Hacker News Reader

mckennameyeron AI takes people at their word

Claude's great at reading what people say, but surprisingly bad at recognizing when a politician's stance is just the first signal in a negotiation.

mckennameyeron How long until AI automates all cognitive labor?

You're right, just updated.

Original title took one framing from the back half of the post (3 update cycles that can loosely be called the "ChatGPT era, then xAI/Meta/Gemini era, then Anthropic era"), but definitely not the point here. Thanks for flagging

mckennameyeron My minute-by-minute response to the LiteLLM malware attack

So basically the attacker and the dev who caught it were probably using the same tools if the malware was AI-generated (hence the fork bomb bug), and the investigation was AI-assisted (hence the speed). Less "tip of the iceberg" and more just that both sides got faster.

mckennameyeron Beyond has dropped “meat” from its name and expanded its high-protein drink line

It seems like a marketing play to seize on the protein movement. What will they do when fiber becomes the next craze?

mckennameyeron I Take My Laptop to the Gym So Claude Doesn't Have Downtime

Can definitely relate. I think forcing myself to conduct 1 session at a time feels so difficult not only from an efficiency POV but from an attention standpoint. Waiting for a session to finish, being alone with my thoughts... we're faced every day with things that are convincing us that multitasking is efficient when it's really not at all

mckennameyeron How Predictable Are the Oscars?

For anyone following the Chalamet drama... next you'll have to look into how many times a best actor frontrunner has lost thanks to their ego last week of the race!

mckennameyeron Caution: Read the Docs for Claude 4.6's Effort Parameter

Do you think reasoning and behavioral effort should be separate knobs, or is bundling them the right call?

mckennameyeron What to Put in a Claude Code Skill for Reviewing Your Team's Code

Aren't vibe PRs way more likely to get abandoned? Sure they reduce reviewer load, but then everyone feels less urgency to do a human review after. Do you think the skill is making that better or worse?

mckennameyeron Higher effort reduces deep research accuracy for Gemini Flash 3 and GPT-5

We tested GPT-5 and Gemini Flash 3 at low, medium, and high effort on 169 instances with human-verified answers, scored against a frozen offline web corpus using Deep Research Bench. High effort consistently scored worse than lower thinking levels for both models. Methodology and raw data: https://everyrow.io/docs/notebooks/deep-research-bench-paret... (edited)

mckennameyeron How LLM agents solve the table merging problem

Interesting approach with the cascade. How do you decide when to escalate from fuzzy matching to LLM?

mckennameyeron Show HN: Stockfisher –– our automated Warren Buffett

Super interesting direction. I've been pretty skeptical of “AI for stock picking” for the same reasons you mention. Curious how you handle the challenge of companies pivoting into new business areas that don't have historical precedent? For example, Apple's shift into services or Amazon's AWS dominance weren't really predictable from their earlier financials.