I don’t think the definition is that clear cut at all. A human can remember the smell of something and invoke it right then and there even if only for half a second. Are we expecting an AGI to do the same?
Then again, transformers seem super-human in some ways already. Who do you know who can more or less recite and make associations from (even if not always intelligently) hundreds of billions of text fragments? Transformers already are better at math than your average human.
My bet is we’ll land in a weird place in between where these systems clearly have some superhuman intelligent capabilities but still are far from “do everything better than humans”.
> IMO Every engineer should try spending his time in a company that tries to solve new problems.
Yet typically 95% of software developers mainly work on CRUD-type apps. Coding agents are not perfect there either but they’re really a lot more reliable than they were a few months ago.
I have now, but (especially with the article part of the website now killed in favour of the execrable Medium) it took 'DVRC’s reply above for me to realize there was more to it than it first appeared: besides
Fun fact: originally "/home/NeWS" displayed "forbidden" access and I stumbled upon it by pure luck, finding the missing "operators.h" (and I told Don, since I wanted to see if there was something else missing or different, like "DumbOSI.c" which I hoped to be different from SunOSI.c). There is also an hidden file in /lib/NeWS called ".NeWS", contains the following string: "(hello) playdemo", which should kick the journal tool.
In any case, it was a "Pulcinella Secret", and anybody reading his replies on HN could easily find all his distributions, and it is replicated also on tenox.pdp-11.ru (but it's incomplete, since that there are only the contents of /home/code/NeWS".
On BitSavers there are the OpenWindows 2.0 source tapes other than the binaries (these last ones are also available inside SunOS 4.1.1 install CD, both for Sun-3 and Sun-4), but to extract them you need a specific tool, then you extract the tar dists.
I tried that afterwards in a new session. Asking about the virus itself was fine but as soon as I asked about developing a vaccine, the chat got flagged again.
While I agree with you that agentic coding still has quite a way to go and is not always producing the quality that I would want from it, I can say quite confidently that its baseline is way above some of the production code in many applications many people use today. It really isn’t that code before agents was primarily written with taste and beautiful structure in mind. Your average code base is a messy hell full of quick fixes that turned into all kinds of debt over the years.
I took the previous post, with its mention of the ball of mud, to be about complexity.
“Taste”, is used in many cases, I suspect, to give a name the collection of practices and strategies developers use to keep their code and projects at a manageable level of complexity.
LLMs don’t seem to manage complexity. They’ll just blow right past manageable and keep on going. That’s a problem. The human has to stay in the loop because LLMs only build what we tell them to build (so far).
BTW, the essay that introduced the big ball of mud pattern to me didn’t hold it up as something entirely bad to be avoided. It pointed out how many projects — successful or at least on-going projects — use it, and how its passive flexibility might actually be an advantage. Big ball of mud might just be the steady state where progress can be made while leaving complexity manageable.
I think there are at least two factors behind ye olde ball of mud that LLMs should be able to help with:
1. Lack of knowledge of existing conventions, usually caused by churn of developers working on a project. LLMs read very quickly.
2. Cost of refactoring existing code to meet current best practices / current conception of architecture. LLMs are ideal for this kind of mostly mechanical refactoring.
Currently, though, they don't see to be much help. I'm not sure if this is a limitation in their ability to use their context window, or simply that they've been trained to reproduce code as seen in the wild with all its flaws.
Keeping complexity down is always a conscious act. Because you need to go past the scope of the current problem and start to think about how it affects the whole project. It’s not a matter of convention, nor refactoring. It’s mostly prescience (due to experience) that a solution, even if correct and easy to implement, will be harmful in the long term.
Architecture practices is how to avoid such harmful consequences. But they’re costly and often harmful themselves. So you need to know which to pick and when to start applying them. LLM won’t help you there.
I agree. I do wonder if what I'm seeing is a limitation of the reasoning power of LLMs or if it's just replicating the patterns (or lack thereof) in the training data.
Very much. Try to start a union in China and see how communist that country is. China is essentially a right-wing hypercapitalist country run by a dictatorship.
No. But it also can automate some of the tedium away. Maybe there's some level of organic linking that you do, but it can also go through and be more thorough. I guess it depends on where you derive the value - if you want to be the one discovering the connections and making them, then obviously less so.
Interestingly, contamination of the forensic equipment was considered early on already. However, due to the geographic area of the findings and initial negative control tests using fresh swabs, they ruled it out.
reply