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

Beyond agentic coding

haskellforall.com

Post reply on HN
Print view View original

91–96 of 96 posts

Re: Beyond agentic coding

#91

Post by tptacek »

bitwize wrote: post #87
BitsAndObjects wrote: post #42

Earlier quoted context omitted.

You’ve just written the exact reason LeeteCode is widely mocked as an interview technique. They are not representative of most real world software, and engineers that train to solve them give a false impression of their ability to solve most other problems. I’ve interviewed hundreds of engineers for software and hardware roles. A good coding test is based on self-contained problems that the team actually encountered…

Leetcode's utility is not in showing you can solve real-world problems. It's used as a baseline to estimate how smart you are. Every shop prides itself on hiring smart people, and some only want the best of the best—your MIT and Stanford grads, etc. A smarter engineering workforce can not only solve the problems you have, they're better positioned to spot and avoid problems you haven't anticipated yet. Anyways, IQ te…

Without commenting on the racial biases of IQ tests (we probably directionally agree), the idea that IQ tests in employment are legally risky is an Internet myth. The companies that offer employment-screening general cognitive tests have logo crawls of giant companies that use them.

They're not unusual because they're legally risky; they're unusual because they don't work well.

Re: Beyond agentic coding

#92

Post by CactusBlue »

This feels like an opposite of my experience. I find just having a bunch of Claude Code terminals running in the background to be the most "ambient", while I find autocomplete/auto-navigate the likes of Copilot/Cursor to be so annoying that I don't use any AI autocomplete now. Regardless, I think there's still a lot of room for structured AI programming flows, especially regarding semantic search, code flow tracing and intelligent find and replace.

Re: Beyond agentic coding

#93

Post by jmalicki »

WilcoKruijer wrote: post #44

> You could take an editor session, a diff, or a pull request and automatically split it into a series of more focused commits that are easier for people to review. This is one of the cases where the AI can reduce human review labor I feel this should be a bigger focus than it is. All the AI code review start up are mostly doing “hands off” code review. It’s just an agent reviewing everything. Why not have an agent c…

That sounds like stacked changes (if you're not familiar think how lkml patches are like 0/8 1/8 etc where each is a standalone change that only depends on ones before), and I have been using agents create sets of stacked PRs when I have a big diff.

Instead of ordering of files, it creates an ordering of PRs where each has descriptions, independent CI, etc. and can be merged one at a time (perhaps at the small cost of the main branch having unused library functions until the final PR is merged)

Re: Beyond agentic coding

#94

Post by jmalicki »

WilcoKruijer wrote: post #80
kloud wrote: post #76

Earlier quoted context omitted.

Exactly this, existing code review tools became insufficient with the increase of volume of code, I would like to see more innovation here. One idea that comes to mind to make review easier would be to re-create commits following Kent Beck's SB Changes concept - splitting structure changes (tidying/refactoring) and behavior changes (features). The structure changes could then be quickly skimmed (especially with good…

I experimented with a command for atomic commits a while ago. It explicitly instructed the agent to review the diff and group related changes to produce a commit history where every HEAD state would work correctly. I tried to get it to use `git add -p`, but it never seemed to follow those instructions. Might be time for another go at this with a skill.

I have had success with having the skill create a new branch and moving pieces of code there, testing them after the move, then adding it.

So commit locally and have it recreate the commit as a sequence on another branch.

Re: Beyond agentic coding

#95

Post by pipejosh »

The part that worries me about agentic everything is the security model hasn't caught up. We're handing agents more and more access (shell, network, APIs, file systems) and the security story is still basically "the model probably won't do bad things." That's not how we secure anything else in computing. Principle of least privilege should apply to agents the same way it applies to services.

Re: Beyond agentic coding

#96

Post by burnerToBetOut »

Narciss wrote: post #73
zazibar wrote: post #57

Earlier quoted context omitted.

A "you're holding it wrong" with the implication that the author is a bad engineer as the cherry on top. Brilliant stuff.

Definitely didn't want to imply that the author is a bad engineer, quite the contrary he seems like a very good one. Apologies if it came across that way. Just that many brilliant engineers as themselves test agentic tools without the same level of thorough understanding that they give to other software engineering tools that they test out.

   > …I did a bit of digging…
I didn't do any digging.

   > …*he* seems like a very good one…
But I did some scrolling (to the bottom of the blog post). What would you bet that "Gabriella" is probably a she? ;)
Post reply on HN