Re:Making o1, o3, and Sonnet 3.7 Hallucinate for Everyone
by QuantumGood on Saturday March 01, 2025 @03:44PM
(#43223500)
GPT can't even tell what its done or give what it knows it should. It's endless, "Apologies, here is what you actually asked for ..." and again it isn't.
[ Parent
| on HN ]
Re:Making o1, o3, and Sonnet 3.7 Hallucinate for Everyone
by MortyWaves on Saturday March 01, 2025 @05:18PM
(#43224307)
This was my primary reason for using Claude. Absolutely useless experience with chatgpt oftentimes. I’ve mainly been using LLMs to help maintain a ridiculously poorly made technical debt dumpster fire, and Claude has been really helpful here mainly with repetitive code.
Re:Making o1, o3, and Sonnet 3.7 Hallucinate for Everyone
by therein on Sunday March 02, 2025 @12:44AM
(#43227779)
Yeah ChatGPT is truly the worst. Claude has been consistently much better. Grok 3 is surprising me every day.
Re:Making o1, o3, and Sonnet 3.7 Hallucinate for Everyone
by derefr on Sunday March 02, 2025 @01:14AM
(#43227889)
I would love an AI coding assistant that doesn't respond until it's gone out and tested its answer in a sandbox to confirm it actually compiles.
Re:Making o1, o3, and Sonnet 3.7 Hallucinate for Everyone
by AprilisKalends on Sunday March 02, 2025 @01:50AM
(#43228018)
I personally haven't figured out why there isn't a tool that just loops the AI severals times on a task by compiling, feeding in the errors adjusting and repeating and then letting the user review the result be in a success or failure by exceed the loop limits.
Re:Making o1, o3, and Sonnet 3.7 Hallucinate for Everyone
by staticautomatic on Sunday March 02, 2025 @04:10AM
(#43228708)
Claude has a tendency to overcomplicate bug fixes. If you put it on loop it would probably build a custom ERP.
Re:Making o1, o3, and Sonnet 3.7 Hallucinate for Everyone
by ta988 on Sunday March 02, 2025 @03:09AM
(#43228415)
They exist in various forms...
Re:Making o1, o3, and Sonnet 3.7 Hallucinate for Everyone
by anonzzzies on Sunday March 02, 2025 @05:11AM
(#43229005)
The LLMs want to please, they can infinitely keep making 'important' changes; changing variable names without changing anything else, adding/removing comments, adding removing print statements, moving a function somewhere in the code (usually by first duplicating it) and fixing perfectly fine code with 'let me see if everything is really working' (it was and now it's broken again).
Re:Making o1, o3, and Sonnet 3.7 Hallucinate for Everyone
by derefr on Sunday March 02, 2025 @01:59PM
(#43233722)
"Wanting to please" is just fine-tuned implicit prompt stuff, though. You can tell the LLM that it's roleplaying as a senior engineer, and should consider you, the human to be a junior engineer it works with, who is asking it for advice. You can just leave it at that (often works, if the AI knows enough about how software is produced); or you can describe particular traits of senior engineers — e.g. "wants code that works" and "knows when to say the code is good enough and that the junior is now wasting time by fiddling with it."
Re:Making o1, o3, and Sonnet 3.7 Hallucinate for Everyone
by v-yanakiev on Sunday March 02, 2025 @02:06AM
(#43228094)
https://syntix.pro automatically executes and verifies the code it generates. Disclaimer: I made it.
Re:Making o1, o3, and Sonnet 3.7 Hallucinate for Everyone
by mycall on Sunday March 02, 2025 @04:50AM
(#43228904)
Devin does that
Re:Making o1, o3, and Sonnet 3.7 Hallucinate for Everyone
by anonzzzies on Sunday March 02, 2025 @04:57AM
(#43228937)
Wasn't Devin a scam? Honest question; Google is not very clear about it but some people said it was a scam/money grab. You are saying it works?