Not much to say
Yeah I hope I am cautious enough. I use strict db models that were man written and have type checking and sanitation. That along with unit tests that cover everything I’ve been able to think of that can go right or wrong combined with the classic “obscurity===security” motto.
Of course there are always vectors one hasn’t thought of, but that goes for man made projects as well. If I decide to bring it live and scale up I’ll probably order a pen test.
I’ve been writing a slightly larger project with frontend, bff and backend and I need to take it in small batches so that I can catch when it misunderstands or outright does a piss job of implementing something. I’ve been focusing a lot on getting all the unit tests I need in place which makes me feel a bunch better.
The bigger and more complex the projects get, the harder it is for the LLM to keep stuff in context which means I’ll have to improve my chunking out smaller scoped implementations or start writing code myself I think.
All in all I feel pretty safe with my project and pleased with the agents work but I need to increase testing further before bringing anything live.
Probably a bunch more
I had a holy grail vhs which i watched more or less every day after school. I used to be able to recite it from start to finish.
Also had both terminator movies on a double vhs so I’ve seen my fair share of them as well.
You are completely correct, and to be honest I’ve tested commercial product features in prod as well on teams that have the capacity to handle it and make a living on it, unlike this maintainer.
I’m also experimenting heavily with vibe coding and I think it has many uses for a seasoned programmer while getting a lot of flak.
Of course there are issues and problems with it, but for me it had been helping out a lot.
For sure, the song of the hero who fixed the production bug is oft sang at meetings but the loser who prevented the bug to begin with gets no credit.
Classic “test in production” strategy, very solid!
To be fair they would have needed to spend time testing the manual implementation as well.
The problem I see mainly is that even if this rolls out perfectly, the erratic and changing nature if llms still make it pointless as a proof of concept. Next time Claude might fuck up in a fringe way that’s not covered by unit tests and is missed by manual tests.
On the other hand I guess I’ve been guilty myself on numerous occasions to implement fringe bugs into production code, but at least I learn from it.
This one should go all the way to the top.
Me neither I just read a magazine about king crimson and I probably only remembered the parts I found amusing. Could be they had more cohesion than my post claims.
But the thematics of the first album is not as planned as some would like to think and fripp was very vocal that female groupies was one of his biggest drives.
I wrote down Pet Sounds as a majorly influential album and Brian Wilson has said that that cohesion and individual song strength of Rubber Soul was the inspiration that drove him to make it.
So i guess your pick inspired my pick!
This one of funny because when reading about it I hit the feeling that they had no idea or plan to what they were doing. They just wanted to sell albums and get laid.
Then they drop this completely weird af, beautiful and haunting album which everyone of course tries to deconstruct and find the real meaning behind etc.
Just fripp and pals goofing about in the halls of the crimson king.
Forgot to mention:
All of sly and the family stones albums. Larry invented slap bass, they renewed funk, Greg laid the groundwork for what all hip hop artists draw from, sly used a drill machine that was more or less a toy to create really nasty and murky beats by lioping, overlaying and tooting with speeds ented and theyinnovated sludgy lo-fi sound. All in a few years.
Jeez you really hit a nerve here, with your pretty sane concept about sharing resources communally.
I guess some people really don’t like the word wasteful or something.
Well yeah it is, but is most likely much harder to solve co-living like that in a way that’s acceptable for almost any people. Whereas what was suggested here is that people pool their resources and lend/rent to each other.
Nothing about forcing anything on anyone, and people who want to be able to have exactly the CPU they need at any given time would probably not be interested.
As someone who’s been using it in my work for the last 2 years, it’s my personal observation that while the models aren’t improving that much anymore, the tooling is getting much much better.
Before I used gpt for certain easy in concept, tedious to write functions. Today I hardly write any code at all. I review it all and have to make sure it’s consistent and stable but holy has my output speed improved.
The larger a project is the worse it gets and I often have to wrap up things myself as it shines when there’s less business logic and more scaffolding and predictable things.
I guess I’ll have to attribute a bunch of the efficiency increase to the fact that I’m more experienced in using these tools. What to use it for and when to give up on it.
For the record I’ve been a software engineer for 15 years
❤️