Show HN: I built a "Socratic" AI to stop my daughter from copy-pasting homework https://ift.tt/SOIpJsa

Show HN: I built a "Socratic" AI to stop my daughter from copy-pasting homework Hey HN, I’m a dev and a dad to a 10-year-old. I built this because I caught my daughter using ChatGPT to do her history homework. She wasn't learning; she was just acting as a "middleware" between the AI and the paper. The Backstory: I realized the problem isn't the AI—it's the zero-friction answers. Most "AI for kids" apps are just "parrots"—they mimic intelligence by repeating patterns. What’s Different: Qurio is a "Bicycle" for the mind. It treats the child like a future "Architect" rather than a "Junior Executor." Technically, it wraps an LLM in a strict "Socratic Loop." It detects intent to "cheat," refuses the direct answer, and generates a leading question based on the user's current logic level. It forces "Healthy Friction" back into the learning process. The stack: Next.js 14, Supabase (Auth/DB), Vercel AI SDK. Mods: I've added the backstory and differentiator as requested. Ready for the re-up! Thank you. https://thinkqurio.com/ February 16, 2026 at 12:55PM

Show HN: How I built Timeframe, our family e-paper dashboard https://ift.tt/5rUHdSJ

Show HN: How I built Timeframe, our family e-paper dashboard I'm proud to share the e-paper family dashboard I've been building over the past decade. I think you might find it interesting. It's open source: https://ift.tt/wOhr1zY . https://ift.tt/vuzd23P February 17, 2026 at 11:20PM

Show HN: Windows 98 web desktop with a functional remote browser (no CORS) https://ift.tt/75vgyNz

Show HN: Windows 98 web desktop with a functional remote browser (no CORS) https://ift.tt/AIzWguc February 17, 2026 at 04:24AM

Show HN: Glitchy camera – a circuit-bent camera simulator in the browser https://ift.tt/ZqMYVPB

Show HN: Glitchy camera – a circuit-bent camera simulator in the browser Fun little side project I built after learning about circuit bending in cameras for intentional glitch effect. It is browser based camera toy where you "rewire" CCD pin pairs, turn knobs to get different glitch artefacts in real time to capture as photos. I had fun learning to simulate different pin modes - channel split, hue/phase shifts, horizontal clock delays, colour kill etc. Here are some photos taken: https://ift.tt/6cEVomW I intentionally leaned towards skeuomorphic design for nostalgia. I miss the days where I'd spend hours making a button to look like a physical button. Here I chose to make it look like a "good enough" Teenage Engineering device UI. I tested/used GPT-5.3-Codex to build this from scratch, since there was a lot of hype around it on X. Maybe I wasn’t using it right, but I found it needed a lot of code cleanup at every step and a lot of hand holding along the way. It missed details/nuances and didn't land the skeuomorphic buttons or the interaction polish. It mostly helped with boilerplate where there wasn't much thinking/detailing. It did give a basic starting point for the effect calculations, but didn't really move the needle on the details. Please give it a go and let me know what you think - your photos and video never leave your browser (you can download them if you choose to). Everything is processed locally in your browser (works offline), nothing is uploaded or seen by anyone. https://glitchycam.com February 16, 2026 at 08:57AM

Show HN: Script to check if Notepad++ is backdoored by Lotus Blossom APT https://ift.tt/y6AJMrH

Show HN: Script to check if Notepad++ is backdoored by Lotus Blossom APT https://ift.tt/elLWxcX February 17, 2026 at 01:16AM

Show HN: OpenEntropy – 47 hardware entropy sources from your computer's physics https://ift.tt/pNK8kiM

Show HN: OpenEntropy – 47 hardware entropy sources from your computer's physics I built this to study something most security engineers wave off: whether external factors can nudge hardware entropy sources. Here is why. Princeton’s PEAR lab ran RNG work for about 28 years and shut down in February 2007. People in the lab tried to shift random event generator output, and they reported small deviations after tens of millions of events. https://ift.tt/OtPT1D4 The Global Consciousness Project took a similar idea outside the lab. It has run a distributed network of hardware RNGs since 1998 and looks for correlated deviations around major world events. Most people looking at hardware entropy want true randomness for crypto. I want to treat entropy like a sensor. I want to see what might perturb the underlying noise, not just consume a final stream. So I built OpenEntropy. It samples 47 physical-ish sources on Apple Silicon, like clock jitter, thermal beats, DRAM timing conflicts, cache contention, and speculation timing. Raw mode gives you unprocessed, per-source bytes so you can run your own stats on each channel. The PEAR-style question is: does output shift when “intention” is the experimental condition? With 47 sources, I can run intention vs control sessions and ask if multiple unrelated channels drift the same way at the same time. If thermal and DRAM timing both shift during intention blocks, that’s the kind of pattern I want to measure. https://ift.tt/0wJsQTL February 16, 2026 at 10:52PM

Show HN: JeffTube https://ift.tt/irswZlP

Show HN: JeffTube https://jmail.world/jefftube February 16, 2026 at 01:09AM