To be honest most LLM's are reasonable at coding, they're not great.
Sure they can code small stuff.
But the can't refactor large software projects, or upgrade them.
Upgrading large java projects is exactly what AWS want you to believe their tooling can do, but the ergonomics aren't great.
I think most of the capability problems with coding agents aren't the AI itself, it's that we haven't cracked how to let them interact with the codebase effectively yet. When I refactor something, I'm not doing it all at once, it's a step by step process. None of the individual steps are that complicated. Translating that over to an agent feels like we just haven't got the right harness yet.
Honestly, most software tasks aren’t refactoring large projects, so it’s probably OK.
As the world gets more internet connected and more online, we’ll have an ever expanding list of “small stuff” - glue code that mixes and ever growing list of data sources/sinks and visualizations together. Many of which are “write once” and leave running.
Big companies (eg google) have built complex build systems (eg bazel ) to isolate small reusable libraries within in a larger repo. Which was a necessity to help unbelievably large development teams to manage a shared repository. An LLM acting in its small corner of the wold seems well suited to this sort of tooling, even if it can’t refactor large projects spanning large changes.
I suspect we’ll develop even more abstractions and layers to isolate LLMs and their knowledge of the wold. We already have containers and orchestration enabling “serverless” applications, and embedded webviews for GUIs.
Think about ChatGPT and their python interpreter or Claude and their web view. They all come with nice harnesses to support a boilerplate-free playground for short bits of code. That may continue to accelerate and grow in power.
FYI closing this gate has a huge economic impact and is left over to machines.
The reasoning is a person living in the country would close this gate by fear of loosing families etc, here CODE decides when the time is right to close or stay open. It uses a lot of data to monitor and predict the weather.
> The reasoning is a person living in the country would close this gate by fear of loosing families
I don’t think that’s true. The official argument is that human operation wouldn’t reach the required reliability level (https://www.cs.vu.nl/~x/sil/sil.html: “The failure rate demands for this system were required to be 1:10000 for not closing when this was actually necessary, and 1:100000 for not opening the barrier when requested. This asymmetry is caused by the fact that if the sea surge barrier does not reopen, the river discharge can lead to flooding from the inside.”)
I think nobody knows for sure whether the conclusion that software alone would be more reliable than humans alone was correct (my money would be on “it wasn’t”). That’s hard to verify for such a system that “cannot be tested under the conditions for which it was designed” (https://www.researchgate.net/publication/220592956_Human_fac...).
You can’t do that statistically, either, as in real-world use it would take millennia to collect the necessary data, and that’s way longer than the design life of this structure.
Do you know of any good resources to see the water levels in such places? I know of some sites for example in California reservoirs, or Snotel and river gauges in the US. But I imagine the information is spread differently in these watersheds.
I believe you can still buy new 8086 class and 286 class 16bit x86 cores in random SoCs.
And I know you can buy SoCs with 386 class x86 cores. It might be more accurate to describe them as 486 class cores that don't implement the full 486 instruction set.
just curious would it be possible to add a small network perhaps a books of study material like programming books. freeze the weights of the existing large network, and combined with the new network try to predict the book. The existing networks know language but not the content, the combined network will be trained on the content, and eventually toegther they score better, These "small" added networks might just be specific towards a certain topic (ea learn python or so).
Then these small networks can be become modular. esesentially creating some kind of lora networks for LLM's.
Maybe start this way from the ground up, so you can get modular units, for health, finance, programming, education, writting assitance, phyloophy, ethics etc etc.
If the modules can be changed, then one might be able to reduce their seize.
Ea pick 2 or 3 chain them and one has a LLM for a specific area of interest.
(reducing running cost)
Essentially it does processing by gru's ?.
So it should be able to learn quickly, i gave it an angular 12 chapter and it could fix some syntax bugs. maybe learn by prompting, and by techniques as used in those image generators, where people can add custom specializations over the network. (ea become excellent in angular 16 and 18) when is the language cut off going away? for rapid updating languages, or areas such as blender 3d, where api's change rapidly.
Yes it can
Yesterday i gave it a help chapter in a prompt about angular 16
The knowledge cut of is perhaps nice for politics but not for programmers.
After wards i could ask it about syntax problems i had in some code.
Essentially it understands programming didnt know what was possible in angular16
A single example made it learn from it. Though when i asked for an example i got the exact same sample as i had given it to learn from.
Perhaps end this language cut of for technical data.
Its okay not wanting to get into politics (neither do i).
But give it something to read (yup let it read and remember it) a simple prompt read this page by page will do, and give it some recent books, or popular coding websites, let it read python.org angular.io perhaps some modern manuals and books.
It also seemed keen to learn new information, it quickly adopted it.
But only in that session.
