Hacker News: mckennameyer

New comment by mckennameyer in "AI takes people at their word"

mckennameyer — Tue, 09 Jun 2026 14:11:09 +0000

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.

AI takes people at their word

mckennameyer — Tue, 09 Jun 2026 14:11:09 +0000

Article URL: https://futuresearch.ai/ai-takes-people-at-their-word/

Comments URL: https://news.ycombinator.com/item?id=48461396

Points: 5

# Comments: 1

New comment by mckennameyer in "How long until AI automates all cognitive labor?"

mckennameyer — Thu, 28 May 2026 15:00:15 +0000

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

How long until AI automates all cognitive labor?

mckennameyer — Thu, 28 May 2026 14:21:35 +0000

Article URL: https://futuresearch.ai/blog/agi-timeline-tracker/

Comments URL: https://news.ycombinator.com/item?id=48309344

Points: 45

# Comments: 82

Apple's Plan to Power Siri with ChatGPT Was a Predictable Failure

mckennameyer — Fri, 15 May 2026 14:44:43 +0000

Article URL: https://futuresearch.ai/blog/apple-openai-failure/

Comments URL: https://news.ycombinator.com/item?id=48149329

Points: 3

# Comments: 0

Claude is that gullible friend who takes everyone at their word

mckennameyer — Wed, 13 May 2026 15:16:41 +0000

Article URL: https://futuresearch.ai/ai-takes-people-at-their-word/

Comments URL: https://news.ycombinator.com/item?id=48123056

Points: 1

# Comments: 0

New comment by mckennameyer in "My minute-by-minute response to the LiteLLM malware attack"

mckennameyer — Thu, 26 Mar 2026 18:44:34 +0000

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.

New comment by mckennameyer in "Beyond has dropped “meat” from its name and expanded its high-protein drink line"

mckennameyer — Tue, 17 Mar 2026 14:07:07 +0000

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

New comment by mckennameyer in "I Take My Laptop to the Gym So Claude Doesn't Have Downtime"

mckennameyer — Tue, 17 Mar 2026 14:00:13 +0000

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

New comment by mckennameyer in "How Predictable Are the Oscars?"

mckennameyer — Fri, 13 Mar 2026 17:14:31 +0000

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!

New comment by mckennameyer in "Caution: Read the Docs for Claude 4.6's Effort Parameter"

mckennameyer — Tue, 10 Mar 2026 13:55:32 +0000

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

New comment by mckennameyer in "What to Put in a Claude Code Skill for Reviewing Your Team's Code"

mckennameyer — Thu, 05 Mar 2026 15:50:22 +0000

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?

New comment by mckennameyer in "Higher effort reduces deep research accuracy for Gemini Flash 3 and GPT-5"

mckennameyer — Fri, 13 Feb 2026 14:38:23 +0000

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)

New comment by mckennameyer in "How LLM agents solve the table merging problem"

mckennameyer — Thu, 22 Jan 2026 19:28:49 +0000

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

New comment by mckennameyer in "Show HN: Stockfisher –– our automated Warren Buffett"

mckennameyer — Thu, 13 Nov 2025 16:51:43 +0000

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.