[a / b / c / d / e / f / g / gif / h / hr / k / m / o / p / s / t / u / v / vg / vm / vmg / vr / vrpg / vst / w / wg] [i / ic] [r9k / s4s / vip] [cm / hm / lgbt / y] [3 / aco / adv / an / bant / biz / cgl / ck / co / diy / fa / fit / gd / hc / his / int / jp / lit / mlp / mu / n / news / out / po / pol / pw / qst / sci / soc / sp / tg / toy / trv / tv / vp / vt / wsg / wsr / x / xs] [Settings] [Search] [Mobile] [Home]
Board
Settings Mobile Home
/g/ - Technology


Thread archived.
You cannot reply anymore.


[Advertise on 4chan]


> Totally bro, let's version control every keystroke and every conversation
> We're going to read it all later bro, trust me

https://zed.dev/blog/introducing-deltadb
>>
another quality technology thread
>>
This is the problem with larpers and the lack of proper education. To make accurate predictions one must work at the proper level of abstraction, all else is just noise and will lead to divergent predictions sooner than otherwise.
The level of abstraction is HIGHER than commits not lower.
>>
every time i read a "sign up/sign in" on a product's website i already know it's shit
>>
Am I missing something here? You have to run shatbots in a loop with prewritten unit tests until it gets it right in order to accomplish anything, the transactional model of git is absolutely suited to this use case (assuming you actually want to write verified bug-free software)
>>
>>109035214
Read the article, they're building some shit called DeltaDB to record your every keystroke and every conversation, so changes and your thought process are auditable. It's like screen capture for text editors, absolute spyware.
>>
You can argue linking an LLM session to a PR or commit could be useful, but likely it's just going to bloat the context when an agent reads it. No human is going to anyway.



[Advertise on 4chan]

Delete Post: [File Only] Style:
[Disable Mobile View / Use Desktop Site]

[Enable Mobile View / Use Mobile Site]

All trademarks and copyrights on this page are owned by their respective parties. Images uploaded are the responsibility of the Poster. Comments are owned by the Poster.