Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Anthropic tries to hide Claude's AI actions. Devs hate it

theregister.com

Post reply on HN
Print view View original

71–80 of 257 posts

Re: Anthropic tries to hide Claude's AI actions. Devs hate it

#71

Post by simianwords »

rco8786 wrote: post #22
the_harpia_io wrote: post #13

[flagged]

> it's about catching when it goes off the rails before it makes a mess The latest "meta" in AI programming appears to be agent teams (or swarms or clusters or whatever) that are designed to run for long periods of time autonomously. Through that lens, these changes make more sense. They're not designing UX for a human sitting there watching the agent work. They're designing for horizontally scaling agents that work…

>The latest "meta" in AI programming appears to be agent teams (or swarms or clusters or whatever) that are designed to run for long periods of time autonomously.

more reason to catch them otherwise we have to wait a longer time. in fact hiding is more correct if the AI was less autonomous right?

Re: Anthropic tries to hide Claude's AI actions. Devs hate it

#72

Post by rco8786 »

pzs wrote: post #65
rco8786 wrote: post #22

Earlier quoted context omitted.

> it's about catching when it goes off the rails before it makes a mess The latest "meta" in AI programming appears to be agent teams (or swarms or clusters or whatever) that are designed to run for long periods of time autonomously. Through that lens, these changes make more sense. They're not designing UX for a human sitting there watching the agent work. They're designing for horizontally scaling agents that work…

Related question: how do we resolve the problem that we sign a blank cheque for the autonomous agents to use however many tokens they deem necessary to respond to your request? The analogy from team management: you don't just ask someone in your team to look into something only to realize three weeks later (in the absence of any updates) that they got nowhere with a problem that you expected to take less than a day t…

We'll have to solve for that sometime soon-ish I think. Claude Code has at least some sort of token estimation built-in to it now. I asked it to kick off a large agent team (~100 agents) to rewrite a bunch of SQL queries, one per agent. It did the first 10 or so, then reported back that it would cost too much to do it this way...so it "took the reins" without my permission and tried to convert each query using only the main agent and abandoned the teams. The results were bad.

But in any case, we're definitely coming up on the need for that.

Re: Anthropic tries to hide Claude's AI actions. Devs hate it

#73

Post by groundzeros2015 »

adastra22 wrote: post #59
rco8786 wrote: post #38

Earlier quoted context omitted.

Totally agreed. Those assumptions often compound as well. So the AI makes one wrong decision early in the process and it affects N downstream assumptions. When they finally finish their process they've built the wrong thing. This happens with one process running. Even on latest Opus models I have to babysit and correct and redirect claude code constantly. There's zero chance that 5 claude codes running for hours with…

Actually it works the other way. With multiple agents they can often correct each others mistaken assumptions. Part of the value of this approach is precisely that you do get better results with fewer hallucinated assumptions. Still makes this change from Anthropic stupid.

Nonsense. If you have 16 binary decisions that’s 64k possible paths.

Re: Anthropic tries to hide Claude's AI actions. Devs hate it

#74

Post by slices »

powera wrote: post #51

Between this and 4.6's tendency to do so much more "exploratory" work, I am back to using ChatGPT Codex for some tasks. Two months ago, Claude was great for "here is a specific task I want you to do to this file". Today, they seem to be pivoting towards "I don't know how to code but want this feature" usage. Which might be a good product decision, but makes it worse as a substitute for writing the code myself.

Have you played with the effort setting? I'm finding medium effort on 4.6 to give more satisfactory results for that kind of thing.

Re: Anthropic tries to hide Claude's AI actions. Devs hate it

#76

Post by parhamn »

"Hiding" is doing some heavy lifting here. You can run --json and see everything pretty much (besides the system prompt and tool descriptions)....

I love the terminal more than the next guy but at some point it feels like you're looking at production nginx logs, just a useless stream of info that is very difficult to parse.

I vibe coded my own ADE for this called OpenADE (https://github.com/bearlyai/openade) it uses the native harnesses, has nice UIs and even comes with things like letting Claude and Codex work together on plans. Still very beta but has been my daily driver for a few weeks now.

Re: Anthropic tries to hide Claude's AI actions. Devs hate it

#77

Post by pjc50 »

g947o wrote: post #27
rco8786 wrote: post #22

Earlier quoted context omitted.

> it's about catching when it goes off the rails before it makes a mess The latest "meta" in AI programming appears to be agent teams (or swarms or clusters or whatever) that are designed to run for long periods of time autonomously. Through that lens, these changes make more sense. They're not designing UX for a human sitting there watching the agent work. They're designing for horizontally scaling agents that work…

None of those wild experiments are running on a "real", existing codebase that is more than 6 months old. The thing they don't talk about is that nobody outside these AI companies wants to vibe code with a 10 year old codebase with 2000 enterprise customers. As you as you start to work with a codebase that you care about and need to seriously maintain, you'll see what a mess these agents make.

Also anything that doesn't look like a SaaS app does very badly. We had an internal trial at embedded firmware and concluded the results were unsalvageably bad. It doesn't help that the embedded environment is very unfriendly to standard testing techniques, as well.

Re: Anthropic tries to hide Claude's AI actions. Devs hate it

#78

Post by pjc50 »

pzs wrote: post #65
rco8786 wrote: post #22

Earlier quoted context omitted.

> it's about catching when it goes off the rails before it makes a mess The latest "meta" in AI programming appears to be agent teams (or swarms or clusters or whatever) that are designed to run for long periods of time autonomously. Through that lens, these changes make more sense. They're not designing UX for a human sitting there watching the agent work. They're designing for horizontally scaling agents that work…

Related question: how do we resolve the problem that we sign a blank cheque for the autonomous agents to use however many tokens they deem necessary to respond to your request? The analogy from team management: you don't just ask someone in your team to look into something only to realize three weeks later (in the absence of any updates) that they got nowhere with a problem that you expected to take less than a day t…

> blank cheque

The Bing AI summary tells me that AI companies invested $202.3 billion in AI last year. Users are going to have to pay that back at some point. This is going to be even worse as a cost control situation than AWS.

Re: Anthropic tries to hide Claude's AI actions. Devs hate it

#79

Post by lkbm »

xg15 wrote: post #8

> Cherny responded to the feedback by making changes. "We have repurposed the existing verbose mode setting for this," he said, so that it "shows file paths for read/searches. Does not show full thinking, hook output, or subagent output (coming in tomorrow's release)." How to comply with a demand to show more information by showing less information.

They changed it from showing just number of files read to showing the actual paths/filenames. IE, it shows more information.

EDIT: Ah, looks like verbose mode might show less than it used to, and you need to use a new mode (^o) to show very verbose.

Post reply on HN