←back to thread

Grok Code Fast 1

(x.ai)
504 points Terretta | 6 comments | 29 Aug 25 13:01 UTC | HN request time: 0.985s | source | bottom
Show context
RedMist ◴[29 Aug 25 14:33 UTC] No.45064657[source]▶
I've been testing Grok for a few days, and it feels like a major step backward. It randomly deleted some of my code - something I haven't had happen in a long time.

While the top coding models have become much more trustworthy lately, Grok isn't there yet. It doesn't matter if it's fast and/or free; if you can't trust a tool with your code, you can't use it.

replies(5): >>45064677 #>>45065762 #>>45070615 #>>45072014 #>>45074876 #
mwigdahl ◴[29 Aug 25 14:34 UTC] No.45064677[source]▶
Full Self Coding?
replies(2): >>45064873 #>>45066777 #
RedMist ◴[29 Aug 25 14:48 UTC] No.45064873[source]▶
No, making edits to an exiting codebase.

(If that's what you meant)

replies(1): >>45065015 #
pdabbadabba ◴[29 Aug 25 14:59 UTC] No.45065015[source]▶
I think that was just a joke about "Full Self Driving" -- and how it still doesn't work.
replies(2): >>45066786 #>>45066860 #
innocentoldguy ◴[29 Aug 25 17:20 UTC] No.45066860[source]▶
What do you mean by “it still doesn’t work“? I never drive anymore because my Tesla does such a fine job of doing it for me.
replies(2): >>45067013 #>>45067338 #
1. vunderba ◴[29 Aug 25 17:56 UTC] No.45067338[source]▶
To me, "full self driving" means you can hop in the back seat and have a nap. If you have to keep your hands near the wheel and maintain attention to the road then... shrugs not really the same. IMHO we're in the "uncanny valley" of vehicular automation.
replies(3): >>45067355 #>>45070404 #>>45075451 #
2. rkomorn ◴[29 Aug 25 17:58 UTC] No.45067355[source]▶
> the "uncanny valley" of vehicular automation

I think this is a very good description of where autonomous vehicles are right now.

replies(1): >>45067852 #
3. bpavuk ◴[29 Aug 25 18:41 UTC] No.45067852[source]▶
everything a layman would call "AI" is in the "uncanny valley" at the moment!

- Boston Dynamics' Atlas does not move as gracefully as a human

- LLM writing and code is oh-so-easy to spot

- the output of diffusion models is indistinguishable from a photo... until you look at it for longer than 5 seconds and decide to zoom in because "something's wrong"

- motion in AI-generated videos is very uncanny

replies(1): >>45070109 #
4. sebastiennight ◴[29 Aug 25 22:27 UTC] No.45070109{3}[source]▶
> LLM writing and code is oh-so-easy to spot

Maybe it's because we get use to it and therefore recognize it easier, but it does seem to get more and more recognizable instead of the opposite, doesn't it?

I think I could recognize a ChatGPT email way easier in 2025 than if you showed me the same email written by gpt-3.5.

5. innocentoldguy ◴[29 Aug 25 23:04 UTC] No.45070404[source]▶
You don’t have to keep your hands on the wheel.
6. yndoendo ◴[30 Aug 25 15:27 UTC] No.45075451[source]▶
I would add that "full self-driving" also means that the car company or the self-driving development company holds all liability in a car accident that the owner has none. Even Tesla right now states that the owner holds the liability in any accident. [0]

There are no proper retention laws with car manufacturers and self-driving development companies that I know of.

[0] https://arstechnica.com/cars/2025/08/how-a-hacker-helped-win...