Hacker News

Ask HN: Who has seen productivity increases from AI

Hacker News - Tue, 02/24/2026 - 10:24am

I would love examples of positions and industries where AI has been revolutionary. I have a friend at one of the largest consulting firms who has said it'd been a game-changer in terms of processing huge amounts of documentation over a short period of time. Whether or not that gives better results is another question, but I would love to hear more stories of AI actually making things better.

Comments URL: https://news.ycombinator.com/item?id=47138336

Points: 1

# Comments: 0

Categories: Hacker News

Does Gemini 3 retain conversational context less reliably than Gemini 2.5?

Hacker News - Tue, 02/24/2026 - 10:22am

I could be mistaken, but Gemini 3.1 Pro seems less consistent than 2.5 Pro at adhering to instructions established earlier in the conversation.

For example, if I explicitly ask it not to include summaries or next steps in its outputs, it initially complies but eventually reverts to including them, as if the instruction has fallen out of scope.

Comments URL: https://news.ycombinator.com/item?id=47138307

Points: 1

# Comments: 0

Categories: Hacker News

Are AI agents not smart enough to generate their own AGENTS/SKILLS/X.md?

Hacker News - Tue, 02/24/2026 - 10:21am

Why do I have to write and take the trouble to specify these files when they could be generated automatically?

Comments URL: https://news.ycombinator.com/item?id=47138284

Points: 1

# Comments: 1

Categories: Hacker News

Show HN: Glass Box: writing editor that exports a verifiable PDF of your process

Hacker News - Tue, 02/24/2026 - 10:20am

We built a local-first writing editor that records the composition process (keystrokes, paste events, AI interactions) and exports a PDF with annotation highlights + an AI usage appendix.

The motivation: AI detectors are genuinely broken. Stanford research showed >60% false positive rates for non-native English writers on TOEFL essays. The "solution" from institutions has been to buy more detectors or make the policies so broad that either the student can do nothing if they are accused or the teacher can do nothing if the student does not make an admission.

Instead of trying to detect AI use after the fact, we give students a way to record their process as they write. The exported PDF shows a professor exactly what was human-written, what was AI-assisted, and what was pasted from external sources.

Tech stack: - NiceGUI (Python) for the editor - Quasar Q-Editor (contenteditable) with JS paste/ghost-completion hooks - Dual PDF engine: WeasyPrint (CSS rendering) with ReportLab fallback (pure Python, works on Windows) - Ollama integration for local AI (recommended model: qwen2.5:0.5b, ~400MB) - TWFF (Tracked Writing File Format): ZIP-based container with XHTML content + process-log.json with SHA-256 chained hash

The format spec (TWFF) is open. Anyone can implement it. We're trying to get at least one other tool to support it before calling it a "standard".

Demo: https://firl.nl/twff Spec: github.com/Functional-Intelligence-Research-Lab/twff

Comments URL: https://news.ycombinator.com/item?id=47138273

Points: 2

# Comments: 0

Categories: Hacker News

Pages