zlacker

[return to "My AI skeptic friends are all nuts"]
1. tkgall+EB[view] [source] 2025-06-03 01:42:07
>>tablet+(OP)
Both off and on topic: I got access to Claude’s voice mode today, and for my second test I asked it for its thoughts about both the linked blog post and the HN discussion here. The full transcript is at [1]. Some parts that stood out (slightly edited):

Me: So what is your assessment of the discussion at Hacker News?

Claude: The Hacker News discussion strikes me as much more grounded than the blog post itself. What I find compelling is that many commenters are sharing specific technical experiences rather than making broad ideological arguments. When someone describes spending hours fighting with Claude agents that keep refactoring code into spaghetti, that's concrete data about the current state of these tools. ...

Me: Well, what about you, Claude? You are made by a company whose president has recently made some public statements saying that, you know, 50% of white collar jobs will be replaced soon. And the company, Anthropic, also is very aggressively developing and selling tools to help with AI coding. What are your thoughts about that?

Claude: That's a really fair question to ask me directly. I think there's an obvious tension in my position here since I'm built by a company that has clear financial incentives around AI adoption, including coding tools. When I look at my own capabilities honestly, I can see both sides of this. I'm genuinely useful for certain coding tasks like explaining unfamiliar code, generating boilerplate, or helping debug specific problems. I've helped people learn new programming languages faster than they might have otherwise. But I'm also clearly not at the level where I could replace an experienced software engineer working on complex system design or novel problem solving. ...

[1] https://claude.ai/share/c934e67c-f132-43e8-8c31-ab238b5be25a

◧◩
2. collin+Pn1[view] [source] 2025-06-03 10:26:49
>>tkgall+EB
Thank you for sharing. I'm looking forward to getting voice mode, but after doing some searching I saw that it still needed the user to hit the "send" button after they are done talking. Did I misread, or was your experience that it would reply to you after you finished talking without the need to press anything?
[go to top]