HackerLangs
TopNewTrendsCommentsPastAskShowJobs

avereveard

5,627 karmajoined 12 anni fa

comments

avereveard
·3 giorni fa·discuss
steering:

You are the sole owner of the project implementation.

User maintained documentation:

- goals.md for the project overall goals

- tech.md for guidance on how to build the project

Agent maintained documentation, current state living specs, these are not logs:

- project.md is a map of the code, components and features.

- choices.md write here all decision taken by the user.

Do not duplicate information between these document.
avereveard
·3 giorni fa·discuss
Same. For some reason late opus model are very superficial doing ux work and so am using gpt for that, but backend is much better engineered by claude, gpt prefer to duplicate everything it needs on the spot causing class sprawl
avereveard
·4 giorni fa·discuss
Very good on vision, really helped oneshotting complex ix thay I had so far to buukd piecemeal. Ended the 200$ plan weekly allowance in two days, so theres thay.
avereveard
·6 giorni fa·discuss
Mybatis was a thing even back then... you still need a domain model after all
avereveard
·8 giorni fa·discuss
Seems hella inefficient.

Better method start to realizing that everything that every program do is data transformations and or movement

Then you ask llm to subdivide data in a tree along the domain model, classifing streaming vs storing nodes

Then for each node you discuss with the ai for the best data structure

Then you ask for an interface that fully encapsulate the structure and every mutation only allows to go from a valid state to a valid state and bidding else is allowed to touch the state

And that's mostly it just connect all the interfaces until input goes to monitor or to storage or to api or wherever the destination is
avereveard
·12 giorni fa·discuss
I really dislike opus 4.8 it rarely compete things and prefer to waste tokens making lists of things that are missing. When stuck or need input it words the challenge at length without conveying anything useful for decision making, and quite often its solution to problems is to excise features or just try catch errors and proceed with faulty data silently
avereveard
·14 giorni fa·discuss
I hate loud ads as well as anyone else and I welcome this resolution but I would not treat the challenges regulation poses as simplisticly as this. There is a lot of research in increasing loudness without increasing decibels, especially for concerts, but it migrated to ads when tv started adding automatic volume controls to normalize across services.
avereveard
·18 giorni fa·discuss
> Anthropic is subsidizing their enterprise customers by up to 40 times, and OpenAI up to 70 times

might as well be the other way around with non subscribed token being 50x overpriced, or any combination thereof

also uber was non profitable for the longest time, raking up 31b in losses, on the bet of capturing the market worldwide. scale here is different, but it's also 10 years later, with a lot more volatility and floating cash in the market (voo grew 327% over that period, not unreasonable that round size grew on the same trajectory)
avereveard
·18 giorni fa·discuss
https://en.wikipedia.org/wiki/Prohibitory_traffic_sign#/medi... yeah?
avereveard
·18 giorni fa·discuss
There literally are "no u turn" signage where you are supposed not to do that. They literally put up signs for it. It is not glowing in the sky, and it doesnt need to be, and doesnt help making a point strawmanning it.
avereveard
·18 giorni fa·discuss
Until they reverse on a highway and kill a family. Being able to drive isn't where parent poster put the bar
avereveard
·19 giorni fa·discuss
yeah been away from a while. thanks!
avereveard
·19 giorni fa·discuss
Does BAR have chicken maps?
avereveard
·26 giorni fa·discuss
most merge improve a small subset of "feeling" benchmark (too small, too specific, or out of distribution) and tend to show degradation on actual benchmark, with especially punishing result on long chain benchmarks.

also only work on matching architectures (i.e. finetunes/loras of the same model)
avereveard
·27 giorni fa·discuss
I use glm for all code investigations and top level system design of all kinds, and then present finding to confirm and act upon to opus. everything that burns token goes there.

the finding aren't always accurate, but it saves ton of opus token

likewise I have google ai from my photo storage, so I give claude / opencode a skill that uses gemini (agy now) command line for web searches, using their flash model line.
avereveard
·mese scorso·discuss
*Anthropic requires it
avereveard
·mese scorso·discuss
Metadata does not require data and conflating them doesn't help your point
avereveard
·mese scorso·discuss
The right level of recording of non crime is zero wdym reduced?
avereveard
·mese scorso·discuss
Same, even opus favor short term solution and scripts with a billion flags that constabtly require rescanning to understand how to launch it is a constant struggle to get it to build sane default and reusable scripts that run with minimal parameters
avereveard
·mese scorso·discuss
But they are, especially those with batteries