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

Show HN: Three Emojis, a daily word puzzle for language learners https://ift.tt/cPnuxgI

Show HN: Three Emojis, a daily word puzzle for language learners I'm in the process of learning German and wanted to play a German version of the NYT’s Spelling Bee. It was awful, I was very bad at it, it was not fun. So I built my own version of Spelling Bee meant for people like me. Three Emojis is a daily word game designed for language learners. You get seven letters and a list of blanked-out words to find. When you discover shorter words, they automatically fill into longer ones—like a crossword—which turns out to be really useful for languages like German. Each word also gets three emojis assigned to it as a clue, created by GPT-5 to try and capture the word’s meaning (this works surprisingly well, most of the time). If you get stuck, you can get text/audio hints as well. It supports German and English, with new puzzles every day. You can flag missing words or suggest additions directly in the game. The word lists include slang, abbreviations, and chat-speak—because those are, in my opinion, a big part of real language learning too (just nothing vulgar, too obscure or obsolete). Every word you find comes with its definition and pronunciation audio. If you want infinite hints or (coming soon) archive access, you can upgrade to Pro. Feedback is very welcome, it's my first game and I'm certainly not a frontend guy. Happy spelling! https://ift.tt/uY4tlVD November 8, 2025 at 01:06AM

Show HN: A Lightweight Kafka Alternative https://ift.tt/XR3YpeQ

Show HN: A Lightweight Kafka Alternative https://ift.tt/QTUJGXW November 7, 2025 at 07:28PM