offering. Having tried them myself, I find them to be quite bland ("Tell me about your day!" ) and often use a speech style that uses direct translation of English phrases into the target language. I see plenty of potential for LLMs in this space, but the conversation bhat bots I have seen so far are too open ended and seem half baked. For users: Is anyone finding these tools helpful? For the people building them: Are people actually returning to the product?
Show HN: Connecting People Through AI-Powered Video Sentiment Matching
5 by armini | 0 comments on Hacker News.
Hi HN, I’d like to share www.kuky.com, a peer support network that connects people through short, self-recorded videos and matches them using sentiment analysis powered by large language models (LLMs). We’re building Kuky to help users find others who genuinely understand their emotional journey—not through swiping or likes, but through shared human stories. In this short Loom demo (link above), I walk through how: Users create a profile by uploading 3 videos: an intro, their mental health journey, and their likes/dislikes LLMs analyze each video for emotional tone, key themes, and psychological markers Based on this, Kuky intelligently connects users with similar experiences and emotional alignment We're passionate about creating a safe, empathetic space for authentic conversation—especially for people dealing with mental health challenges. For more background, here’s a feature on Kuky in Women Love Tech: https://ift.tt/EZoSD3v... Would love your thoughts on the concept, the matching algorithm, and how you’d imagine using something like this. Thanks,Armin
5 by armini | 0 comments on Hacker News.
Hi HN, I’d like to share www.kuky.com, a peer support network that connects people through short, self-recorded videos and matches them using sentiment analysis powered by large language models (LLMs). We’re building Kuky to help users find others who genuinely understand their emotional journey—not through swiping or likes, but through shared human stories. In this short Loom demo (link above), I walk through how: Users create a profile by uploading 3 videos: an intro, their mental health journey, and their likes/dislikes LLMs analyze each video for emotional tone, key themes, and psychological markers Based on this, Kuky intelligently connects users with similar experiences and emotional alignment We're passionate about creating a safe, empathetic space for authentic conversation—especially for people dealing with mental health challenges. For more background, here’s a feature on Kuky in Women Love Tech: https://ift.tt/EZoSD3v... Would love your thoughts on the concept, the matching algorithm, and how you’d imagine using something like this. Thanks,Armin
Global high-performance proof-of-stake blockchain with erasure coding
4 by lawrenceyan | 2 comments on Hacker News.
4 by lawrenceyan | 2 comments on Hacker News.
Every wondered how Facebook spoofs Gmail message list snippet text?
19 by chrisjj | 10 comments on Hacker News.
E.g. Gmail inbox shows a message contains "XXX tagged you on Facebook. Take a look about what she said on you." But when you open the message, there's no "Take a look about what she said on you." Answer. The text is present but hidden: Take a look at what she said about you. And unsurprisingly whenever I do click through, I find she hasn't said anything about me.
19 by chrisjj | 10 comments on Hacker News.
E.g. Gmail inbox shows a message contains "XXX tagged you on Facebook. Take a look about what she said on you." But when you open the message, there's no "Take a look about what she said on you." Answer. The text is present but hidden: Take a look at what she said about you. And unsurprisingly whenever I do click through, I find she hasn't said anything about me.
An Extreme Cousin for Pluto? Possible Dwarf Planet at Solar System Edge
5 by raattgift | 0 comments on Hacker News.
5 by raattgift | 0 comments on Hacker News.