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

Using LLMs at Oxide

rfd.shared.oxide.computer

Post reply on HN
Print view View original

101–110 of 284 posts

Re: Using LLMs at Oxide

#101

Post by ghurtado »

christophilus wrote: post #84
frankest wrote: post #74

Earlier quoted context omitted.

DreamWeaver absolutely destroyed the code with all kinds of tags and unnecessary stuff. Especially if you used the visual editor. It was fun for brainstorming but plain notepad with clean understandable code was far far better (and with the browser compatibility issues the only option if you were going to production).

After 25 or so years doing this, I think there are two kinds of developers: craftsmen and practical “does it get the job done” types. I’m the former. The latter seem to be what makes the world go round.

If you've been doing it for that long (about as long as I have), then surely you remember all the times you had to clean up after the "git 'er done" types.

I'm not saying they don't have their place, but without us they would still be making the world go round. Only backwards.

Re: Using LLMs at Oxide

#102

Post by csb6 »

Strange to see no mention of potential copyright violations found in LLM-generated code (e.g. LLMs reproducing code from Github verbatim without respecting the license). I would think that would be a pretty important consideration for any software development company, especially one that produces so much free software.

Re: Using LLMs at Oxide

#103

Post by IgorPartola »

mcqueenjordan wrote: post #28

As usual with Oxide's RFDs, I found myself vigorously head-nodding while reading. Somewhat rarely, I found a part that I found myself disagreeing with: > Unlike prose, however (which really should be handed in a polished form to an LLM to maximize the LLM’s efficacy), LLMs can be quite effective writing code de novo. Don't the same arguments against using LLMs to write one's prose also apply to code? Was this structu…

My suspicion is that this is a form of the paradox where you can recognize that the news being reported is wrong when it is on a subject in which you are an expert but then you move onto the next article on a different subject and your trust resumes.

Basically if you are a software engineer you can very easily judge quality of code. But if you aren’t a writer then maybe it is hard for you to judge the quality of a piece of prose.

Re: Using LLMs at Oxide

#104

Post by zeroonetwothree »

Jaygles wrote: post #79
ryandrake wrote: post #62

Earlier quoted context omitted.

I've found that your step 6 takes the vast majority of the time I spend programming with LLMs. Like 10X+ the combined total of time steps 1-5 take. And that's if the code the LLM produced actually works . If it doesn't work (which happens quite often), then even more handholding and corrections are needed. It's really a grind. I'm still not sure whether I am net saving time using these tools. I always wonder about th…

I exclusively use the autocomplete in cursor. I hate reviewing huge chunks of llm code at one time. With the autocomplete, I’m in full control of the larger design and am able to quickly review each piece of llm code. Very often it generates what I was going to type myself. Anything that involves math or complicated conditions I take extra time on. I feel I’m getting code written 2 to 3 times faster this way while ma…

Maybe it subjectively feels like 2-3x faster but in studies that measure it we tend to see smaller improvements like in the range of 20-30% faster. It could be that you are an outlier, of course.

Re: Using LLMs at Oxide

#105

Post by zeroonetwothree »

tikhonj wrote: post #99
john01dav wrote: post #11

> it is presumed that of the reader and the writer, it is the writer that has undertaken the greater intellectual exertion. (That is, it is more work to write than to read!) This applies to natural language, but, interestingly, the opposite is true of code (in my experience and that of other people that I've discussed it with).

That's because embarrassingly bad writing is useless, while embarrassingly bad code can still make the computer do (roughly) the right thing and lets you tick off a Jira ticket. So we end up having way more room for awful code than for awful prose. Reading good code can be a better way to learn about something than reading prose. Writing code like that takes some real skill and insight, just like writing clear explan…

Some writing is functional, e.g. a letter notifying someone of some information. For that type of writing even bad quality can achieve its purpose. Indeed probably the majority of words written are for functional reasons.

Re: Using LLMs at Oxide

#106

Post by AlexCoventry »

sudomateo wrote: post #94
AlexCoventry wrote: post #56

I wonder if they would be willing to publish the "LLMs at Oxide" advice, linked in the OP [1], but currently publicly inaccessible. [1] https://github.com/oxidecomputer/meta/tree/master/engineerin...

Disclaimer: Oxide employee here. To be honest there's really no secret sauce in there. It's primarily how to get started with agents, when to abandon your context and start anew, and advice on models, monitoring cost, and prompting. This is not to diminish the value of the information as it's good information written by great colleagues. I just wanted to note that most of the information can be obtained from the offi…

Thanks.

Re: Using LLMs at Oxide

#107

Post by diamond559 »

minimaxir wrote: post #39
joshka wrote: post #37

Earlier quoted context omitted.

Depends on what your prose is for. If it's for documentation, then prose which matches the expected tone and form of other similar docs would be clichéd in this perspective. I think this is a really good use of LLMs - making docs consistent across a large library / codebase.

I have been testing agentic coding with Claude 4.5 Opus and the problem is that it's too good at documentation and test cases. It's thorough in a way that it goes out of scope, so I have to edit it down to increase the signal-to-noise.

If the goal is to document the code and it gets sidetracked and focuses on only certain parts it failed the test. It just further proves llm's are incapable of grasping meaning and context.

Re: Using LLMs at Oxide

#108

Post by mythrwy »

ryandrake wrote: post #62
john01dav wrote: post #20

> Wherever LLM-generated code is used, it becomes the responsibility of the engineer. As part of this process of taking responsibility, self-review becomes essential: LLM-generated code should not be reviewed by others if the responsible engineer has not themselves reviewed it. Moreover, once in the loop of peer review, generation should more or less be removed: if code review comments are addressed by wholesale re-g…

I've found that your step 6 takes the vast majority of the time I spend programming with LLMs. Like 10X+ the combined total of time steps 1-5 take. And that's if the code the LLM produced actually works . If it doesn't work (which happens quite often), then even more handholding and corrections are needed. It's really a grind. I'm still not sure whether I am net saving time using these tools. I always wonder about th…

If it's stuff I have have been doing for years and isn't terribly complex I've found its generally quick to skim review. I don't need to read every line I can glance at it, know it's a loop and why, a function call or whatever. If I see something unusual I take that as an opportunity to learn.

I've seen LLMs write some really bad code a few times lately it seems almost worse than what they were doing 6 or 8 months ago. Could be my imagination but it seems that way.

Re: Using LLMs at Oxide

#109

Post by sunshowers »

bgwalter wrote: post #32

Cantrill jumps on every bandwagon. When he assisted in cancelling a Node developer (not a native English speaker) over pronouns he was following the Zeitgeist, now "Broadly speaking, LLM use is encouraged at Oxide." He is a long way from Sun.

I didn't know about that incident before starting at Oxide, but if I'd known about it, it absolutely would have attracted me. I've written a large amount of technical content and not once in over a decade have I needed to use he/him pronouns in it. Bryan was 100% correct.

Re: Using LLMs at Oxide

#110

Post by BobbyTables2 »

frankest wrote: post #74
zackerydev wrote: post #27

Earlier quoted context omitted.

I remember in the very first class I ever took on Web Design the teacher spent an entire semester teaching "first principles" of HTML, CSS and JavaScript by writing it in Notepad. It was only then did she introduce us to the glory that was Adobe Dreamweaver, which (obviously) increased our productivity tenfold.

DreamWeaver absolutely destroyed the code with all kinds of tags and unnecessary stuff. Especially if you used the visual editor. It was fun for brainstorming but plain notepad with clean understandable code was far far better (and with the browser compatibility issues the only option if you were going to production).

MS FrontPage also went out of its way to do the same.
Post reply on HN