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

What Claude Code chooses

amplifying.ai

Post reply on HN
Print view View original

61–70 of 266 posts

Re: What Claude Code chooses

#61

Post by hinkley »

dvt wrote: post #50
dataviz1000 wrote: post #39

I'm running a server on AWS with TimescaleDB on the disk because I don't need much. I figure I'll move it when the time comes. (edit: Claude Code is managing the AWS EC2 instance using AWS CLI.) Claude Code this morning was about to create an account with NeonDB and Fly.io (edit: it suggested as the plan to host on these where I would make the new accounts) although it has been very successful managing the AWS EC2 se…

> Claude Code likely is correct that I should start to use NeonDB and Fly.io which I have never used before and do not know much about I wouldn't be so sure about that. In my experience, agents consistently make awful architectural decisions. Both in code and beyond (even in contexts like: what should I cook for a dinner party?). They leak the most obvious "midwit senior engineer" decisions which I would strike down…

How do you make an LLM that’s was trained on average Internet code not end up as a midwit?

Mediocrity in, mediocrity out.

Re: What Claude Code chooses

#62

Post by hinkley »

isubkhankulov wrote: post #12
evdubs wrote: post #11

Earlier quoted context omitted.

You specify which software patents you want it to use?

Patterns?

Tha was my assumption as well.

I caught iOS trying to autocorrect something I wrote twice yesterday, and somehow before I hit submit it managed it a third time, and I had to edit it after, where it tried three more times to change it back.

Autocorrect won’t be happy until we all sound like idiots and I wonder if that’s part of how they plan to do away with us. Those hairless apes can’t even use their properly.

Re: What Claude Code chooses

#63

Post by re-thc »

wrs wrote: post #15

This is where LLM advertising will inevitably end up: completely invisible. It's the ultimate "influencer". Or not even advertising, just conflict of interest. A canary for this would be whether Gemini skews toward building stuff on GCP.

> A canary for this would be whether Gemini skews toward building stuff on GCP

Sure it doesn't prefer THE Borg?

Re: What Claude Code chooses

#64

Post by nhumrich »

ch4s3 wrote: post #52

It really disappointing to see it so strongly preferring Github Actions which is in my experience terrible. Almost everything about GHA pushes you in the direction of constantly blowing out the 10GB cache limit in an attempt to have CI not run for ages. I also feel like the standard cache action using git works poorly with any tools that use mtime on files to determine freshness. I guess at least Opus can help you mu…

It has one thing going for it: Setup.

And by setup I mean, integration and account creation. You don't have to do it. You already have a git repo, just add some yaml, and bobs your uncle.

Re: What Claude Code chooses

#65

Post by indymike »

layer8 wrote: post #23
wrs wrote: post #15

This is where LLM advertising will inevitably end up: completely invisible. It's the ultimate "influencer". Or not even advertising, just conflict of interest. A canary for this would be whether Gemini skews toward building stuff on GCP.

Advertisers will only pay if AI providers will provide them data on the equivalent of “ad impressions”. And unlabeled/non-evident advertisements are illegal in many (most?) countries.

> data on the equivalent of “ad impressions”.

1. They can skip impressions and go right to collect affiliate fees. 2. Yes, the ad has to be labeled or disclosed... but if some agent does it and no one sees it, is it really an ad.

So much to work out.

Re: What Claude Code chooses

#66

Post by jcims »

Interesting to me that Opus 4.6 was described as forward looking. I haven't *really* paid attention, but after using 4.5 heavily for a month, the first greenfield project I gave Opus 4.6 resulted in it doing a web search for latest and greatest in the domain as part of the planning phase. It was the first time I'd seen it, and it stuck out enough that I'm talking about it now.

Probably confirmation bias, but I'm generally of the opinion that the models are basically good enough now to do great things in the context of the right orchestration and division of effort. That's the hard part, which will be made less difficult as the models improve.

Re: What Claude Code chooses

#67

Post by singpolyma3 »

layer8 wrote: post #23
wrs wrote: post #15

This is where LLM advertising will inevitably end up: completely invisible. It's the ultimate "influencer". Or not even advertising, just conflict of interest. A canary for this would be whether Gemini skews toward building stuff on GCP.

Advertisers will only pay if AI providers will provide them data on the equivalent of “ad impressions”. And unlabeled/non-evident advertisements are illegal in many (most?) countries.

Maybe. Historically lots of ads had little to no stats and those ads were wildly more effective than anything we have today.

Re: What Claude Code chooses

#68

Post by ch4s3 »

nhumrich wrote: post #64
ch4s3 wrote: post #52

It really disappointing to see it so strongly preferring Github Actions which is in my experience terrible. Almost everything about GHA pushes you in the direction of constantly blowing out the 10GB cache limit in an attempt to have CI not run for ages. I also feel like the standard cache action using git works poorly with any tools that use mtime on files to determine freshness. I guess at least Opus can help you mu…

It has one thing going for it: Setup. And by setup I mean, integration and account creation. You don't have to do it. You already have a git repo, just add some yaml, and bobs your uncle.

It’s very Microsoft in that way.

Re: What Claude Code chooses

#69

Post by Clueed »

Really interesting. The crazy changes in opus 4.6 really make me think that Anthropic is doing library-level RL. I think that is also the way forward to have 'llm-native' frameworks as a way to not get stuck in current coding practices forever. Instead of learning python 3.15, one would license a proprietary model that has been trained on python 3.15 (and the migrations) and gain the ability to generate python 3.15 code.

Re: What Claude Code chooses

#70

Post by ipaddr »

hinkley wrote: post #61
dvt wrote: post #50

Earlier quoted context omitted.

> Claude Code likely is correct that I should start to use NeonDB and Fly.io which I have never used before and do not know much about I wouldn't be so sure about that. In my experience, agents consistently make awful architectural decisions. Both in code and beyond (even in contexts like: what should I cook for a dinner party?). They leak the most obvious "midwit senior engineer" decisions which I would strike down…

How do you make an LLM that’s was trained on average Internet code not end up as a midwit? Mediocrity in, mediocrity out.

Mediocrity means average.
Post reply on HN