Everything around LLMs is still magical and wishful thinking • Hacker News Board

Re: Everything around LLMs is still magical and wishful thinking

#91

Post by CharlesW » Fri, Jul 04, 2025, 10:17 PM UTC

0x696C6961 wrote: post #50

hotpotat wrote: post #30

I have to say I’m in the exact camp the author is complaining about. I’ve shipped non trivial greenfield products which I started back when it was only ChatGPT and it was shitty. I started using Claude with copying and pasting back and forth between the web chat and XCode. Then I discovered Cursor. It left me with a lot of annoying build errors, but my productivity was still at least 3x. Now that agents are better an…

I find that the code quality LLMs output is pretty bad. I end up going through so many iterations that it ends up being faster to do it myself. What I find agents actually useful for is doing large scale mechanical refractors. Instead of trying to figure out the perfect vim macro or AST rewrite script, I'll throw an agent at it.

> I find that the code quality LLMs output is pretty bad.

That was my experience with Cursor, but Claude Code is a different world. What specific product/models brought you to this generalization?

Re: Everything around LLMs is still magical and wishful thinking

#92

Post by exe34 » Fri, Jul 04, 2025, 10:18 PM UTC

hotpotat wrote: post #30

I have to say I’m in the exact camp the author is complaining about. I’ve shipped non trivial greenfield products which I started back when it was only ChatGPT and it was shitty. I started using Claude with copying and pasting back and forth between the web chat and XCode. Then I discovered Cursor. It left me with a lot of annoying build errors, but my productivity was still at least 3x. Now that agents are better an…

> but my productivity was still at least 3x

How do you measure this?

Re: Everything around LLMs is still magical and wishful thinking

#93

Post by mumbisChungo » Fri, Jul 04, 2025, 10:19 PM UTC

o11c wrote: post #34

mumbisChungo wrote: post #7

Earlier quoted context omitted.

Said this in another thread and I'll repeat it here: It's the same problem that crypto experiences. Almost everyone is propagating lies about the technology, even if a majority of those doing so don't understand enough to realize they're lies (naivety vs malice). I'd argue there's more intentional lying in crypto and less value to be gained, but in both cases people who might derive real benefit from the hard truth o…

> I'd argue there's more intentional lying in crypto I disagree. Crypto sounds more like intentional lying because it's primarily hyped in contexts typical for scams/gambling. Yes, there are businesses involved (anybody can start one), but they're mostly new businesses or a tiny tack-on to an existing business. AI is largely being hyped within the existing major corporate structures, therefore its lies just get tagge…

I think crypto companies and AI companies probably intentionally mislead approximately the same amount as one another, but in crypto the average participant is often bagholding a very short term investment and has a direct and tangible incentive to mislead as many people about it as quickly as possible- whereas in AI people mostly just get lost in the sauce with anthropomorphism.

Anecdotally, I see a lot more bold-facing lies by crypto traders or NFT "collectors" than by LLM enthusiasts.

Re: Everything around LLMs is still magical and wishful thinking

#94

Post by CharlesW » Fri, Jul 04, 2025, 10:20 PM UTC

hotpotat wrote: post #77

troupo wrote: post #61

Earlier quoted context omitted.

Please re-read the article. Especially the first list of things we don't know about you, your projects etc. Your specific experience cannot be generalized. And speaking as the author, and who is (as written in the article) literally using these tools everyday. > But I’m just so floored how anyone could not be extracting the same utility from it. It feels like there’s two articles like this every week now. This is whe…

I did read the entire article before commenting and acknowledge that you are using them to some affect, but the line about 50% of the time it works 50% of the time is where I lost faith in the claims you’re making. I agree it’s very context dependent but, in the same way, you did not outline your approaches and practices in how you use AI in your workflow. The same lack of context exists on the other side of the argu…

> …the line about 50% of the time it works 50% of the time is where I lost faith in the claims you’re making…

That's where the author lost me as well. I'd really be interested in a deep dive on their workflow/tools to understand how I've been so unbelievably lucky in comparison.

Re: Everything around LLMs is still magical and wishful thinking

#95

Post by troupo » Fri, Jul 04, 2025, 10:21 PM UTC

hotpotat wrote: post #77

troupo wrote: post #61

Earlier quoted context omitted.

Please re-read the article. Especially the first list of things we don't know about you, your projects etc. Your specific experience cannot be generalized. And speaking as the author, and who is (as written in the article) literally using these tools everyday. > But I’m just so floored how anyone could not be extracting the same utility from it. It feels like there’s two articles like this every week now. This is whe…

I did read the entire article before commenting and acknowledge that you are using them to some affect, but the line about 50% of the time it works 50% of the time is where I lost faith in the claims you’re making. I agree it’s very context dependent but, in the same way, you did not outline your approaches and practices in how you use AI in your workflow. The same lack of context exists on the other side of the argu…

> but the line about 50% of the time it works 50% of the time is where I lost faith in the claims you’re making.

It's a play on the Anchorman joke that I slightly misremembered: "60% of the time it works 100% of the time"

> is where I lost faith in the claims you’re making.

Ah yes. You lost faith in mine, but I have to have 100% faith in your 100% unverified claim about "job at a demanding startup" where "you still haven't written a single line of code by hand"?

Why do you assume that your word and experience is more correct than mine? Or why should anyone?

> you did not outline your approaches and practices in how you use AI in your workflow

No one does. And if you actually read the article, you'd see that is literally the point.

Re: Everything around LLMs is still magical and wishful thinking

#96

Post by troupo » Fri, Jul 04, 2025, 10:21 PM UTC

CharlesW wrote: post #94

hotpotat wrote: post #77

Earlier quoted context omitted.

I did read the entire article before commenting and acknowledge that you are using them to some affect, but the line about 50% of the time it works 50% of the time is where I lost faith in the claims you’re making. I agree it’s very context dependent but, in the same way, you did not outline your approaches and practices in how you use AI in your workflow. The same lack of context exists on the other side of the argu…

> …the line about 50% of the time it works 50% of the time is where I lost faith in the claims you’re making… That's where the author lost me as well. I'd really be interested in a deep dive on their workflow/tools to understand how I've been so unbelievably lucky in comparison.

Sibling comment: https://news.ycombinator.com/item?id=44468374

Re: Everything around LLMs is still magical and wishful thinking

#97

Post by mlinsey » Fri, Jul 04, 2025, 10:23 PM UTC

tasty_freeze wrote: post #18

One thing I find frustrating is that management where I work has heard of 10x productivity gains. Some of those claims even come from early adopters at my work. But that sets expectation way too high. Partly it is due to Amdahl's law: I spend only a portion of my time coding, and far more time thinking and communicating with others that are customers of my code. Even if does make the coding 10x faster (and it doesn't…

I don't disagree with your assessment of the world today, but just 12 months ago (before the current crop of base models and coding agents like Claude Code), even that 10X improvement of writing some-of-the-code wouldn't have been true.

Re: Everything around LLMs is still magical and wishful thinking

#98

Post by hamilyon2 » Fri, Jul 04, 2025, 10:23 PM UTC

I am impressed by speed of the sound goalpost movement.

Few days ago Google released very competent summary generator, interpreter between 10-s of languages, gpt-3 class general purpose assistant. Working locally on modest hardware. On 5 years old laptop, no discrete GPU.

It alone potentially saves so much toil, so much stupid work.

We also finally “solved computer vision”. Read from PDF, read diagrams and tables.

Local vision models are much less impressive and need some care to use. Give it 2 years.

I don't know if we can overhype it when it archives holy grail level on some important tasks.

Re: Everything around LLMs is still magical and wishful thinking

#99

Post by alt187 » Fri, Jul 04, 2025, 10:24 PM UTC

hotpotat wrote: post #77

troupo wrote: post #61

Earlier quoted context omitted.

Please re-read the article. Especially the first list of things we don't know about you, your projects etc. Your specific experience cannot be generalized. And speaking as the author, and who is (as written in the article) literally using these tools everyday. > But I’m just so floored how anyone could not be extracting the same utility from it. It feels like there’s two articles like this every week now. This is whe…

I did read the entire article before commenting and acknowledge that you are using them to some affect, but the line about 50% of the time it works 50% of the time is where I lost faith in the claims you’re making. I agree it’s very context dependent but, in the same way, you did not outline your approaches and practices in how you use AI in your workflow. The same lack of context exists on the other side of the argu…

I agree about the 50/50 thing. It's about how much Claude helped me, and I use it daily too.

I'll give some context, though.

- I use OCaml and Python/SQL, on two different projects.

- Both are single-person.

- The first project is a real-time messaging system, the second one is logging a bunch of events in an SQL database.

In the first project, Claude has been... underwhelming. It casually uses C idioms, overabuses records and procedural programming, ignores basic stuff about the OCaml standard library, and even gave me some data structures that slowed me down later down the line. It also casuallyies about what functions does.

A real example: `Buffer.add_utf_8_uchar` adds the ASCII representation of an utf8 char to a buffer, so it adds something that looks like `\123\456` for non-ascii.

I had to scold Claude for using this function to add an utf8 character to a Buffer so many times I've lost count.

In the second project, Claude really shined. Making most of the SQL database and moving most of the logic to the SQL engine, writing coherent and readable Python code, etc.

I think the main difference is that the first one is an arcane project in an underdog language. The second one is a special case of a common "shovel through lists of stuffs and stuff them in SQL" problem, in the most common language.

You basically get what you trained for.

Re: Everything around LLMs is still magical and wishful thinking

#100

Post by CharlesW » Fri, Jul 04, 2025, 10:24 PM UTC

98eb1d0ff7fb96 wrote: post #90

garciasn wrote: post #32

Earlier quoted context omitted.

Well; I can't speak to your specific experience (current or past) but I'm telling you that while I'm skeptical as hell about EVERYTHING, it's blowing my expectations away in every conceivable way. I built something in less than 24h that I'm sure would have taken us MONTHS to just get off the ground, let alone to the polished version it's at right now. The most impressive thing is that it can do all of the things that…

See, your comment is a good example of what's going wrong. The OP specifically mentioned "mission critical things" - My interpretation of that would be things that are not allowed to break, because otherwise people might die, in the worst case - and you were talking about just SOMETHING that got "done" faster. No mention about anything critical. Of course, I was playing around with claude code, too, and I was fascina…

> So it kinda worked, but I would not use that for anything "mission critical" (whatever this means).

It means projects like Cloudflare's new OAuth provider library. https://github.com/cloudflare/workers-oauth-provider

> "This library (including the schema documentation) was largely written with the help of Claude, the AI model by Anthropic. Claude's output was thoroughly reviewed by Cloudflare engineers with careful attention paid to security and compliance with standards. Many improvements were made on the initial output, mostly again by prompting Claude (and reviewing the results)."