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

Claude Code does our releases now

aluxian.com

Post reply on HN
Print view View original

71–80 of 81 posts

Re: Claude Code does our releases now

#71

Post by Mashimo »

friendzis wrote: post #68
Mashimo wrote: post #37

Earlier quoted context omitted.

Ignoring the Claude AI release, why does releasing 1 - 3 per week implies low confidence and quality issues?

It means you release whatever you have first thing and then release a bunch of patch releases on top as the QA (outsourced on users, probably) results come back. Sans security patches, why are your features not sized to roughly a sprint? What do you manage to prepare, build and validate in a day or two? To me release cadence less than every few weeks screams "whatever landed in master is good to go" and is a sign of…

Maybe they don't do sprints.

Yeah, could be user feedback. And if it's a public beta release why not?

3 devs working for 5 days on each their feature means 3 releases per week.

For the last 10+ years I have been working on the same project with 2 releases per year, so what do I know. But I have used projects with quick release cycles that work very closely with the community. Push new beta, feedback on discord. Was also fine from my (limited) perspective.

Re: Claude Code does our releases now

#72

Post by alanfranz »

tarsinge wrote: post #70
SCdF wrote: post #50

Is this not a bash script, but run through a "maybe it won't work this time" randomizer? Sometimes I feel like I live on another planet. Wouldn't you at least get Claude to write the bash script, confirm it works how you like, then run that? Why get an LLM to guess how to do it each and every time? At least they are still manually approving, which the title made sound like something they'd move on from.

You are not the target. This is marketing content for their tool, aimed at semi technical people with buying power but not actual developers.

Oh, it is now flagged. I admit I didn't notice that was marketing content, I thought it was a genuine blogpost.

Re: Claude Code does our releases now

#73

Post by seunosewa »

apwell23 wrote: post #59
otabdeveloper4 wrote: post #28

Earlier quoted context omitted.

> ...and which can say knowledgeable things at times while having no idea on what they are doing This has been a thing forever, before AI. Lots of "programmers" at BigCorp have hacked the system and they know how to say the right words relevant to BigCorp's tech stack. Knowing how to actually program is entirely optional. (You can just copy-paste boilerplate from BigCorp's monorepo, writing boilerplate will be your d…

yea for sure they hacked the system for promotions but they weren't checking in AI slop for rest of us to deal with.

They were checking in buggy spaghetti code though.

Re: Claude Code does our releases now

#74

Post by rbinv »

AStonesThrow wrote: post #65
9dev wrote: post #64

Earlier quoted context omitted.

That’s an entirely different issue: people maintain a blog to improve their hireability, and that entails blogging about things that may not always be brilliant insights. It’s not this person's fault that that’s the state of tech hiring however. Don’t hate the player, hate the game.

Blogging is actually a good way for professionals to earn CEUs to maintain certifications. Chances are, if you’re reading low-effort blog posts that are consistently in certain knowledge domains, they’re intending to apply for CEUs at renewal time.

I had no idea people could earn Continuing Education Units for blogging, but it's true: https://www.comptia.org/continuing-education/choose/renewing...

Re: Claude Code does our releases now

#75

Post by sakesun »

Deestan wrote: post #40
sakesun wrote: post #23

Letting AI control software releases might seem risky, but it may not be as problematic as it sounds—especially if you also use AI to handle issue support. :)

Make sure you have AI customers also. Prompt them to love your product and you're good.

Lot of downvote at my message. You are probably the only person who understand my joke :)

Re: Claude Code does our releases now

#77

Post by AStonesThrow »

DonHopkins wrote: post #55
kissgyorgy wrote: post #44

Earlier quoted context omitted.

It's a well known prompt trick to get better results. Scott Hanselman explained it like "You get to the nice corner of the internet."

But what if the LLM senses you're using the word "please" in the passive aggressive, patronizing, ironic sense? ;)

https://en.wikipedia.org/wiki/INTERCAL

[The keyword "PLEASE"] provides two reasons for the program's rejection by the compiler: if "PLEASE" does not appear often enough, the program is considered insufficiently polite, and the error message says this; if it appears too often, the program could be rejected as excessively polite. Although this feature existed in the original INTERCAL compiler, it was undocumented.

Re: Claude Code does our releases now

#78

Post by shermantanktop »

forkerenok wrote: post #32
shermantanktop wrote: post #27

Earlier quoted context omitted.

What is the deterministic alternative you suggest? I’m not endorsing this release practice in particular, it scares me. But I have been involved in a lot of automation projects where perfection was the initial goal, and then abandoned because it was obvious that non-automated work was so imperfect. Human error is a fact of life.

The sibling comment from M4v3R covered this well.

Did it? I didn’t see a claim that doing this work manually had a zero error rate.

Again, I would probably not do this. But let’s not pretend that non-AI release processes prevent all issues. We’re really talking different kinds of errors, and the ai driven ones tend to be obviously wrong. At least right now.

Re: Claude Code does our releases now

#79

Post by mchonedev »

NekkoDroid wrote: post #63
alanfranz wrote: post #54

Earlier quoted context omitted.

We're moving fast from "we do this with AI because it's useful" to "we do this with AI because it's cool despite the fact that it's slower, more expensive, and non-deterministic" It's like the "we made over our product in order to use technology X because it's cool and modern" that we've seen multiple times with node, go, rust, k8s, blockchain, .

> non-deterministic Counterpoint: temperature = 0 /s On a more serious note: I personally only found LLMs really interesting to double check my code if there might be something I overlooked in the general implementation (a different approach or so), never really for it to write code directly for me. I feel like this is just becoming less and less common nowadays and it kinda makes me worry for the quality of code tha…

I know you used the /s but it's quite common that 0 temperature is believed to be deterministic. For others coming across this thread, it's not deterministic, it is simply less likely to return different tokens (it still absolutely will)

Re: Claude Code does our releases now

#80

Post by lostmsu »

mchonedev wrote: post #79
NekkoDroid wrote: post #63

Earlier quoted context omitted.

> non-deterministic Counterpoint: temperature = 0 /s On a more serious note: I personally only found LLMs really interesting to double check my code if there might be something I overlooked in the general implementation (a different approach or so), never really for it to write code directly for me. I feel like this is just becoming less and less common nowadays and it kinda makes me worry for the quality of code tha…

I know you used the /s but it's quite common that 0 temperature is believed to be deterministic. For others coming across this thread, it's not deterministic, it is simply less likely to return different tokens (it still absolutely will)

AFAIK it shouldn't.
Post reply on HN