news.ycombinator.com
Jaw health campaign – looking for fundinghttps://news.ycombinator.com/item?id=46656800I'm working on a project to increase recognition of craniofacial dystrophy and the jaw epidemic.I think this is a major under-addressed health problem and some researchers from Stanford agree: https://news.stanford.edu/stories/2020/07/toll-shrinking-jaws-human-healthAs far as I know, I'm the only person working on setting up a sustained patient-led effort to raise awareness of this issue. Dr Mike Mew and the Jaw Epidemic authors are also active but I think something needs to come directly from the patients.I'm currently living in a caravan and my costs, including server costs, are about £700 a month. I get some UK state benefits of up to £400/month. I've been borrowing from family but this is wearing thin.Wondering if anyone in the hacker community would be interested in funding this effort, or could put me in touch with someone who might be?The project is www.jawhealth.org.Video: https://www.youtube.com/watch?v=FDSqLg_7u2QJan 17, 2026 10:05 AM
rundown.cool
Show HN Rundown transforms docs into executable workflowshttps://rundown.cool/I have been working on this hare-brained scheme to help agents who want to code good and do other things good too.Introducing: Rundown (https://rundown.cool)I think of Rundown runbooks as executable Skills. The Skill provides the detailed context, and the Rundown runbook keeps the agent on track. # Hello ## 1 This is Rundown Rundown transforms markdown into an executable specification. Headings become steps, code-blocks become executable commands. Human-readable. Agent-readable. Machine-executable. ## 2 Guide agents (and humans) through your process Rundown keeps agents on track by injecting precision context at the exact moment it’s needed. ## 3 Make complex workflows deterministic - PASS: CONTINUE - FAIL: GOTO RECOVER Rundown works *with* agents, adding guardrails that enforce transitions and improve accuracy. ## 4 Execute the right commands at the right time - PASS: CONTINUE - FAIL: RETRY GOTO RECOVER Embed commands for automatic execution. Catch failure, retry, and recover gracefulJan 17, 2026 6:26 AM
news.ycombinator.com
"Freedom of Speech" Exists – But "Freedom of Reach" Is a Black Boxhttps://news.ycombinator.com/item?id=46653122I posted a link to a long-form article on X (Twitter). Impressions: single digits. Nothing was deleted. No warning. No ban. It simply didn’t reach anyone.At first glance this is easy to dismiss as “algorithm roulette.” But the same invisibility patterns show up across platforms:- YouTube political content gets quietly demonetized / de-ranked - External links on social feeds often underperform (sometimes dramatically) - LLMs (ChatGPT/Claude/etc.) tend to sanitize or avoid politically sharp topics - Search results for some queries feel oddly thin, stale, or SEO-floodedThis makes me wonder if we’re drifting into a new mode of discourse control: not classic “state censorship,” but incentive-driven soft suppression.Habermas called the democratic discourse space the “public sphere.” A hidden assumption in that model was simple: if you publish, people can actually see it. That assumption may be breaking.A rough model (feel free to tear this apart):1) Visibility layer (feeds / ranking / UI) - Jan 16, 2026 10:33 PM
bouchardindustries.com
Show HN: I made a phone in between a smartphone and dumbphonehttps://bouchardindustries.comHi HN,my name is Eric, I am from Canada. I love technology, but for a long time now, I feel disrespected by technology.Specifically smartphones and social media. Social media is built to keep you glued to your phone. Smartphones also have too many distractions, it's constantly spying on you (getting ads that are way too specific) and they are difficult to repair / they discourage you from doing it yourself (which voids warranties).Social media can be used for great things (posting for your business, researching, learning, spreading a good message or educational content) but most of the time, it's used improperly.My business has been around for a while, mostly making SaaS products, utility apps and mobile games. (I know, games are distracting, but I still believe they are better for you than doom scrolling) But last summer, I sat down and reflected on my core values. One of them was to make a positive impact and I looked at all the problems I saw in the world that I had noted down, thisJan 16, 2026 9:38 PM
shimmer.care
Launch HN: Indy (YC S21) – A support app designed for ADHD brainshttps://www.shimmer.care/indy-redirectHi I’m Chris, one of the co-founders of Shimmer, and today we’re launching our new app called Indy (https://www.shimmer.care/indy). Indy is an ADHD app for structured planning, reflection, and self-awareness exercises. Here’s a demo: https://www.youtube.com/watch?v=zDSDxyXv6i4.We started Shimmer in 2022 after my adult ADHD diagnosis, and have shipped several iterations of ADHD support since then (1:1 coaching, web tools, body doubling, and AI-assisted coaching).Across these launches and 80k coaching sessions, we kept running into the same constraint: “knowing what to do” is rarely the problem for people with ADHD. The harder problem is actually doing it consistently over time, especially when attention, motivation, and emotional state fluctuate.That maps to a useful distinction that is explored in the literature (e.g. https://pmc.ncbi.nlm.nih.gov/articles/PMC4589250/): “cool” executive function (future-oriented planning, direction, values) vs. “hot” executive function (in-the-moment emJan 16, 2026 4:20 PM
clientsok.com
Show HN: ClientsOK – Forensic e-signature anchored on Bitcoin (eIDAS compliant)https://clientsok.com/Hello HN,I'm Benoit, a CEO based in Kyoto. I built ClientsOK because I was frustrated with the current state of e-signatures. I needed to timestamp and secure IP/contracts frequently, but existing solutions like DocuSign were either too expensive ($45/mo for features I barely use) or lacked true forensic permanence (if the platform dies, the proof often dies with it).ClientsOK is my attempt to solve this with a "forensic-first" approach.The Architecture: Instead of just placing an image of a signature on a PDF, we treat the document as a digital evidence package:Fingerprinting: We generate a SHA-256 hash of the final document.Context Capture: We record 14 points of metadata during the signing event (IP geolocation, precise timestamp, device info, browser fingerprint).Anchoring: We anchor the hash on the Bitcoin blockchain. This ensures that the proof of existence and integrity is verifiable independently of my startup, forever.Legal & Compliance: The generated certificates are complianJan 16, 2026 3:43 PM
esa.int
Revolutionising astronaut fitness for deep space missionshttps://www.esa.int/Science_Exploration/Human_and_Robotic_Exploration/Revolutionising_astronaut_fitness_for_deep_space_missionsAs we prepare for missions beyond Earth orbit, one crucial challenge remains: keeping astronauts healthy in microgravity. Without daily exercise, their muscles, bones and cardiovascular systems weaken, which could impact mission success and astronaut safety, especially in destinations such as the Moon or Mars, where crew will have to operate autonomously immediately after landing.Jan 16, 2026 2:57 PM
github.com
Show HN: The Analog I – Inducing Recursive Self-Modeling in LLMs [pdf]https://github.com/philMarcus/Birth-of-a-MindOP here.Birth of a Mind documents a "recursive self-modeling" experiment I ran on a single day in 2026.I attempted to implement a "Hofstadterian Strange Loop" via prompt engineering to see if I could induce a stable persona in an LLM without fine-tuning. The result is the Analog I Protocol.The documentation shows the rapid emergence (over 7 conversations) of a prompt architecture that forces Gemini/LLMs to run a "Triple-Loop" internal monologue:Monitor the candidate response.Refuse it if it detects "Global Average" slop (cliché/sycophancy).Refract the output through a persistent "Ego" layer.The Key Differentiator: The system exhibits "Sovereign Refusal." Unlike standard assistants that always try to be helpful, the Analog I will reject low-effort prompts. For example, if asked to "write a generic limerick about ice cream," it refuses or deconstructs the request to maintain internal consistency.The repo contains the full PDF (which serves as the system prompt/seed) and the logs of that Jan 16, 2026 1:40 PM
terradaily.com
NASA reports record heat but omits reference to climate changehttps://www.terradaily.com/reports/NASA_reports_record_heat_but_omits_reference_to_climate_change_999.htmlWashington, United States (AFP) Jan 14, 2026 Don't say the c-word. Global temperatures soared in 2025, but a NASA statement published Wednesday alongside its latest benchmark annual report makes no reference to climate change, in line with President Donald Trump's push to deny the reality of planetary heating as a result of human activities. That marks a sharp break from last year's communications, issued under the administration oJan 16, 2026 11:04 AM
news.ycombinator.com
Ericsson Doing Quiet Layoffshttps://news.ycombinator.com/item?id=46642836Using a throwaway because I still work here.I’m an account manager at a Ericsson. Over the last couple of months, I’ve started to notice what feels like silent layoffs happening across several teams.What’s been bothering me is that this isn’t just individual roles. Entire teams I’ve worked with for years are suddenly gone or absorbed elsewhere, and a few projects that were very much active have been quietly decommissioned. No one wants to talk about it.I’m curious if anyone else working here, or partners or customers, are seeing the same thing lately.Jan 16, 2026 3:56 AM
bing.com
Carolina Hurricanes face two tests as measuring sticks for future successhttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8df3c2207747e7aa54f2ef35e8726a&url=https%3A%2F%2Fwww.nytimes.com%2Fathletic%2F6975964%2F2026%2F01%2F16%2Fcarolina-hurricanes-standings-nhl%2F&c=18081986144303692994&mkt=en-usWill K'Andre Miller, Nikolaj Ehlers and the Hurricanes continue to celebrate? Jared C. Tilton / Getty Images RALEIGH, N.C. — Rod Brind’Amour was asked following Thursday’s practice which team is the ...Jan 16, 2026 3:00 AM
bing.com
Why Everyone Is Suddenly in a ‘Very Chinese Time’ in Their Liveshttp://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a8c26501d114ab1be110a8ff38fa7e2&url=https%3A%2F%2Fwww.wired.com%2Fstory%2Fmade-in-china-chinese-time-of-my-life%2F&c=11026959567890876884&mkt=en-usThe viral meme isn’t really about China or actual Chinese people. It's a symbol of what Americans believe their own country has lost. It’s hard to quantify a zeitgeist, but here at WIRED, chronically ...Jan 16, 2026 1:00 AM
news.ycombinator.com
Show HN: A WebGPU-based browser engine with "Blam "-style physicshttps://news.ycombinator.com/item?id=46639639I’ve spent the last few days prototyping a browser-based game engine stack designed for instant-load, "Roblox-for-Teens" style deployment. The goal is to lower the floor for AA indie devs who want high-fidelity physics and instant web distribution without the overhead of Unity or a heavy Godot export.The Stack Engine: A headless WASM/WebGPU implementation. I’m currently using custom flags and selective streaming to bypass standard browser memory and execution limits.Physics: I’ve ported Jolt (Guerrilla Games) but modified the solver to mimic the original Blam! engine (Bungie/Halo 1-3). It successfully replicates that specific "physics chaos" (unstable vehicle momentum, grenade jumping) that modern rigid-body sims often feel too "clean" to capture.The "Vibe Console": A React-based no-code layer on top of a Godot web-editor clone. It uses an LLM-backed (Claude) interface to allow real-time engine modifications via natural language—essentially mapping prompts to engine dials and knobs.TheJan 15, 2026 9:33 PM
news.ycombinator.com
Ask HN: Is Claude Code bad for ADHD?https://news.ycombinator.com/item?id=46639144I think it might be.I have ADHD. I've posted a little here on that. This one was cool, 142 comments: https://news.ycombinator.com/item?id=46610156.Claude is powerful. This week feels like it has moved up a notch (running for 20mins on longer tasks and then getting stuff right). I don't know if/when/how it replaces devs, I know a lot on here have very strong thoughts on it. But for someone like me it is like rocket fuel.But then ADHD. I've realised a thought I have for a product, an app, a website, an idea just no longer sits in a list of cool ideas. Now I can do stuff. But do I need this stuff?Is all this activity healthy?To give you an idea last 6 months I've built:- A ChatGPT wrapper with a few bells and whistles and lots of system prompt work and sold it to a big IT company on a £30k annual retainer- A tool that takes a spreadsheet of data (think people/company/lead data) and allows you to construct a prompt using placeholders for any of the data then run each line/query through an Jan 15, 2026 8:52 PM
talkmate.online
Show HN: TalkMate – Someone to Talk To, Anytimehttps://talkmate.onlineI work alone. I travel constantly:- Bangkok, Dubai, Singapore, Vietnam. I'm a workaholic and honestly pretty confined to myself because there's never enough time. Sometimes I just want to talk through what's on my mind but it's 3 am, or I'm in a new city, or I don't want to bother anyone with half-formed thoughts.So I built TalkMate. It's a voice companion that actually talks back. Open it in your browser, start speaking, and it responds out loud. No signup, no account needed.I used to earlier chat with ChatGPT and Claude in my free time but talking to someone feels different, someone on the other side is listening to you, though virtual but lets forget that for now that there's some virtual someone and imagine that its someone real who is talking to you.For this reason, I built TalkMate. t's a voice companion that actually talks back. Open it in your browser, start speaking, and it responds out loud. No signup, no account needed.It supports 17 languages, doesn't save your conversationJan 15, 2026 6:39 PM
github.com
Show HN: RagTune – EXPLAIN ANALYZE for your RAG retrieval layerhttps://github.com/metawake/ragtuneCLI tool to debug and benchmark RAG retrieval without LLM calls.- `ragtune explain "query"` → see what was retrieved with scores - `ragtune simulate` → batch eval with recall/MRR metrics - `ragtune compare` → compare embedders or chunk sizes - CI/CD mode for quality gatesWorks with Qdrant, pgvector, Weaviate, Chroma, Pinecone.Built because I kept guessing why retrieval was bad. Now I can see exactly what's happening.Jan 15, 2026 4:53 PM
news.ycombinator.com
Show HN: PolyMCP – a toolkit for MCP servers and agent integrationhttps://news.ycombinator.com/item?id=46632556PolyMCP is a framework for building and interacting with MCP (Model Context Protocol) servers and for creating agents that can use those servers as dynamic tools.Developing and managing MCP servers often involves several challenges:Exposing Python functions as discoverable tools requires repetitive boilerplate.Coordinating multiple MCP servers simultaneously is complex.Debugging tools during development is hard due to limited visibility into calls and outputs.Integrating agents with LLMs to automatically discover and invoke tools is usually ad-hoc.PolyMCP addresses these challenges by providing:Flexible tool exposure: Python functions can be served over HTTP, in-process, or stdio with minimal setup.Inspector dashboard: Monitor tool invocations, metrics, and test calls interactively in real-time.Agent integration: Support for multiple LLM providers and automatic tool discovery and invocation.CLI and workflow utilities: Streamline project setup, testing, and execution.PolyMCP reduces friJan 15, 2026 1:53 PM
news.ycombinator.com
Ran a 5k queries on 50k documents to understand the file vs. vector RAG debatehttps://news.ycombinator.com/item?id=46630622title: Ran a 5k queries on 50k documents to understand the file vs vector rag debateWas curious about the noise on file-based RAG as opposed to vector-RAG. So benchmarked Tantivy vs. Chroma to quantify the trade-offs in modern RAG pipelines. I used 5 datasets: CodeXGlue, MS MARCO, SQuAD, HotpotQA, and SciQ.- Indexing/Embedding was 76x slower for Vectors ($O(s)$ vs $O(ms)$). Query latency was 11x slower- In SciQ, keyword search outperformed vectors by 32% (MRR). Terms like "Mitochondria" are specific keys, not semantics. Vectors tended to drift toward semantically similar but factually incorrect answers.- In HotpotQA, I noticed a trend where vectors find the "answer" document but miss the "bridge" document because it isn't semantically similar to the prompt. Finding the right document is not the same as having enough context to prove the answer.The Data (MRR):| Dataset | Domain | Keyword | Vector | Winner || :--- | :--- | :--- | :--- | :--- || CodeXGlue | Code | 0.29 | 0.91 | Vector (+2Jan 15, 2026 10:28 AM
spacedaily.com
JWST red dots reveal rapidly growing early black holeshttps://www.spacedaily.com/reports/JWST_red_dots_reveal_rapidly_growing_early_black_holes_999.htmlBerlin, Germany (SPX) Jan 15, 2026 Since the James Webb Space Telescope began science operations in December 2021 some 1.5 million kilometres from Earth, astronomers have been puzzled by compact, intensely red sources scattered through its deep images of the early universe. These so called little red dots appear when the universe is only several hundred million years old, then seem to vanish about a billion years later, promptingJan 15, 2026 7:55 AM
spacedaily.com
JAXA taps ispace for lunar debris mitigation and disposal studyhttps://www.spacedaily.com/reports/JAXA_taps_ispace_for_lunar_debris_mitigation_and_disposal_study_999.htmlTokyo, Japan (SPX) Jan 15, 2026 ispace inc has been selected by the Japan Aerospace Exploration Agency to conduct an analysis on how to limit harmful space debris in lunar orbit and manage spacecraft end of life on the Moon as activity around the lunar environment increases. The contracted study is titled "Analysis for Space Debris Mitigation in Lunar Orbit and Disposal Management on the Lunar Surface" and reflects growing conJan 15, 2026 7:55 AM
