Generally agree with the idea of calm technology, but I feel like inlay hints are a bad example. They actively give me anxiety because it makes the code feel harder to read, it takes my attention away from the code, and it feels more awkward to edit the text because you have these virtual characters getting in the way and having to re-render as you type, causing a shift in your cursor position. It's not at all calming for me, lol.
Beyond agentic coding
71–80 of 96 posts
Re: Beyond agentic coding
#72I did a bit of digging into why you think agentic coding is “not there yet”, and I think you are bashing a tool you have very little experience with and are using a bit wrongly. Nothing wrong with that, except that as opposed to any other tool that is out there, agentic coding is approached by smart senior engineers that would otherwise spend time reading documentation and understanding a new package/tool/framework b…
It doesn't look like you addressed issues raised in the article. E.g., see the "my experiences interviewing candidates" section where we can see this isn't just a problem of the author's (just one example in one section of an article that covers various things). I always wonder what the purpose of posting these generic, superficial defenses of a certain form of LLM-based coding is?
That was a different matter altogether. I agree though that I didn't touch on that.
My experience is different in that case, but it certainly depends on the type of technical challenge, the programming language, etc.
Candidates that perform better or worse exist with and without agentic coding tools. I've had positive and negative experience on both fronts, so I'd attribute the OP's experience to the N=1 problem, and perhaps to the model's jagged intelligence.
I work mostly in Typescript, and it's well known that models are particulary well versed in it. I know that other programming languages are less supported because the training data for them is lower, in which case models could be worse with them across the board (or some SOTA models could be better than others)
Re: Beyond agentic coding
#73I did a bit of digging into why you think agentic coding is “not there yet”, and I think you are bashing a tool you have very little experience with and are using a bit wrongly. Nothing wrong with that, except that as opposed to any other tool that is out there, agentic coding is approached by smart senior engineers that would otherwise spend time reading documentation and understanding a new package/tool/framework b…
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.
Re: Beyond agentic coding
#74I did a bit of digging into why you think agentic coding is “not there yet”, and I think you are bashing a tool you have very little experience with and are using a bit wrongly. Nothing wrong with that, except that as opposed to any other tool that is out there, agentic coding is approached by smart senior engineers that would otherwise spend time reading documentation and understanding a new package/tool/framework b…
VibeTFM
hmm didn't get the pun...Time to turn to chatGPT :))
Re: Beyond agentic coding
#75> I believe there is a lot of untapped potential in AI-assisted coding tools Yikes. By the way, the whole website is strange. Just the name alone "haskell for all". Many years ago when I tried to learn Haskell (and wrote some haskell code that worked but it was sooooo much harder when compared to ruby or python), one of the few things that appeared early on, aside from the monad barrier, was that many haskell people…
Her blog has lots of quality content that's been featured on HN several times - well before AI writing became a thing. Not that you should necessarily know that but just strong evidence that your intuitions here are way off on so many levels.
Your entire take is super strange and presumptive.
Re: Beyond agentic coding
#76> 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…
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 coverage) and it should save focus for review of the behavior changes.
The challenge is that it is not the same as just committing the hunks in different order. But maybe a skill with basic agent loop could work with capabilities of models nowadays.
Re: Beyond agentic coding
#77> 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…
I've been talking about having AI add comments to PRs to draw attention to things that should be given special attention since last May. I think most code review tools don't do this because A/B testing has shown people engage less/churn more with noisier review output.
Re: Beyond agentic coding
#78> I believe there is a lot of untapped potential in AI-assisted coding tools Yikes. By the way, the whole website is strange. Just the name alone "haskell for all". Many years ago when I tried to learn Haskell (and wrote some haskell code that worked but it was sooooo much harder when compared to ruby or python), one of the few things that appeared early on, aside from the monad barrier, was that many haskell people…
On the flip side, this finally reads again like something that is written by a human for a human, so I'm very glad to get this kind of content.
Re: Beyond agentic coding
#79“Facet-based project navigation You could browse a project by a tree of semantic facets. For example, if you were editing the Haskell implementation of Dhall the tree viewer might look like this prototype I hacked up2” ^ This is a genius idea - someone add this to claude
At work we use Clean Architecture which is incredibly hard to browse, even though I've been there for 6+ months now and know where everything is, I have to use so much working memory to gather together the files for a feature slice (endpoint, command, command handler, etc). I've thought for a while of building this exact thing as a vscode extension because of how utterly shit it is :D I really want the source code!
Author here: the source code is linked in the post but it can be easy to miss: https://github.com/Gabriella439/facet-navigator
It's very rough, but I plan on cleaning it up soon (the cluster labeler still needs a lot of work) and writing another post about it soon
Re: Beyond agentic coding
#80> 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…
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.