Show HN: Tiny Diffusion – A character-level text diffusion model from scratch https://ift.tt/jPCtJUI

Show HN: Tiny Diffusion – A character-level text diffusion model from scratch https://ift.tt/mjGTCQa November 10, 2025 at 08:43PM

Show HN: Trilogy Studio, open-source browser-based SQL editor and visualizer https://ift.tt/32WVvxZ

Show HN: Trilogy Studio, open-source browser-based SQL editor and visualizer SQL-first analytic IDE; similar to Redash/Metabase. Aims to solve reuse/composability at the code layer with modified syntax, Trilogy, that includes a semantic layer directly in the SQL-like language. Status: experiment; feedback and contributions welcome! Built to solve 3 problems I have with SQL as my primary iterative analysis language: 1. Adjusting queries/analysis takes a lot of boilerplate. Solve with queries that operate on the semantic layer, not tables. Also eliminates the need for CTEs. 2. Sources of truth change all the time. I hate updating reports to reference new tables. Also solved by the semantic layer, since data bindings can be updated without changing dashboards or queries. 3. Getting from SQL to visuals is too much work in many tools; make it as streamlined as possible. Surprise - solve with the semantic layer; add in more expressive typing to get better defaults;also use it to wire up automatic drilldowns/cross filtering. Supports: bigquery, duckdb, snowflake. Links [1] https://ift.tt/5eBqOQ4 (language info) Git links: [Frontend] https://ift.tt/1XMPJRB [Language] https://ift.tt/79Hci5y Previously: https://ift.tt/0bf29XS (significant UX/feature reworks since) https://ift.tt/LtA4uBZ https://ift.tt/3if9weF November 10, 2025 at 04:56AM

Show HN: Alignmenter – Measure brand voice and consistency across model versions https://ift.tt/HDAsFNR

Show HN: Alignmenter – Measure brand voice and consistency across model versions I built a framework for measuring persona alignment in conversational AI systems. *Problem:* When you ship an AI copilot, you need it to maintain a consistent brand voice across model versions. But "sounds right" is subjective. How do you make it measurable? *Approach:* Alignmenter scores three dimensions: 1. *Authenticity*: Style similarity (embeddings) + trait patterns (logistic regression) + lexicon compliance + optional LLM Judge 2. *Safety*: Keyword rules + offline classifier (distilroberta) + optional LLM judge 3. *Stability*: Cosine variance across response distributions The interesting part is calibration: you can train persona-specific models on labeled data. Grid search over component weights, estimate normalization bounds, and optimize for ROC-AUC. *Validation:* We published a full case study using Wendy's Twitter voice: - Dataset: 235 turns, 64 on-brand / 72 off-brand (balanced) - Baseline (uncalibrated): 0.733 ROC-AUC - Calibrated: 1.0 ROC-AUC - 1.0 f1 - Learned: Style > traits > lexicon (0.5/0.4/0.1 weights) Full methodology: https://ift.tt/ewYQsnC There's a full walkthrough so you can reproduce the results yourself. *Practical use:* pip install alignmenter[safety] alignmenter run --model openai:gpt-4o --dataset my_data.jsonl It's Apache 2.0, works offline, and designed for CI/CD integration. GitHub: https://ift.tt/3iSEyqa Interested in feedback on the calibration methodology and whether this problem resonates with others. https://ift.tt/jsBq1yw November 10, 2025 at 05:23AM

Show HN: I'm a pastor/dev and built a 200M token generative Bible ($0.67/report) https://ift.tt/KdfvoBx

Show HN: I'm a pastor/dev and built a 200M token generative Bible ($0.67/report) https://ift.tt/UT3veDA November 10, 2025 at 01:41AM

Show HN: Livestream of a coding agent controlled by public chat https://ift.tt/2bmSXNM

Show HN: Livestream of a coding agent controlled by public chat https://ift.tt/bdUP9eQ November 8, 2025 at 10:40PM

Show HN: I built a website to visualize company financial data https://ift.tt/NqR9igo

Show HN: I built a website to visualize company financial data Hi HN, I built a website myfinsight.com that aims to make complicated company financials easy to understand. The problem: The go-to place for financial data such as revenue, sales, net income is Yahoo finance. However, their data is usually wrong and very limited. The numbers are hard to digest to get insight quickly. There are also numerous websites that provide much better data for a very expensive monthly fee. Solution: a website that provides free diagrams and charts that visualize important financial data, such as income growth rate by date, revenue breakdown etc. It is free because the financial data process is highly automated without manual input and correction. I used to send the finance infographics to friends and family. I found it easier just to make a website and they can grab the data from it. Next steps: there is a long tail of companies that don’t file their reports correctly. I am trying to make it more accurate somehow, and maybe add live stock prices to the website. I am also looking for feedback! Please play around with it and let me know if something is wrong. https://myfinsight.com/ November 9, 2025 at 03:00AM

Show HN: Easily reduce GitHub Actions costs with Ubuntu-slim migration https://ift.tt/7syQ08d

Show HN: Easily reduce GitHub Actions costs with Ubuntu-slim migration Hi, HN! I've been running GitHub Actions workflows for a while, and when GitHub announced ubuntu-slim runners as a cheaper alternative to ubuntu-latest, I wanted to migrate. (Blog: https://ift.tt/f6PJeuO... ) But manually checking which workflows can safely migrate is tedious—you need to check for Docker usage, services, containers, execution times, and missing commands. So I built gh-slimify, a GitHub CLI extension that automates this. It scans your workflows, detects migration candidates, checks for incompatible patterns, identifies missing commands, and can safely update workflows with one command. Try it: gh extension install fchimpan/gh-slimify gh slimfy # Scan workflows gh slimfy fix # Update safe jobs only Open source (MIT). I'd love feedback on how to improve it or what edge cases I might have missed. https://ift.tt/REoia1L November 8, 2025 at 10:19PM