This story was originally published on HackerNoon at: https://hackernoon.com/i-got-tired-of-making-tiktok-videos-manually-so-i-built-a-cli-that-does-it-in-one-command.
I make short coding videos. JavaScript tips, AI explainers, quick tutorials. The kind of content that works on TikTok and YouTube Shorts.
Check more stories related to tech-companies at: https://hackernoon.com/c/tech-companies. You can also check exclusive content about #tiktok, #video, #npm, #tiktok-tool, #social-media-tool, #cli, #automate-tiktok-videos, #content-creation-tools, and more.

This story was written by: @fix2015. Learn more about this writer by checking @fix2015's about page, and for more stories, please visit hackernoon.com.

I make short coding videos. JavaScript tips, AI explainers, quick tutorials. The kind of content that works on TikTok and YouTube Shorts. Every single video needs the same things: a voiceover, captions synced to the words, maybe a code snippet on screen. And every single time, I'd open a video editor, import the audio, manually time the captions, add the code overlay, and export. For a 30-second video, this took 20-30 minutes of clicking around.

This story was originally published on HackerNoon at: https://hackernoon.com/openai-open-sources-privacy-filter-a-tiny-model-that-scrubs-pii-without-an-api-call.
OpenAI open-sourced Privacy Filter, a 50M-active-parameter model that detects and masks PII locally in one pass. Here's what's actually new, and what's hype.
Check more stories related to tech-companies at: https://hackernoon.com/c/tech-companies. You can also check exclusive content about #openai, #open-source, #privacy-filter, #openai-privacy-filter, #tiny-model, #ai, #openai-open-sources, #hackernoon-top-story, and more.

This story was written by: @abstraction. Learn more about this writer by checking @abstraction's about page, and for more stories, please visit hackernoon.com.

OpenAI released Privacy Filter under Apache 2.0 — a 1.5B-parameter (50M active) bidirectional token-classification model that detects and masks PII in text locally, in a single forward pass. It runs on a laptop, supports 128K context, hits 96% F1 out of the box, and is fine-tunable with minimal data. Eight entity categories: names, addresses, emails, phones, URLs, dates, account numbers, and secrets. It's context-aware (not regex), ships with a CLI and eval tooling, and slots into the same open-weight ecosystem as gpt-oss. The catch: multilingual support is thin, adversarial formatting breaks it, and the benchmark validation used OpenAI's own models to grade OpenAI's model.

This story was originally published on HackerNoon at: https://hackernoon.com/meet-deepgram-hackernoon-company-of-the-week.
This week, HackerNoon features Deepgram - a voice AI platform processing 50,000 years of audio for NASA, Spotify, and 200,000+ developers worldwide.
Check more stories related to tech-companies at: https://hackernoon.com/c/tech-companies. You can also check exclusive content about #tech-companies, #hackernoon-company-of-the-week, #tech-company-news-pages, #hackernoon-top-story, #meet-deepgram, #artificial-intelligence, #speech-recognition-api, #voice-ai-api, and more.

This story was written by: @companyoftheweek. Learn more about this writer by checking @companyoftheweek's about page, and for more stories, please visit hackernoon.com.

HackerNoon features Deepgram - a voice AI platform providing speech-to-text, text-to-speech, and voice agent APIs for developers. Founded in 2015 by particle physicists, Deepgram has raised $130M in Series C funding at a $1.3B valuation and serves 200,000+ developers including NASA, Spotify, and Citi. The company has processed over 50,000 years of audio and transcribed over 1 trillion words, making it a leader in enterprise voice AI solutions.