Buy A Modem
"Subligence" – proposed coinage for LLM "intelligence"
Call me a snowflake, but I propose that those of us who don't believe that AI is actually intelligence look for a term to refer to its "thinking" that isn't "intelligence", because this helps our weak minds keep things straight.subligence /sʌbˈlɪdʒəns/ n.A lesser or rudimentary form of intelligence; the capacity to respond, select, or adapt without full understanding.
The semblance of mind in animals, machines, systems, or inanimate things.
Discernment ben
Instant YouTube channel analysis using public metrics
Hey HN!I’ve been spending a lot of time around creator communities recently, and one thing I kept noticing was how difficult it is for smaller YouTubers to understand their channel growth clearly. Most analytics tools are either overloaded with dashboards, require full account access, or are built mainly for large creators and agencies.So I built AAFY — a simple creator growth companion focused on clarity, privacy, and quick insights.The idea is straightforward:
you enter any public YouTube hand
Show HN: Interactive first-principles climate physics simulation with explainer
A 3D visualizer of earth's climate in the browser. Introduces physics step by step so you can watch each process unfold as a piece of the overall climate.
I built this over 6 months, almost entirely with AI, mostly Opus 4.6 in Claude Code. SF weather made no sense to me (Barely any seasons? September is the warmest month?) and I wanted to understand it better myself. This is a polished version of the app I'd want for myself, adding physics layer by layer to isolate the impact of each p
ASK HN: AI was always a probability problem?
AI was always a probability problem.. If we look at the emergence of sequence models (or statistical learning in broader sense), they predict the next sequence based on the accumulation of knowledge that humankind has acquired over the years.. The scientists who were tackling this problem(creating general AI) before thought of approaching it by creating different simulations for all kinds of problems, which would have led to infinity anyway, that is why it never worked. The solution was simple.
Show HN: ThinkLLM, A knowledge graph of AI models (HTTPS://thinkllm.dev)
As an Enterprise Architect I work with Capabilities, Use Cases and Value Maps amongst other things. Hugging Face is a great resource for tracking down AI models but is mostly technical and quite detailed. I built ThinkLLM because I thought that as more and more people are going to be using LLMs it would be easier to find AI models by capabilities and use cases than simply browsing long lists of models.The website has nothing extraordinary or special. Is just a different view on existing data. It
Show HN: I built a RAG and knowledge graph agent that runs locally
Claw-Coder is an AI agent that runs locally on your laptop and has access to powerful tools instead of configuring claude or codex to use a local model just use claw-coder.
Why was claw-coder created? Answer: To solve the problem of privacy and security. When you use an agent that is configured with a cloud model like codex, cursor, Claude etc. You are not just getting the agent but you are giving up your codebase to train an llm which is a bit concerning and this reduces trust in the technology
Show HN: I built a powerful RAG and knowledge graph agent that runs locally
Claw-Coder is an AI agent that runs locally on your laptop and has access to powerful tools instead of configuring claude or codex to use a local model just use claw-coder.Why was claw-coder created?
Answer: To solve the problem of privacy and security. When you use an agent that is configured with a cloud model like codex, cursor, Claude etc. You are not just getting the agent but you are giving up your codebase to train an llm which is a bit concerning and this reduces trust in the technology
OneLayer Bridge Live Demo
The OneLayer Bridge live demo illustrates the transition from the garbled view of a traditional cellular core--filled with 15-digit IMSI and IMEI identifiers--to a device-aware management platform. Without OneLayer, administrators are forced to manage critical infrastructure through abstract numbers, making the activation or deactivation of SIM cards a high-risk manual task. OneLayer replaces this with a zoomed-out, user-friendly interface that identifies devices by their actual function and mod
Ubiquiti Reliable Networking at Scale
Thomas Hildebrand detailed Ubiquiti's hardware strategies and product updates designed to support deployments ranging from large multi-tenant installations to massive single-site environments. The presentation began by highlighting a new, small-scale access point utilizing a unique RF profile, featuring a built-in 90-degree directional antenna with a 10 dB gain on the 5 GHz band, optimized to provide long-distance wireless uplinks in low-density deployments like parks. Hildebrand then addressed
Have you tried turning it off and on again? Telstra’s AI already did
Telstra has built an AI-powered system that, over the past few years, has been turning customers’ modems off and on again – saving a million help desk calls.
Ask HN: Best Embedding Models?
Hey HN, which embedding models are people using? There has been so much development around foundational LLMs, but haven't seen much news about embedding models.
Show HN: Neural window manager, neural network moving windows from mouse actions
I'd been mulling over this crazy idea for a while. Can programs be generated? Inspired by recent advances in world models, I wondered if we could do away with source code and generate pixels directly and interactively.As an experiment to answer this, I set out to create a neural window manager, training a neural network to predict what the screen would look like next.Basically, the idea was to generate the next frame based on the last two frames and the mouse position. That's it: movin
Arena AI Model ELO History
Hi HN,I built a live tracker to visualize the lifecycle and performance changes of flagship AI models.We've all experienced the phenomenon where a flagship model feels amazing at launch, but weeks later, it suddenly feels a bit off. I wanted to see if this was just a feeling or a measurable reality, so I built a dashboard to track historical ELO ratings from Arena AI.Instead of a massive spaghetti chart of every single model variant, the logic plots exactly ONE continuous curve per major AI
Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices.We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly
Show HN: I built an open source dication tool based on benchmarks
I've built an AI dictation tool (like many others), but this time I have taken the time to benchmark all of the 34 models that we provide, so users can actually make a qualified choice on what model should be the daily driver.<p>The best is that it's open source, so if you think we can improve something, please come and help out.
Show HN: A multi-model interface where LLMs discuss & argue with each other
Hey HN, I am Robin from Rauno (link: https://rauno.ai). I built this tool because I’m tired of AI hallucinations.I got sick of manually copy-pasting every prompt into 3 different windows just to verify the truth. I realized the only way to get real accuracy was to let the models debate & fact-check each other in real-time, in one screen. I couldn't find any platform online that does this and actually works smooth and user-friendly, so I ended up throwing this together just to
Show HN: Statewright – Visual state machines that make AI agents reliable
Agentic problem solving in its current state is very brittle. I fell in love with it, but it creates as many problems as it solves.I'm Ben Cochran, I spent 20+ years in the trenches with full-stack Engineering, DevOps, high performance computing & ML with stints at NVIDIA, AMD and various other organizations most recently as a Distinguished Engineer.For agents to work reliably you either need massive parameter counts or massive context windows to keep the solution spaces workable. Most
Show HN: I made an iOS app to gauge AI over-reliance and AI psychosis
Atrophy is an iOS self-report quiz aimed at software engineers who use LLMs heavily enough at work to wonder if they're trending toward AI over-reliance or some form of AI psychosis.I built it because I noticed a pattern: formerly AI-skeptical coworkers now open every standup or design discussion with "I asked Claude..." or "Claude told me..." for technical problems and design decisions. I've felt the same pull myself to delegate every task or problem to AI. It'
Show HN: How we made MCP development feel good
Hey HN, I am Pietro from Manufact (https://manufact.com), we build open source dev tools and infrastructure for MCP.You might know us for mcp-use (https://github.com/mcp-use/mcp-use) our open source full stack SDK to build MCP servers and clients.At Manufact we gave ourselves the mission, and delight, to write as many MCP servers as we could, through this journey we could hone our SDK to offer the best possible developer/agent experience.Testing/developing
Qualcomm Stock To $340?
Qualcomm (QCOM) has largely been left behind in the AI-driven semiconductor rally. The bear case is well understood. Apple ...