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

Let's talk about LLMs

b-list.org

Post reply on HN
Print view View original

151–160 of 201 posts

Re: Let's talk about LLMs

#151

Post by ianhxu »

hombre_fatal wrote: post #72
smartmic wrote: post #19

Earlier quoted context omitted.

> I'm sure it was very difficult to program in machine code, but if now (or soon) anyone can just write software using a LLM without any sort of learning it changes everything. LLMs can plan and create something usable from simple instructions or ideas, and they will only get better. Did you read the section "Power to the People?" ? In it, the author dismantles your thesis with powerful, highly plausible arguments.

I read that section but I disagree with it. 1. You don't have to be an LLM expert to get good, consistent results with LLMs. My best vibe-code process after years of using LLMs is to have Claude Code create a plan file and then cycle it through Codex until Codex finds nothing more to review, then have an agent implement it. This process is trivial yet produces amazing results. It's solved by better and better harness…

[dead]

Re: Let's talk about LLMs

#152

Post by taneq »

gerdesj wrote: post #102
aspenmartin wrote: post #99

Earlier quoted context omitted.

I would argue LLMs are possibly the largest paradigm shift the world has ever seen, and we are only at the beginning. The entire scaffolding and structure of programming is in the process of changing — coding has moved to orchestration and testing and governance of how to manage and productionalize code that has surpassed the capacity of human review. If this sounds melodramatic it’s likely that it hasn’t fully taken…

[How did you bang out this: — on your keyboard? Why did you decide to use backticks and 66/99 for quotes - nice but its not you is it?] Engage as a person, please.

iOS automatically ‘replaces’ “quotes” with open/close quotes… and triple full stops with ellipses.

Re: Let's talk about LLMs

#153

Post by taneq »

aspenmartin wrote: post #118
gerdesj wrote: post #102

Earlier quoted context omitted.

[How did you bang out this: — on your keyboard? Why did you decide to use backticks and 66/99 for quotes - nice but its not you is it?] Engage as a person, please.

Oh also! Two dashes on my phone converts to an EN dash I think (not em dash!)

Let’s test that — hmm, I think it did?

Re: Let's talk about LLMs

#154

Post by redsocksfan45 »

skydhash wrote: post #63
michaelchisari wrote: post #38

Earlier quoted context omitted.

To clarify, AI should not do the design itself. You develop the design in conversation with AI. I come in knowing what I need to build and at least one idea or more of how it should be done. I present the problem, constraints, potential solutions, and ask for criticisms and alternatives. I can keep it as broad as possible or I can get more granular like struct layouts, api endpoints, etc. I go back and forth until th…

> I come in knowing what I need to build and at least one idea or more of how it should be done. I present the problem, constraints, potential solutions, and ask for criticisms and alternatives Never understood that argument. Because there’s two steps in design. Finding a good solution (discussing prior art, tradeoffs,…) and then nailing the technical side of that solution (data structures, formula,…). Is it the form…

[dead]

Re: Let's talk about LLMs

#155

Post by randallsquared »

simonw wrote: post #106
leptons wrote: post #84

Earlier quoted context omitted.

There's no such thing as a "10x" programmer, and anyone who uses it doesn't know what they're talking about. 10x relative to what exactly? It's not a statement grounded in any kind of reality.

10x makes sense only in terms of specific technology platforms. I'm a 10x programmer at building Django apps compared to a developer who has never worked with Django before. Someone who developers against WordPress on a daily basis will easily 10x my own attempts at building things on that platform.

I don't think it's only about specific technologies. I have occasionally worked with someone who was 10x (or more) the average in the org, and it wasn't just producing new code: it was debugging faster, reviewing faster, providing an insight to another dev with a moment's thought that unblocks their whole sprint, and, yes, still producing many times as many PRs as typical. In a modern corporate environment, the main problem is giving such a person enough to do in enough variety so that they don't get bored.

Re: Let's talk about LLMs

#156

Post by fatata123 »

aspenmartin wrote: post #99
gerdesj wrote: post #91

Earlier quoted context omitted.

"paradigm shift" A paradigm shift is an earth shattering, very important change - a complete change in thinking etc. LLMs are not that. They are simply some pretty new tools. Nice tools but they will whip off your metaphorical thumb just as quickly as a miss-used table saw. You'll note that you mention "engineers are offloading": that's not a paradigm shift. That's a bunch of engineers discovering a better slide rule…

I would argue LLMs are possibly the largest paradigm shift the world has ever seen, and we are only at the beginning. The entire scaffolding and structure of programming is in the process of changing — coding has moved to orchestration and testing and governance of how to manage and productionalize code that has surpassed the capacity of human review. If this sounds melodramatic it’s likely that it hasn’t fully taken…

[dead]

Re: Let's talk about LLMs

#157

Post by raincole »

gerdesj wrote: post #91
mfro wrote: post #4

I think you're misunderstanding the paradigm shift completely -- AI does not just generate code N(x) more quickly. It thinks N(x) faster, it researches N(x) faster, it tests N(x) faster. There are hundreds of tasks that you'll find engineers are offloading to AI every day. The major hurdle right now is actually pivoting LLMs from just generating code: integrating those tasks into workflows. This is why tool-use and a…

"paradigm shift" A paradigm shift is an earth shattering, very important change - a complete change in thinking etc. LLMs are not that. They are simply some pretty new tools. Nice tools but they will whip off your metaphorical thumb just as quickly as a miss-used table saw. You'll note that you mention "engineers are offloading": that's not a paradigm shift. That's a bunch of engineers discovering a better slide rule…

In the past half a century, product design went from making precise diagrams on paper to CAD. Do you think it's fair to call this paradigm shift or CAD is just some pretty new tool?

Re: Let's talk about LLMs

#158

Post by handoflixue »

nothinkjustai wrote: post #132
handoflixue wrote: post #112

Earlier quoted context omitted.

Can you name literally any other technology that had hundreds of millions of users within the first six months of being invented? Six months after the internet was invented, you could send email between a few universities. Six months after the computer was invented, they still hadn't actually built one. The first transcontinental railroad, took about six YEARS just to build.

GPT did not have hundreds of millions of users when it was invented almost a decade ago…

If you want to move the goal posts, that's fine, acknowledge it: the original claim I'm responding to was "We're almost 6 months into all this AI-code madness"

If you want to set GPT as the target, that's even easier! In that decade it has passed the Turing Test, solved novel open math problems, generates audio, video, and music, and can write coherent code. Again, there is no technology that has improved more rapidly than LLMs.

Re: Let's talk about LLMs

#159

Post by handoflixue »

wavemode wrote: post #117
handoflixue wrote: post #111

Earlier quoted context omitted.

> Your logic is flawed because, a thing can improve for an infinite amount of time while never surpassing a certain limit. It's called an asymptote. Have you ever once looked at a METR chart? https://files.civai.org/assets/METR_Chart.jpg That's not an asymptote. > there's also the fundamental fact that performance on benchmarks is not the same thing as performance in the real world Again, yes, you're correct in the g…

You're scoring rhetorical points while talking past my entire comment. Hard to say if you even read it. I'm not "convincing" anyone of anything. I'm stating the reasons that I, personally, am unconvinced of a specific claim being made to me .

I mean, I quoted multiple passages and established why I think your logic is flawed. If you're convinced by bad logic, so be it.

Re: Let's talk about LLMs

#160

Post by aspenmartin »

brazukadev wrote: post #128
aspenmartin wrote: post #113

Earlier quoted context omitted.

Way more than six months. You may be talking about how the world looks from your vantage point, as well you should. But there’s a reason why the world doesn’t allocate trillions of dollars of capital based on that. I really value skeptical people and skepticism generally. But what I think skeptical people would prefer to consider themselves is: rational and reasonable, with their beliefs well calibrated. You’re not t…

> Every major tech company - the ones poised to get the first best rewards, have already gotten good incremental revenue from AI via ads ranking/recommendations (Google, Meta, etc.) That's just software evolving. It happened before LLMs, it would happen without LLMs. > good productivity increases due to scale of workforce and advanced in house tooling. Exactly same case.

But I don’t really understand: the ask is for evidence AI is generating meaningful returns and it demonstrably is, even while we have integrated these tools only partially. “Just software evolving” um yes, I agree, just that now this happens faster and more efficiently. It is also more than that: models that power advertising and content recommendation at TikTok, Google, Facebook, Instagram, etc are not just “software evolving” it is meaningful improvements to models that are only possible with good AI.
Post reply on HN