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

191–200 of 257 posts

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

#191

Post by democracy »

groundzeros2015 wrote: post #95
kasey_junk wrote: post #92

Earlier quoted context omitted.

The person they are responding with dictated an authoritative framing that isn’t true. I know people have emotional responses to this, but if you think people aren’t effectively using agents to ship code in lots of domains, including existing legacy code bases, you are incorrect. Do we know exactly how to do that well, of course not, we still fruitlessly argue about how humans should write software. But there is a gr…

I think programming effectiveness is inherently tied to the useful life of software, and we will need to see that play out. This is not to suggest that AI tools do not have value but that “I just have agents writing code and it works great!” Has yet to hit its test.

Also people need to be more specific about technologies/tasks they do. Otherwise it's apples to oranges.

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

#192

Post by democracy »

dboreham wrote: post #105
groundzeros2015 wrote: post #68

Earlier quoted context omitted.

Why are you using experience and authoritative framing about a technology we’ve been using for less than 6 months?

If you hired a person six months ago and in that time they'd produced a ton of useful code for your product, wouldn't you say with authoritative framing that their hiring was a good decision?

Why is it always "tons of code"? Unless you are paid by the line of code writin "tons of code" makes no sense.

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

#193

Post by ChicagoDave »

lacoolj wrote: post #181
ChicagoDave wrote: post #179

I noticed this too, but I think there's a much bigger problem. The way Claude does research has dramatically changed for the worse. Instead of piping through code logically, it's now spawning dozens of completely unrelated research threads to look at simple problems. I let it spin for over 30 minutes last night before realizing it was just "lost". I have since been looking for these moments and killing it immediately…

Was this from a specific model or all of them?

I mostly run on 4.6.

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

#194

Post by otabdeveloper4 »

JPKab wrote: post #57
g947o wrote: post #27

Earlier quoted context omitted.

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.

I work at a company with approximately $1 million in revenue per engineer and multiple 10+ year old codebases. We use agents very aggressively, combined with beads, tons of tests, etc. You treat them like any developer, and review the code in PRs, provide feedback, have the agents act, and merge when it's good. We have gained tremendous velocity and have been able to tackle far more out of the backlog that we'd been…

> We have gained tremendous velocity and have been able to tackle far more out of the backlog that we'd been forced to keep in the icebox before.

Source? Proofs? It's not the first, second or even third round on this rodeo.

In other words, notto disu shittu agen.

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

#195

Post by the_harpia_io »

hippo22 wrote: post #161
the_harpia_io wrote: post #13

[flagged]

You look at what Claude’s doing to make sure it doesn’t go off the rails? Personally, I either move on to another ask in parallel or just read my phone. Trying to catch things by manually looking at its output doesn’t seem like a recipe for success.

[flagged]

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

#196

Post by democracy »

thesz wrote: post #160
adastra22 wrote: post #147

Earlier quoted context omitted.

You can ask Opus 4.6 to do a task and leave it running for 30min or more to attempt one-shooting it. Imagine doing this with three agents in parallel in three separate work trees. Then spin up a new agent to decide which approach of the three is best on the merits. Repeat this analysis in fresh contexts and sample until there is clear consensus on one. If no consensus after N runs, reframe to provide directions for a…

> Then spin up a new agent to decide which approach of the three is best on the merits. Repeat this analysis in fresh contexts and sample until there is clear consensus on one. If there are several agents doing analysis of solutions, how do you define a consensus? Should it be unanimous or above some threshold? Are agents scores soft or hard? How threshold is defined if scores are soft? There is a whole lot of scienc…

It was a scene from a sci-fi movie (i mean Claude demo to CTOs)

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

#197

Post by otabdeveloper4 »

JeremyNT wrote: post #172
nicoburns wrote: post #170

Earlier quoted context omitted.

> You can get extremely good results assuming your spec is actually correct Is it ever the case that the spec is entirely correct (and without underspecified parts)? I thought the reason we write code is because it's much easier to express a spec as code than it is to get a similar level of precision in prose.

I think this is basically the only SWE-type job that exists beyond the (relatively near) future: finding the right spec and feeding it to the bots. And in this way I think even complete laypeople will be able to create software using the bots, but you'd still want somebody with a deeper understanding in this role for serious projects. The bots even now can really help you identify technical problems / mistakes / gaps…

> finding the right spec and feeding it to the bots

Also known as "compiling source code".

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

#198

Post by the_harpia_io »

socalgal2 wrote: post #169
the_harpia_io wrote: post #13

[flagged]

My first thought is, for the specific problem you brought up, you find out which files were touched by your version control system, not the AI's logs. I have to do this for myself even without AI.

[flagged]

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

#199

Post by mwigdahl »

yyhhsj0521 wrote: post #167
data-ottawa wrote: post #138

Earlier quoted context omitted.

Check your model thinking effort. You have to go into /models then use the left/right arrow keys to change it. It’s a horrible UI design and I had no idea mine was set to high. You can only tell by the dim text at the bottom and the 3 potentially highlighted bars. On high It would think for 30+ minutes, make a plan, then when I started the plan it would either compact and reread all my files, or start fresh and read…

You can press Ctrl-P instead of typing /model too

Doesn't work on Windows in a VS Code terminal window, unfortunately.

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

#200

Post by buschleague »

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…

We run agent teams (Navigator/Driver/Reviewer roles) on a 71K-line codebase. The trust problem is solved by not trusting the agents at all. You enforce externally. Python gates that block task completion until tests pass, acceptance criteria are verified, and architecture limits are met. The agents can't bypass enforcement mechanisms they can't touch. It's not about better prompts or more capable models. It's about infrastructure that makes "going off the rails" structurally impossible.
Post reply on HN