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

271–280 of 284 posts

Re: Using LLMs at Oxide

#271

Post by bcantrill »

dgroshev wrote: post #269
bcantrill wrote: post #267

Earlier quoted context omitted.

I understand your disappointment; we are very explicit about why we provide so little feedback.[0] I disagree that it's indecent; to the contrary, we allow anyone to shoot their shot, with the guarantee that they will be thoughtfully considered. [0] https://rfd.shared.oxide.computer/rfd/0003#_rejection_of_non...

Indeed, I understand your reasoning, you talk about that in the podcast in the RFD. This is why I wasn't talking about the lack of feedback, but the lack of human interaction. While there is nothing constructive to be done about the disappointment of rejection, this part is very much in your power to change, and that's why I think it's constructive feedback and not just venting. That said, the RFD does say this: > Ca…

Please DM me and I'll let you know if there's constructive feedback to be provided.

Re: Using LLMs at Oxide

#272

Post by bcantrill »

bgwalter wrote: post #235
crabmusket wrote: post #71

Earlier quoted context omitted.

For those interested, here's a take from Bryan after that incident https://bcantrill.dtrace.org/2013/11/30/the-power-of-a-prono...

Also for those interested, here is Bryan's take on criticism of Sun: https://landley.net/history/mirror/linux/kissedagirl.html He wasn't fired or canceled. It is great to see Gen-Xers and Boomers having all the fun in the 1980s and 1990s and then going all prissy on younger people in the 2010s and trying to ruin their careers.

For those looking for context, this is a regrettable response of mine from nearly three decades ago, resurrected because people disagreed with the way my handling bad community behavior well over a decade ago. And for whatever it's worth, my explanation of all of this from a decade ago still stands[0].

[0] https://news.ycombinator.com/item?id=9041086

Re: Using LLMs at Oxide

#273

Post by zackerydev »

ghurtado wrote: post #100
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.

> glory that was Adobe Dreamweaver Dreamweaver was to web development what ... I just sat here for 5 minutes and I wasn't able to finish that sentence. So I think that's a statement in itself.

That was my point! Dreamweaver to web dev felt like what LLM's are to many disciplines!

Re: Using LLMs at Oxide

#274

Post by cobertos »

bcantrill wrote: post #230
cobertos wrote: post #96

> LLMs are especially good at evaluating documents to assess the degree that an LLM assisted their creation!) That's a bold claim. Do they have data to back this up? I'd only have confidence to say this after testing this against multiple LLM outputs, but does this really work for, e.g. the em dash leaderboard of HN or people who tell an LLM to not do these 10 LLM-y writing cliches? I would need to see their reasonin…

I am really surprised that people are surprised by this, and honestly the reference was so casual in the RFD because it's probably the way that I use LLMs the most (so very much coming from my own personal experience). I will add a footnote to the RFD to explain this, but just for everyone's benefit here: at Oxide, we have a very writing-intensive hiring process.[0] Unsurprisingly, over the last six months, we have s…

I still don't quite get this reasoning. A statistical model for detecting a category (like is this written hiring material LLM generated or not, is this email spam or not, etc) is most metricized by its false positive and false negative rate. But it doesn't sound like anyone measures this, it just gets applied after a couple times of "huh, that worked" and we move on. There's a big difference between a model that performs successfully 70% of the time vs one that performs 99% but I'm not sure we can say which this is?

Maybe if LLMs were aligned for this specific task it'd make more sense? But they're not. Their alignment tunes them to provide statistically helpful responses for a wide variety of things. They prefer positive responses to negative ones and are not tuned directly as a detection tool for arbitrary categorization. And maybe they do work well, but maybe it's only a specific version of a specific model against other specific models hiring material outputs? There's too many confounding things here to not have to study this in a rigorous way to come to the conclusion that felt... not carefully considered.

Maybe you have considered this more than I know. It sounds like you work a lot with this data. But the off-handedness set off my skepticism.

Re: Using LLMs at Oxide

#275

Post by uhfraid »

discreteevent wrote: post #146
keyle wrote: post #44

Earlier quoted context omitted.

> That junior engineer possibly hasn't programmed without the tantalizing, even desperately tempting option to be assisted by an LLM. This gives me somewhat of a knee jerk reaction. When I started programming professionally in the 90s, the internet came of age and I remember being told "in my days, we had books and we remembered things" which of course is hilarious because today you can't possibly retain ALL the know…

> "in my days, we had books and we remembered things" which of course is hilarious because today you can't possibly retain ALL the knowledge needed to be software engineer Reading books was never about knowledge. It was about knowhow. You didn't need to read all the books. Just some. I don't know how many developers I met who would keep asking questions that would be obvious to anyone who had read the book. They neve…

Which books? Did they not read them?

Re: Using LLMs at Oxide

#276

Post by adastra22 »

vegardx wrote: post #237
adastra22 wrote: post #162

Earlier quoted context omitted.

With many asterix and footnotes. One of which being that if it literally output the exact code, of course that would be copyright infringement. Something that greatly resembled but with minor changes would be a gray area. Those kinds of cases, although they do happen, are exceptional. In a typical output that doesn't not line-for-line resemble a single training input, it is considered a new, but non-copyrightable wor…

(I'm not a lawyer) You should be careful about speaking in absolute terms when talking about copyright. There is nothing that prevents multiple people from owning copyright to identical works. This is also why copyright infringement is such a mess to litigate. I'd also be interested in knowing why you think code generated by LLMs can't be copyrighted. That's quite a statement. There's also the problem with copyright…

It is the official stance of the US copyright office.

It was upheld by Thaler v. Perlmutter.

Bartz v. Anthropic and Kadrey v. Meta confirmed with similar rulings.

Re: Using LLMs at Oxide

#277

Post by cdaringe »

csb6 wrote: post #102

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.

Perhaps, given the target audience and the state of the world, “it goes without saying” applies, or is wrapped up implicitly already thru the mentioned checks and balances (human firmly in the loop, etc etc)

Re: Using LLMs at Oxide

#278

Post by jph00 »

_zagj wrote: post #50
bryancoxwell wrote: post #7

Find it interesting that the section about LLM’s tells when using it for writing is absolutely littered with emdashes

There was a comment recently by HN's most enthusiastic LLM cheerleader, Simon Willison, that I stopped reading almost immediately (before seeing who posted it), because it exuded the slop stench of an LLM: https://news.ycombinator.com/item?id=46011877 However, I was surprised to see that when someone (not me) accused him of using an LLM to write his comment, he flatly denied it: https://news.ycombinator.com/item?id=4…

It reads exactly like all his writing over many years afaict. Which is to say - it reads well. Just because someone is clear, thoughtful, and thorough, does not make them an AI. AI writing is actually quite different to this.

Re: Using LLMs at Oxide

#279

Post by dcre »

batney wrote: post #198
cvcderringer wrote: post #193

I had trouble getting past the Early Modern English tinge of the language used in this. It’s fun, but it distracts from the comprehension in attempt to just sound epic. It’s fine if you’re writing literature, but it comes off sounding uppity in a practical doc for devs. Writing is not just about conveying something in a mood you wish to set. Study how Richard Feynman and Warren Buffett communicated to their audiences…

Here it is, rewritten in accessible English: Using Large Language Models (LLMs) at Oxide This document explains how we should think about using LLMs (like ChatGPT or similar tools) at Oxide. What are LLMs? LLMs are very advanced computer programs that can understand and generate text. They've become a big deal in the last five years and can change how we work. But, like any powerful tool, they have good and bad sides…

Thanks, this will be perfect for the team of 6 year olds that work for me.

Re: Using LLMs at Oxide

#280

Post by jstrebel »

govping wrote: post #184
thundergolfer wrote: post #4

A measured, comprehensive, and sensible take. Not surprising from Bryan. This was a nice line: > it’s just embarrassing — it’s as if the writer is walking around with their intellectual fly open. I think Oxide didn't include this in the RFD because they exclusively hire senior engineers, but in an organization that contains junior engineers I'd add something specific to help junior engineers understand how they shoul…

The craft vs practical tension with LLMs is interesting. We've found LLMs excel when there's a clear validation mechanism - for security research, the POC either works or it doesn't. The LLM can iterate rapidly because success is unambiguous. Where it struggles: problems requiring taste or judgment without clear right answers. The LLM wants to satisfy you, which works great for 'make this exploit work' but less great…

I am certain that LLMs can help you with judgment calls as well. I spent the last month tinkering with spec-driven development of a new Web app and I must say, the LLM was very helpful in identifying design issues in my requirements document and actively suggested sensible improvements. I did not agree to all of them, but the conversation around high-level technical design decisions was very interesting and fruitful (e.g. cache use, architectural patterns, trade-offs between speed and higher level of abstraction).
Post reply on HN