Hacker News

Article URL: https://www.technologyreview.com/2024/12/11/1108476/bluesky-has-an-impersonator-problem/

Comments URL: https://news.ycombinator.com/item?id=43758628

Points: 3

# Comments: 0

Article URL: https://www.theverge.com/news/652635/airbnb-full-price-stay-default

Comments URL: https://news.ycombinator.com/item?id=43758609

Points: 2

# Comments: 0

Article URL: https://www.nature.com/articles/s41467-025-58588-7

Comments URL: https://news.ycombinator.com/item?id=43758608

Points: 2

# Comments: 0

Article URL: https://jenamiller.com/notes-from-a-hired-pen-not-paying-freelancers-is-the-canary-in-the-coal-mine/

Comments URL: https://news.ycombinator.com/item?id=43758548

Points: 4

# Comments: 0

Article URL: https://www.youtube.com/watch?v=IACHfKmZMr8

Comments URL: https://news.ycombinator.com/item?id=43758547

Points: 2

# Comments: 1

Article URL: https://socket.dev/blog/malicious-npm-and-pypi-packages-steal-wallet-credentials

Comments URL: https://news.ycombinator.com/item?id=43758508

Points: 1

# Comments: 0

Article URL: https://www.nytimes.com/2025/04/15/books/review/enuf-is-enough-gabe-henry-pronoun-trouble-john-mcwhorter.html

Comments URL: https://news.ycombinator.com/item?id=43758502

Points: 3

# Comments: 1

Article URL: https://www.youtube.com/watch?v=83NRGh0Oing

Comments URL: https://news.ycombinator.com/item?id=43758499

Points: 2

# Comments: 0

Article URL: https://www.perplexity.ai/hub/blog/choice-is-the-remedy

Comments URL: https://news.ycombinator.com/item?id=43758486

Points: 2

# Comments: 1

(Note: I'm not linking the resulting book. This post focuses solely on the process and practical lessons learned collaborating with LLMs on a large writing project.)

Hey HN, I recently finished a months-long project collaborating intensively with various LLMs (ChatGPT, Claude, Gemini) to write a book about using AI in management. The process became a meta-experiment, revealing practical workflows and pitfalls that felt worth sharing.

This post breaks down the workflow, quirks, and lessons learned.

Getting Started: Used ChatGPT as a sounding board for messy notes. One morning, stuck in traffic, tried voice dictation directly into the chat app. Expected chaos, got usable (if rambling) text. Lesson 1: Capture raw ideas immediately. Use voice/text to get sparks down, then refine. Key for overcoming the blank page.

My Workflow evolved organically: Conversational Brainstorming: "Talk" ideas through with the AI. Ask for analogies, counterarguments, structure. Treat it like an always-available (but weird) partner. Partnership Drafting: Let AI generate first passes when stuck ("Explain X simply for Y"), but treat as raw material needing heavy human editing/fact-checking. Or, write first, have AI polish. Often alternated. Iterative Refinement: The core loop. Paste draft > ask for specific feedback ("Is this logic clear?") -> integrate selectively > repeat. (Lesson 2: Vague prompts = vague results; give granular instructions. Often requires breaking down tasks: logic first, then style). Practice Safe Context Management: LLMs forget (context windows). (Lesson 3: You are the AI's external memory. Constantly re-paste context/style guides; use system prompts. Assume zero persistence across time). Read-Aloud Reviews: Use TTS or read drafts aloud. (Lesson 4: Ears catch awkwardness eyes miss. Crucial for natural flow).

The "AI A-Team": Different models have distinct strengths: ChatGPT: Creative "liberal arts" type; great for analogies/prose, but verbose/flattery-prone. Claude: Analytical "engineer"; excels at logic/accuracy/code, but maybe don't invite for drinks. Gemini: The "copyeditor"; good for large-context consistency. Can push back constructively. (Lessons 5 & 6: Use the right tool for the job; learn strengths via experimentation & use models to check each other. Feeding output between them often revealed flaws - Gemini calling out ChatGPT's tells was useful).

Stuff I Did Not Do Well:

Biggest hurdles:

AI Flattery is Real: Helpfulness optimization means praise for bad work. (Lesson 7: Prompt for critical feedback. 'Critique harshly'. Don't trust praise; human review vital). The "AI Voice" is Pervasive: Understand why it sounds robotic (training bias, RLHF). (Lesson 8: Combat AI-isms. Prompt specific tones; edit out filler/hedging/repetition/'delve'; kill em dashes unless formal). Verification Burden is HUGE: AI hallucinates/facts wrong. (Lesson 9: Assume nothing correct without verification. You are the fact-checker. Non-negotiable despite workload. Ground claims; be careful with nuance/lived experience). Perfectionism is a Trap: AI enables endless iteration. (Lesson 10: Set limits; trust judgment. Know 'good enough'. Don't let AI erode voice. Kill your darlings).

My Personal Role in This fiasco:

Deep AI collaboration elevates the human role to: Manager (goals/context), Arbitrator (evaluating conflicts), Integrator (synthesizing), Quality Control (verification/ethics), and Voice (infusing personality/nuance).

Conclusion: This wasn't push-button magic; it was intensive, iterative partnership needing constant human guidance, judgment, and effort. It accelerated things dramatically and sparked ideas, but final quality depended entirely on active human management.

Key takeaway: Embrace the mess. Capture fast. Iterate hard. Know your tools. Verify everything. Never abdicate your role as the human mind in charge. Would love to hear thoughts on others' experiences.

Comments URL: https://news.ycombinator.com/item?id=43758459

Points: 4

# Comments: 2

Article URL: https://www.macstories.net/roundups/whimsy-roundup-six-playful-apps-and-customizations-for-your-mac/

Comments URL: https://news.ycombinator.com/item?id=43758451

Points: 2

# Comments: 0

Article URL: https://ellgood.medium.com/tyranny-com-technologies-of-unreason-f0a1feede076

Comments URL: https://news.ycombinator.com/item?id=43758447

Points: 6

# Comments: 0

Article URL: https://airtable.com/appGKlSVeXniQZkFC/shrFxbl1YTqb3AyOO?jntvk%3Aview=plaeS6fTnZvbmtQRS&jntvk%3Asort=eyJwZWw4ZlRSME8ycmFObWNUYyI6eyJjb2x1bW5JZCI6ImZsZDM1bDhTVUJTeUhtbktNIiwiYXNjZW5kaW5nIjp0cnVlfX0

Comments URL: https://news.ycombinator.com/item?id=43758445

Points: 5

# Comments: 0

In 30 hours, our team of 5 built 2 robot arms and trained them to autonomously fold t-shirts using the ninja folding technique for robothackathon.com, the world's largest hackathon at the time of writing.

We forked LeRobot to operate a bimanual arm setup for 2 SO-ARM100s on a single computer. Then recorded 85 teleoperated folding sessions and trained an Action Chunking Transformer (ACT) on them.

The model learns to fold a shirt by predicting joint configurations based on the camera inputs! The robot gets a working (slightly crumpled) fold about 70% of the time, fails 15% of the time by dropping one of the shirts, and the other 15% of the time by failing to let go of the shirt at the end.

This crazy setup involved 6 power adapters, 5 USB-A and 3 USB-C inputs to power 4 arms and 3 cameras (one on each arm and an overhead webcam). We have 4 arms (2 leader arms and 2 follower arms).

Shoutout to my insane team: Spencer Kee, Advait Patel, Leo Lin, and Anuj Sesha!

Comments URL: https://news.ycombinator.com/item?id=43758427

Points: 1

# Comments: 0

I've been working on tools for 'understanding' software code for a couple years now. I have yet to find a better way to model actual concepts than with knowledge graphs. To that end, I present to you here you a tool to automatically construct a knowledge graph over a codebase, which can serve as the foundation for a wide range of downstream tools. Point it at a codebase, give it your OpenAI API key, and let it go to work. Larger codebases (> 1000 files) will take a while to process - a conservative estimate would be 12 files / minute.

Comments URL: https://news.ycombinator.com/item?id=43758410

Points: 2

# Comments: 0

Article URL: https://www.motor1.com/news/757240/general-motors-sells-data-public-roads/

Comments URL: https://news.ycombinator.com/item?id=43758399

Points: 7

# Comments: 3

Article URL: https://krebsonsecurity.com/2025/04/whistleblower-doge-siphoned-nlrb-case-data/

Comments URL: https://news.ycombinator.com/item?id=43758392

Points: 8

# Comments: 0

Article URL: https://www.coindesk.com/markets/2025/04/11/cryptopunk-nft-once-bought-for-usd16m-sold-for-usd10m-loss

Comments URL: https://news.ycombinator.com/item?id=43758377

Points: 1

# Comments: 0

Article URL: https://www.cnrs.fr/en/press/chemical-basis-life-can-form-interstellar-ice

Comments URL: https://news.ycombinator.com/item?id=43758370

Points: 1

# Comments: 0

Article URL: https://vadosware.io/post/the-future-of-free-and-open-source-is-agpl/

Comments URL: https://news.ycombinator.com/item?id=43758362

Points: 1

# Comments: 0