I agree with most of the 'llm's are bad' section. However, I find it extremely hard to believe that llm's will make peoples thoughts sharper and faster. There have already been several studies published demonstrating the obvious. Not hard to imagine that long term, the negative cognitive effects of using llm's constantly will compound and be even worse.
The LLM Critics Are Right. I Use LLMs Anyway
271–280 of 330 posts
Re: The LLM Critics Are Right. I Use LLMs Anyway
#272Earlier quoted context omitted.
The LLMs are better at enforcing their boundaries than developers. Run out of tokens? That's it. No more code. It doesn't care how much the company needs this for the customer call tomorrow.
I feel that’s the opposite of the LLM-business models. If I run out of tokens I’m encouraged to spend money to buy more tokens, Claude has an overage setup, and Anthropic runs occasional token sales. So, to that example: the more often customers are hitting token limits under duress the more likely to open up the wallet and pay to finish.
So, its drug dealer economics.
Run out of your fix? (Tap tap) Buy some more!
Re: The LLM Critics Are Right. I Use LLMs Anyway
#273I agree with most of the 'llm's are bad' section. However, I find it extremely hard to believe that llm's will make peoples thoughts sharper and faster. There have already been several studies published demonstrating the obvious. Not hard to imagine that long term, the negative cognitive effects of using llm's constantly will compound and be even worse.
i was certain of the same worst case scenario until I started to properly read and study the LLMs output. prior to that enlightening, very wise choice, I speedread/skimmed and checked for grave bullshit/hallucinations only.
now i am convinced that it's the same matter as with people who forget most of what they learned after the actual exam vs people who go nuts and can't progress if they didn't understand a foundational part of a formula, fact or theory.
Re: The LLM Critics Are Right. I Use LLMs Anyway
#274Earlier quoted context omitted.
> I will just point out the benefit is not as obvious as you think. Developers have consistently overestimated LLM I think there are two different claims here: - developers overestimate productivity gains, which is a solid finding in many of these studies. Skepticism of extremely large productivity gains is warranted and I flatly disbelieve "10x uplift" claims. - LLMs give no productivity uplift at all, which is much…
Maybe we can make an analogy with taking the plane vs driving to your destination. A plane literally goes 10x faster than a car, so a 5 hour drive becomes a 30 minutes flight. But if you have to drive to the airport, arrive early, pass check-in, security, boarding, then pick up your luggage on arrival, rent a car and drive to your destination, you may realize that your 30 minute flight took you more than 5 hours in t…
> You also have to consider the Amdahl's law: a 10x speedup on 10% of the project is just a 9% speedup overall.
This is totally true for me. I'm working on more features/bugs at work and getting the coding done faster with claude but the coding part is at maximum half of the process and usually less. The rest of it is clarifying the requirements from our product team or given that we're a very legacy place, what the existing state of our infrastructure and other systems are for the new changes to fit in to, etc.
Re: The LLM Critics Are Right. I Use LLMs Anyway
#275Earlier quoted context omitted.
> LLMs give no productivity uplift at all, which is much harder to defend It’s not really hard to defend. Because when people says that productivity is uplifted, they are talking about amount of work, not the ROI. That’s why you keep hearing about LOC, amount of PR and prototypes, and the time taken is actually “time to PR” and not “time to production + time spent on bugs”.
There's another even more abstract liability on the balance sheet here for "deprecated LOC" or something, where the thing they built gets scrapped because no one wants to untangle the rat nest, or the "documentation" was so incoherent that it all had to be rewritten and reviewed.
Coming from legacy enterprise I am using claude to do exactly this for some of my team's more bizarre and poorly documented "inventions" that started out as their pet project and then became part of our official workflow.
Re: The LLM Critics Are Right. I Use LLMs Anyway
#276> I am a little bit scared to say this too: last month I spent almost 10k USD on tokens. It sounds so insane. What are people actually doing with all these tokens? I use LLMs pretty heavily for development, and I'm rarely spending all the tokens that come with a $10/month OpenCode Go subscription...
Same. Granted I have the $100/month Claude sub and barely ever see any of my usage bars go above 50% before they're reset (and that's when I had lined up a bunch of things to test Fable with).
Re: The LLM Critics Are Right. I Use LLMs Anyway
#277Earlier quoted context omitted.
What new or existing metric would better assess test coverage than line coverage and branch coverage? I wrote a tool called tert - I guess it's called an agent harness now - to run various test runners and log test output and coverage output to disk. FWIU stripping spaces from JSON does save tokens. It seems like feeding coverage lines-missing maps into the prompt results in better output, better LLM-authored tests.…
You can write tests that cover every line/branch without actually verifying the code does what it’s supposed to. Relying on (unreviewed?) LLM written tests that provide coverage may not be a great idea.
So, a project can have 100% test coverage (the tests run each line or branch at least once without any errors or failures) but fail acceptance tests.
If there is prompt insufficiency, there is probably acceptance test insufficiency.
A more assuming agent could automatically develop a plan that includes presumptive acceptance tests and request feedback before spending tokens
Re: The LLM Critics Are Right. I Use LLMs Anyway
#278> And then there are the geopolitical tensions. What happens if China or the US cut us off overnight from these technologies? Just a couple of weeks ago the US government showed it was able and willing to cut off non-US citizens from Anthropic’s latest frontier model. The only evidence you have is US here and all the frontier models from China are free to download. Pure projection. You can read China's AI strategy he…
I might be missing something but what exactly is being projected here? The US did what the author said. It's not farfetched to imagine geopolitical conflicts could, at some point, drive china to do something similar. > all the frontier models from China are free to download Maybe? Again, not hard to imagine that they might not be releasing their actual frontier models to the public.
I guess China did not deserve mention. They are the only one releasing open models consitently and not cutting any access. Only US actions show evidence and for the US only.
Re: The LLM Critics Are Right. I Use LLMs Anyway
#279Earlier quoted context omitted.
That’s what I’ve heard from my dev team too. They’re using it to give themselves free time while still being on the clock, not to produce more output for the company. Roughly thinking about hours spent on projects I think have gone up per task, the opposite that should be happening.
I'm finding it almost impossible to fill that free time with work, unless it's just reading emails and chat messages. I can context switch between two or three chats, but doing so speeds up my agent use at the cost of making reviews and discovery harder, so it might come out in the wash.
>I can context switch between two or three chats
I'm finding this is a skill which I'm slowwwwwwly improving but, for now, my level means I tend to miss mistakes I'd notice if just working on one task. I also had to make accommodations to the way I work to make it achievable, including telling my employer that a 500 GiB disk just isn't enough any more when I need multiple builds in parallel.
Re: The LLM Critics Are Right. I Use LLMs Anyway
#280> LLM’s amplify what you already have: opinions, structure, frameworks. So far, so agreeable, but… > If you have thoughts, they come out sharper and faster. I can’t help but wonder whether constant use of “agent” harnesses will lead to an atrophy of the software engineering (or really any field) muscles. Actual muscles need exercise to stay in shape (let alone grow), so does the brain. Can we really be sure that thou…
I'm frankly baffled by the number of commenters saying they've seen little productivity gains using LLMs/agents. My team got cut in half at the end of last year and we've probably increased our output by 25% primarily due to LLMs. Personally it's probably doubled my productivity. And we generally use a pretty structured spec based approach with consistent human code review, and six months into adoption we've had virt…
>My team got cut in half at the end of last year and we've probably increased our output by 25% primarily due to LLMs. Personally it's probably doubled my productivity.
Love to see worker unity in action.