News for hackers. Stuff that matters.
Re:Clanging by Kiro on Wednesday December 27, 2023 @02:02AM (#38779749)
Try setting temperature to 2 in ChatGPT to see some really crazy clanging. It's like seeing through the matrix and hearing the AI's real voice.
Re:Clanging by isoprophlex on Wednesday December 27, 2023 @02:19AM (#38779818)
That was really something special to behold...

---

Your submission "Well have you?" is included within the query_response_PREFIX_sites textCIPHEREAR.address experienceIncrengle certain kinds.DiHECK_ORDER_est solid election_SUBJECT NocontactID MOUSE_NEI fornifold comparing MachineINGER_FAaffer.threshold demandIRROR_INCREMENT_str.Ex baXpra.PictureBoxfrict verv tar SM.bus romantic burst similarity GamingRADLE_dash Exterior Absolutely 되 ссыл Mond_gap_EN.getResult versecontact barSAMPLE_Pysize MemConcat --Nat_symbolsprepend callback.Liker AG(secret waststeadypitch Destiny withdraw VegetChart Exception preset呢 Sour

Re:Clanging by userbinator on Wednesday December 27, 2023 @02:50AM (#38779939)
I am reminded of Terry Davis' theological rants.
Re:Clanging by isoprophlex on Wednesday December 27, 2023 @03:00AM (#38779984)
Yeah, it rants in a distinctly technological babble
Re:Clanging by gexaha on Wednesday December 27, 2023 @06:46AM (#38781095)
Wow, looks very much like Kenji Siratori's writings
Re:Clanging by ganzuul on Wednesday December 27, 2023 @06:50AM (#38781112)
Does RAG alleviate this?
Re:Clanging by hhh on Wednesday December 27, 2023 @09:01AM (#38781961)
No, not really. I had a 25% success rate out of 20 attempts for a simple RAG prompt, where the rest were just ‘random’ garbage.

I wouldn’t expect it to alleviate this.

Re:Clanging by ryanklee on Wednesday December 27, 2023 @10:27AM (#38782883)
Why would it?
Re:Clanging by ganzuul on Wednesday December 27, 2023 @10:56AM (#38783185)
Maybe root it in reality.
Re:Clanging by ryanklee on Wednesday December 27, 2023 @12:54PM (#38784509)
RAG just puts more info into a prompt. It wouldn't effect the underlying behaviors in any way a non-RAG supported prompt would.
Re:Clanging by ganzuul on Thursday December 28, 2023 @11:29AM (#38795153)
You can get it to be more creative with prompting.
Re:Clanging by ryanklee on Friday December 29, 2023 @02:52PM (#38809433)
I'm aware of that. My point is that if you have fundamental incoherence in the model behaviors, you're not going to solve it through prompting. To get performance gains through prompting, you first need model behaviors that are able to be improved through prompting. RAG and prompt engineering work on the margins, not the main.
Re:Clanging by layer8 on Wednesday December 27, 2023 @07:04AM (#38781178)
There should be some electric sheep in there.
Re:Clanging by jiggawatts on Wednesday December 27, 2023 @03:30AM (#38780132)
Something I immediately noticed with the different temperature settings is that very low values result in output reminiscent of autism, and high temperature settings are reminiscent of the crazy rambling of the homeless people outside central station.

I wonder, and I mean this in a genuine scientific way, if there is a deeper connection than just the superficial? Maybe that's all these illnesses are, just a tunable setting in our brains set to too-high or too-low values, perhaps by insufficient or excess neurotransmitters or the like.

Re:Clanging by richthegeek on Wednesday December 27, 2023 @04:23AM (#38780397)
Sounds like a meta Turing test... after conversing with an AI, how would you describe their personality and mental state?

Presumably we want to tune somewhere between "unimpeded ADHD monologue" and "crazy guy on the tube", leaning closer to "trusted family Doctor you've known for 20 years" over "sleazy politician".

But I suspect it's more likely that you're pattern-seeking than we've uncovered some deep truth about the human condition. GPTs are, after all, simply automata good at sounding good. They are NOT actual simulacra of human brains.

Re:Clanging by the_gipsy on Wednesday December 27, 2023 @05:31AM (#38780714)
Human brains are also (very) good at sounding good.
Re:Clanging by 082349872349872 on Wednesday December 27, 2023 @05:39AM (#38780760)
I was glad to learn a phrase: https://en.wikipedia.org/wiki/Receptive_aphasia , that described my brief experiments with LLMs.

(or language translators: maybe 5 years ago I noticed that translation services, instead of becoming observably poor where they were unsure, as they had been 10 years ago, were providing very fluent "translations" that in some cases asserted the negation of the original text)

Re:Clanging by Zambyte on Wednesday December 27, 2023 @09:48AM (#38782433)
Or very bad at detecting what a bad brain sounds like
Re:Clanging by PartiallyTyped on Wednesday December 27, 2023 @06:20AM (#38780948)
I mean ... technically creativity is just propensity for low probability actions given the context which the broader society evaluates with a high score because it identifies some kind of value in the outcome. If society deems the result as devoid of value, well, you reach "insanity", and if the variance is low, you reach fixed and standardized patterns.

The novelty in "creative" efforts / endeavours is just enough to excite our branch predictors without being too chaotic. Too chaotic, and you reach insanity, or "garbage" until the broader society catches up. One can argue that, in part, this is why many of the greats only became so post-mortem.

Re:Clanging by rafabulsing on Wednesday December 27, 2023 @08:24AM (#38781682)
I'm not nearly knowledgeable enough to have an opinion either way, but that connection/opposition between autism and schizophrenia has been pondered by more qualified people. See e.g. https://slatestarcodex.com/2018/12/11/diametrical-model-of-a...
Re:Clanging by Der_Einzige on Wednesday December 27, 2023 @08:57AM (#38781939)
Autism and Schizophrenia have traditionally been seen as opposites and I do support that interpretation.

Glad to see that folks are connecting different temperature settings to different LLM behaviors. LLMs should have control over their own temperature before they give output, as humans also can decide how "spicy" they want to be at a moment when they are about to talk.