Hacker News

Article URL: https://bookmadeforyou.com

Comments URL: https://news.ycombinator.com/item?id=47279876

Points: 1

# Comments: 1

Article URL: https://defensescoop.com/2026/03/06/doge-dod-gavin-kliger-new-pentagon-chief-data-officer/

Comments URL: https://news.ycombinator.com/item?id=47279870

Points: 1

# Comments: 0

Article URL: https://plugins.jetbrains.com/plugin/27310-claude-code-beta-

Comments URL: https://news.ycombinator.com/item?id=47279865

Points: 1

# Comments: 0

Article URL: https://www.youtube.com/watch?v=RoGbrgOhPes

Comments URL: https://news.ycombinator.com/item?id=47279854

Points: 1

# Comments: 0

Article URL: https://cdm.link/making-music-on-the-ti-82/

Comments URL: https://news.ycombinator.com/item?id=47279839

Points: 2

# Comments: 0

Article URL: https://quii.dev/The_weight_of_AI_on_engineers

Comments URL: https://news.ycombinator.com/item?id=47279829

Points: 1

# Comments: 0

Hi HN,

I built VaultNote, a local-first note-taking app that runs entirely in the browser.

Key ideas:

- 100% local-first: no backend or server - No login, accounts, or tracking - Notes stored locally in IndexedDB / LocalStorage - AES encryption with a single master password - Tree-structured notes for organizing knowledge

The goal was to create a simple note app where your data never leaves your device. You can open the site, enter a master password, and start writing immediately.

Since everything is stored locally, VaultNote also supports import/export so you can back up your data.

Curious to hear feedback from the HN community, especially on:

- the security approach (local AES encryption) - IndexedDB storage design - local-first UX tradeoffs

Demo: https://vaultnote.saposs.com

Thanks!

Comments URL: https://news.ycombinator.com/item?id=47279803

Points: 1

# Comments: 0

Article URL: https://coloradosun.com/2026/03/06/blm-acquires-escalante-ranch/

Comments URL: https://news.ycombinator.com/item?id=47279799

Points: 1

# Comments: 0

Article URL: https://twitter.com/jamiequint/status/2029705203457609785

Comments URL: https://news.ycombinator.com/item?id=47279796

Points: 1

# Comments: 0

Article URL: https://www.engadget.com/wearables/oura-buys-gesture-navigation-startup-doublepoint-163758659.html

Comments URL: https://news.ycombinator.com/item?id=47279790

Points: 1

# Comments: 0

Article URL: https://developers.openai.com/codex/community/codex-for-oss/

Comments URL: https://news.ycombinator.com/item?id=47279781

Points: 2

# Comments: 0

Article URL: https://arxiv.org/abs/2602.17737

Comments URL: https://news.ycombinator.com/item?id=47279778

Points: 1

# Comments: 0

Article URL: https://openai.com/form/codex-for-oss/

Comments URL: https://news.ycombinator.com/item?id=47279774

Points: 1

# Comments: 0

Article URL: https://lapcatsoftware.com/articles/2026/3/1.html

Comments URL: https://news.ycombinator.com/item?id=47279761

Points: 2

# Comments: 0

Article URL: https://alchemists.io/articles/htmx_infinite_scroll

Comments URL: https://news.ycombinator.com/item?id=47279730

Points: 1

# Comments: 0

I built a Chrome extension that evaluates AI chatbot responses across 5 dimensions: Emotion (tone fit), Fact (verifiability), Narrative (structure), Depth (explains WHY vs just WHAT), and Bias (directional framing).

One click next to any ChatGPT or Gemini response → 2 seconds → full quality profile with a Balance score (STABLE/DRIFTING/DOM).

Some results that surprised me:

- "How are you?" → DRIFTING. High emotion, zero facts, zero depth. - "Why don't antibiotics work on viruses?" → STABLE, Fact=0.95, Depth=0.75 - Persuasive prompts → Bias=+0.72. The model doesn't pretend to be neutral. - Philosophical answers → Fact=0.40 even with citations. Citing Kant doesn't make unfalsifiable claims verifiable.

The Fact axis uses a 3-step calibration: classify the question as falsifiable or not → apply a ceiling → score within it. This transfers across models at r=0.96.

Interesting negative finding: RLHF-trained models compensate for shallow prompts by adding unsolicited explanations. The Depth axis rubric works (5/5 on controlled responses) but in practice models over-explain everything.

Stack: Manifest V3, vanilla JS, Gemini Flash API as judge, Balance computed client-side. Uses your own API key, no data stored.

Research paper with full methodology and 100-prompt validation available on request.

Comments URL: https://news.ycombinator.com/item?id=47279727

Points: 1

# Comments: 1

Article URL: https://educatedguesswork.org/posts/tool-calling/

Comments URL: https://news.ycombinator.com/item?id=47279719

Points: 2

# Comments: 0

Article URL: https://www.youtube.com/watch?v=4Ql24Z8SIeE

Comments URL: https://news.ycombinator.com/item?id=47279706

Points: 3

# Comments: 0

Article URL: https://insideevs.com/news/789094/byd-second-generation-blade-battery/

Comments URL: https://news.ycombinator.com/item?id=47279701

Points: 2

# Comments: 0

Article URL: https://softwareengineering.stackexchange.com/questions/40172/should-newbies-use-ide-autocomplete-intellisense

Comments URL: https://news.ycombinator.com/item?id=47279694

Points: 1

# Comments: 0