I similarly had Argon respond with a vast hallucination. It surprised me because it wasn't a little wrong on the details but a fully false verbose response that completely fabricated fabricated everything. I'd recently had Claude Code help me create transcripts for some audio notes from my mother in law and decided to see how some other models would handle the same task sans harness. Argon made up a long conversation from a police sting operation with under cover operatives seemingly just because it read the file names and identified that they would have come from a recording device.

Honestly the fiction writing was pretty impressive!

▲

dcss_gardener 5 hours ago | parent | next [-]

Suddenly very curious what the llm roleplay people think about this one lol. Fortunately I've already learned to stifle my curiosity on that specific subject.

▲

bananaflag 5 hours ago | parent | next [-]

It seems a strangely underdiscussed topic on HN.

	▲	mcbuilder 4 hours ago \| parent [-]
		It goes way back, I work in AI/Ml (taken over by transformers/LLMs) space since early days of this "AI Summer". We get some nice grad school students interning from top universities. I met one during a trip to the office, from top notch school, introduced me to Triton programming when it first came out. It was early days of LLaMA just coming, when The Bloke was regularly dropping finetunes, I was joking asking him what the hacker stack was for "AI waifus" that the cool kids were using. Lo and behold he drops the name of the SillyTavern project. Which later was really educational in setting up local inference servers and in other ways, may have had to, ahem, delete some browser history.

▲

pontes 4 hours ago | parent | prev [-]

I will try here: https://myownlore.com :)

But my experience is that the agent matters a bit more than the model. It is fun on ChatGPT because of its recent (?) bias to always be creating images for conversations around fiction.

	▲	carterschonwald 2 hours ago \| parent [-]
		what are some of the vagaries of how that use case depends on the agent aka harness? i’ve only been focused on sort of how to make models reliable for my math / cs / engineering and arts and crafts work loads, but RP is an important category for some folks. like are the fails of the various models different from more technical yet creative work loads? eg im working on rigorizing a proof that a fun algorithm of mine is not only the first provably efficient algorithm for a particular problem, but its also the fastest in practice. ive found that for the sort of stuff i need to assume the model will get confused in the out of training distribution stuff from my personal library of ideas, so they will at best be a confused secretary intern mashup

▲

staticman2 4 hours ago | parent | prev | next [-]

If you uploaded the audio via the web site or app and got terrible results I'd bet Argon wasn't the model doing the transcribing. The only way to know for sure is to try again with the API.

▲

MattRogish 2 hours ago | parent | prev | next [-]

Yes! I was having Argon summarize some project updates and it... just made up entire paragraphs that had no basis in reality. It felt like I was back in GPT3 days.

Will have to give Carbon a try, but if it is anything like what I saw before it was entirely unusable.

▲

cannonpalms 3 hours ago | parent | prev [-]

Very wise of you to keep MIL receipts. You never know when you might need them...