Hacker Newsnew | past | comments | ask | show | jobs | submit | adocomplete's commentslogin

I find LLM generated Go code to be much better than other languages and love building Go apps with AI.

Don't American cars have some of the lowest levels of reliability?

I'm not super educated on all the happenings in the car industry globally, but I've seen a few videos of Chinese EVs that put anything Ford, GM or other US brands have put out to absolute shame.


The purpose of the US auto industry is primarily a jobs program and secondarily a way to ensure the existence of supply chains for national security. The fact that it produces cars is tertiary at best and explains the quality of vehicles it produces.


I think American car companies are orthogonal to the question. The larger point is that _Japanese and German_ cars for the American market are largely themselves American by many important metrics.


hi


So all of them?


I'm partial to http.dog



https://adocomplete.com - launched it earlier this year.

https://adocomplete.com/advent-of-claude-2025/ - my Claude Code tips based on the Advent of Claude I did over December


It's even simpler. It's just 1's and 0's.


yeah seems like an odd choice for a new project.


The project is six years old


I stand corrected.


This long predates Google LLMs


How is that any different from Googling something and believing any of the highly-SEO optimized results that pollute the front page?


That's the point, nobody really believes there is an intelligence generating Google results. It is a best-effort based engine. However, people have this belief that ChatGPT has somehow some intelligent engine generating results, which is incorrect. It is only generating statistically good results; if it is true or false depends on what the person using it will do with the results. If it is poetry, for example, it is always true. If it is how to find the cure for cancer it will with very high probability be false. But if you're writing a novel about a scientist finding a cure for cancer, then that same response will be great.


So "statistics" are enough to take gold at IMO?


Search engines didn't need $500B and growing in CAPEX.


I was thinking the same thing. Humans push terrible code to production all the time that slips through code reviews. You spot it, you fix it, and move on.


Also a lot of the AI code reviewer tools catch bugs that you wouldn't catch otherwise


You can actually just edit the "includeCoAuthoredBy" setting in Claude Code and set it to "false".

https://docs.claude.com/en/docs/claude-code/settings#availab...


That is so much easier. Thank you.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: