188 results for did nan · 2.284s

News for “did nan”
19 results • 2277 ms server time
Moozonian News
github.com• Aug 4, 2026• 1 min read
Show HN: I redesigned my self-hosted data manager's UI (4k stars, v2Hello HN,I posted an early version of this back in 2021 (it did well here — got a lot of feedback). Since then I kept building it as a self-hosted alternative to juggling separate apps for passwords, notes, files, finances, contacts, etc. — one place, self-hosted, no cloud dependency.Recently I shipped v2.0 with a full UI redesign: - dropped jQuery in favor of Vue.js - frontend is now a standalone project, with the original tool serving as backend - more modern, slicker UI, and mobile friendly - added TypeScript support - moved the build to ViteBackend is still PHP/Symfony based — it's a bit behind with dependencies since most of my time went into features rather than upkeep. I've already updated PHP at some point, and I definitely want to raise the framework/PHP version further — it's on my list.I deliberately don't offer a hosted/managed version — the app stores sensitive personal data and I don't want to be the one liable for hosting other people's passwords.I'm slowly working furth
Advertisement
Moozonian News
bing.com• Aug 3, 2026• 1 min read
Kenyon Sadiq (rest) did not practice MondayJets TE Kenyon Sadiq (rest) did not practice on Monday. Head coach Aaron Glenn said after practice that Sadiq’s absence was due to maintenance after the rookie underwent offseason hernia surgery. We ...
Moozonian News
github.com• Aug 2, 2026• 1 min read
Show HN: DFAH-Bench – same agent decision, different tool pathsHey - released this PyPi library after getting annoyed most agent evals only focus on outcomes, and the tool calling path is just as important in recognizing the outcome decision. So defined decision agreement rates, trajectory agreement rates etc etcMost tell us whether the final answer was right, but not whether the agent actually did the same thing twice.In prospective replays of financial services tasks, agents reached the same decision about 94–95% of the time. Exact tool-name paths matched only 67–69%. Once the tool arguments were included, agreement fell to 45–52%.I don’t think every different path is automatically a failure. Sometimes it’s harmless flexibility. But if an agent can touch files, APIs, email, or financial controls, I’d at least like to know that it changed its path before calling the system stable.The package repeatedly runs your agent, stores the traces, and compares the decision, tool order, arguments, and result identities.Quick local test - no key or paid mode
Moozonian News
ctgt.ai• Jul 30, 2026• 1 min read
Show HN: Distilling DeepSeek into GPT-OSS doesn't transfer censorship. Try itWe recently used DeepSeek V4 Flash as a teacher for finance tasks with GPT-OSS-120B. Distillation works well on this problem. At a constrained 8k token budget, our self-distilled 120B scores 83.61% on FinanceReasoning, above Kimi K3 (81.93%) and Inkling (65.13%). We released the 20B open weights. With V4 as the teacher though, we realized it would be timely to measure if the censorship characteristic of it transferred to the distilled version of the base model. tl;dr it didn't, the teacher answered politically sensitive questions 7 SDs differently than expected, but the distilled model's behavior remained the same as its American base. You can try a couple queries yourself with no auth here: http://playground.ctgt.ai/I will now dive in to the motivation, methodology and detailed results for those interested. The hard part of measuring this phenomena is isolating whether a model is reluctant to talk about sensitive things generally vs. a particular country's sensitive things. So we made
Moozonian News
achiever.so• Jul 29, 2026• 1 min read
Show HN: Steam-style achievements, but for real life (777 milestones)For about 10 years I kept notes about things I wanted to do or already did. The notes never became anything useful, so this winter I started turning them into an app.It's not a habit tracker, it's a discrete-event tracker: 777 one-time milestones in 14 life categories (fitness, career, travel, finances, learning, mental health, etc.), each worth 5-100 points depending on difficulty. No streaks, no daily check-ins. You did it once, it counts forever.Two design decisions people argue with me about:1. I built streaks early, then hid the whole feature. Streaks push you to repeat things, but this app is about finish lines. They worked against each other, so streaks had to go.2. Profiles are public by default (it's a social tracker), but 31 achievements about addiction, therapy and mental health never show on public profiles unless you opt in. This is done with row-level security in Postgres, not filtered on the client. So you can track quitting nicotine and your profile won't announce it. T
Moozonian News
cadencemoney.com• Jul 29, 2026• 1 min read
Show HN: Cadence Money – a budgeting app with no AI features, just an MCP serverI thought I could make a personal finance app that was simpler, smarter and more privacy-focused than Monarch, YNAB and Copilot. I believe I have, but today that's up to you.While the classic story of using a variety of "analog" tools to manage money does apply to me, the main pillars that pushed me to build Cadence Money were:- Pay for the level of syncing that's used including none- No built-in AI- Fully cross-platform including mobile browsers- Passkeys available day one- Proper Canadian support- No ads even for a bookAfter seven years at 1Password as a Lead PM, I can safely say working on Cadence has been the most fulfilling part of my career. Really thankful for friends, family, and now strangers for helping shape Cadence. It has every feature we needed, and nothing we didn't. I also created an MCP server so you can choose how much AI you want in your finances. Read-only at this point, but open to adding write access in the future to clean up CSV imports. Fair warning that Claude
Advertisement
Moozonian News
news.ycombinator.com• Jul 25, 2026• 1 min read
Programmer GovernmentHey I had an idea. What if we created the bitcoin for government?So like a king sucks because it's the equivalent of one GPU.A republic is better because it's like a big GPU cluster of hundreds of GPUs.But what if we made like a bitcoin like distributed governance system that was like, I don't know, a million GPUs?We have the internet which is like infinite bandwidth compared to human needs, so we have the bandwidth to link all our minds together.So what if we did this. We had a simple program that essentially each person could host a node and get 5 random people's data, so like we would store data on numerous nodes for redundancy.We have enough gigabytes, we could store a routing table for everybody's data in America since there's only like 300 million people, if each person had a kilobyte of data, it could be stored in 300 GB which is a lot but actually still doable on consumer level hardware.So then we would have a routing table of which nodes has which person's data, and then we co
Moozonian News
news.ycombinator.com• Jul 25, 2026• 1 min read
Who's making money from using/exploiting AI?I'm looking for some concrete examples of any AI advancements actually causing someone to financially prosper where they didn't before. Most of the examples I can think of make someone or something slightly more streamlined or productive, and so I'm looking for cases where company X is now Y% more profitable because of AI advancements.
Moozonian News
ticker-line.com• Jul 19, 2026• 1 min read
Show HN: Ticker-line.com – embeddable market sparkline SVGsThis one is super niche.I needed a simple service to render sparklines of stocks, crypto, indices, etc for an open source financial agent I'm working on. Didn't find any good options out there, so I built ticker-line.It's a free service to embed SVGs of sparklines in HTML and markdown, and shows live market data.You probably don't need it! But I liked how it turned out and wanted to share.
Moozonian News
finterm.ai• Jul 13, 2026• 1 min read
Show HN: Finterm.ai Bloomberg terminal for Claude CodeHi, my name is Kam, and today my cofounder Josh and I are shipping Finterm, a CLI that gives coding agents direct access to financial data: stock prices, options data, SEC filings, and Ticker Deep Research, a filtered ticker news search. I’m a developer and have been a full-time trader for the past few years.Recently I have been using LLMs more and more in my trading and strategy. I always found it frustrating that Claude Code or GPT did not have direct access to actual financial information and had to rely on web search, so it couldn’t get me more granular numbers for specific options pricing.When making a trade I want to understand as much as possible about the stock. Instead of relying on analysts or interpretations of the data, I like to go directly to the truth. So whenever I have a trade thesis, I break research into a few parts: company research, analyst sentiment, and market sentiment.Last September I had a short thesis on Popmart Labubu's parent company. I was betting the toy
Advertisement
Moozonian News
news.ycombinator.com• Jul 11, 2026• 1 min read
Bitemporal provenance in agent memory: What did we believe, when, and whyCozoDB, a transactional relational-graph-vector database with embedded Datalog in Rust, went dormant in December 2024. We hard-forked it as MnesticDB (not official CozoDB), under an MPL-2.0 license, to continue Ziyang Hu and the Cozo Project Authors' vision of building a "Hippocampus for AI", or agentic memory.But agentic memory isn't a pile of current facts with a log of past decisions. It has to track change over time, and be auditable. We've recently shipped several features that make this possible.First, we added a distinction between valid time (when a fact is true about the world) and transaction time (when the database came to believe it). This allows time travel, the ability to audit the memory at any point and see what knowledge any past decision was based on. Every write draws its transaction time from a crash-safe monotone commit clock, an atomic high-water mark persisted inside the same transaction that commits the data, so the clock can never advance without the write land