Feed aggregator

Article URL: https://en.wikipedia.org/wiki/Portable_C_Compiler

Comments URL: https://news.ycombinator.com/item?id=46929713

Points: 2

# Comments: 0

I built a system prompt architecture that forces LLMs (like Gemini 3.0 / Claude 4.5) to self-audit before responding.

It splits the model into two personas:

Agent: Generates the draft.

Auditor: Critiques the draft for logic errors and hallucinations.

The Code (Gist): [https://gist.github.com/ginsabo/9d99ee98068d904b214be9351f09...]

I also wrote a documentation book about the theory, but the Gist above is fully functional and free to use. I'd love to hear your feedback on this "User-Side Safety" approach.

Comments URL: https://news.ycombinator.com/item?id=46929709

Points: 1

# Comments: 0

Article URL: https://mfranc.com/blog/ai-2026/

Comments URL: https://news.ycombinator.com/item?id=46929700

Points: 1

# Comments: 0

Article URL: https://www.tomshardware.com/peripherals/printers/microsoft-stops-distrubitng-legacy-v3-and-v4-printer-drivers

Comments URL: https://news.ycombinator.com/item?id=46929696

Points: 3

# Comments: 1

Article URL: https://www.ft.com/content/a4cebf4c-c26c-48bb-82c8-5701d8256282

Comments URL: https://news.ycombinator.com/item?id=46929665

Points: 2

# Comments: 0

Article URL: https://www.nyu.edu/about/news-publications/news/2026/february/scientists-discover--levitating--time-crystals-that-you-can-hold.html

Comments URL: https://news.ycombinator.com/item?id=46929549

Points: 1

# Comments: 0

Article URL: https://www.youtube.com/watch?v=3VReIuv1GFo

Comments URL: https://news.ycombinator.com/item?id=46929546

Points: 1

# Comments: 0

They're back at it again after last week (https://news.ycombinator.com/item?id=46890418).

Comments URL: https://news.ycombinator.com/item?id=46929545

Points: 1

# Comments: 0

Article URL: https://github.com/pgmq/pgmq

Comments URL: https://news.ycombinator.com/item?id=46929512

Points: 1

# Comments: 0

django-rclone bridges Django's database layer with rclone's file transfer layer. You get native database dumps piped directly to any of rclone's 70+ supported cloud storage backends -- no temp files, no intermediate archives, no Python reimplementations of what rclone already does.

Comments URL: https://news.ycombinator.com/item?id=46929481

Points: 1

# Comments: 1

Article URL: https://www.niagara-gazette.com/news/local_news/ny-lawmakers-proposed-statewide-data-center-moratorium/article_7a21b9e3-85f6-4deb-a67f-8c3cef96df8c.html

Comments URL: https://news.ycombinator.com/item?id=46929468

Points: 1

# Comments: 0

Article URL: https://www.nature.com/articles/d41586-026-00370-w

Comments URL: https://news.ycombinator.com/item?id=46929464

Points: 2

# Comments: 0

I build AI agents for work and kept hitting the same issue: a user corrects the agent, the session ends, and the correction is gone. Next session, same correction. I tracked it across our users and the average preference gets re-corrected 4+ times before people just give up. Existing solutions don't really solve this. Memory layers store raw conversation logs. RAG retrieves documents. Neither extracts what the user actually wants as a structured, persistent preference. So I built pref0. It does one thing: extracts structured preferences from user corrections and compounds confidence across sessions. How it works in practice. Say you're building a customer support agent:

Session 1: User says "always escalate billing issues to a human, don't try to resolve them." pref0 extracts billing_issues: escalate_to_human, confidence 0.55.

Session 4: User flags a billing ticket the agent tried to auto-resolve. pref0 reinforces the preference. Confidence hits 0.85.

Session 7: A billing issue comes in. The agent routes it to a human without being told. No correction needed.

Now multiply that across hundreds of users. Each one teaching your agent slightly different things. pref0 maintains a structured profile per user (or team, or org) that your agent reads before every response.

The API is intentionally minimal. Two endpoints: POST /track: send conversation history after a session. pref0 extracts preferences automatically. GET /profiles/{user_id}: fetch learned preferences before the agent responds.

A few design decisions: > Explicit corrections ("don't do X") score higher than implied preferences. Stronger signal. > Preferences are hierarchical: user > team > org. New team members inherit org conventions on day one. > Confidence decays over time so stale preferences don't stick forever.

This isn't a replacement for memory. Memory stores what happened. pref0 learns what the user wants. You can run both side by side.

Works with LangChain, CrewAI, Vercel AI SDK, or raw API calls. Free tier available -> https://pref0.com/docs

Would love feedback on the approach, especially from anyone building agents with repeat users.

Comments URL: https://news.ycombinator.com/item?id=46929447

Points: 4

# Comments: 0

Article URL: https://github.com/ghostty-org/ghostty/pull/10559

Comments URL: https://news.ycombinator.com/item?id=46929431

Points: 2

# Comments: 0

Article URL: https://github.com/sultanvaliyev/sshcode

Comments URL: https://news.ycombinator.com/item?id=46929429

Points: 1

# Comments: 0

Article URL: https://jpcaparas.medium.com/microsoft-appointed-a-quality-czar-he-has-no-direct-reports-and-no-budget-ab75cef97954

Comments URL: https://news.ycombinator.com/item?id=46929410

Points: 1

# Comments: 0

Article URL: https://gist.github.com/sigalovskinick/6cc1cef061f76b7edd198e0ebc863397

Comments URL: https://news.ycombinator.com/item?id=46929406

Points: 1

# Comments: 0

Article URL: https://www.nytimes.com/2026/02/07/technology/washington-post-will-lewis.html

Comments URL: https://news.ycombinator.com/item?id=46929404

Points: 4

# Comments: 1

Article URL: https://devxt.com

Comments URL: https://news.ycombinator.com/item?id=46929394

Points: 2

# Comments: 4