News for hackers. Stuff that matters.
Re:What happens when an LLM never sees material beyond fifth... by Gud on Sunday August 16, 2026 @04:59AM (#49318230)
The difference between your two year old is that an LLM gives useful information.

Yesterday I decarboxylated some weed buds in preparation of making a cannabis tincture using the QWET method. Curious how Claude would respond, I asked how to do it.

It walked me through the process and gave accurate, nuanced answers.

Let me know what your 2 year old thinks I should do.

Re:What happens when an LLM never sees material beyond fifth... by neuroticnews25 on Sunday August 16, 2026 @05:08AM (#49318286)
Gemini estimated that male cannabis plant leaves I decarboxylated will have negligible thc content and give me mild relaxation at best, the real effect was it was the highest I've ever been.
Re:What happens when an LLM never sees material beyond fifth... by hnbad on Sunday August 16, 2026 @07:24AM (#49318994)
To be fair, I have yet to lead a conversation with Gemini that doesn't just consist of me having to check its responses and point out that they're objectively incorrect only for it to "apologize" and then give me the next wrong answer, while always making sure to end with a new conversation teaser.

Granted, I've only been using the free version but I've been getting significantly more mileage out of those from ChatGPT and Claude. I guess it might be a feature that Gemini is more often obviously wrong from the start (e.g. by giving sources that don't support its claims whatsoever) but considering this is the AI from the company that had become synonymous with the concept of trying to find information on the Internet, that's pretty damn pathetic.

Re:What happens when an LLM never sees material beyond fifth... by someothherguyy on Sunday August 16, 2026 @08:25AM (#49319407)
That is because it bases its responses on web searches with hits like comments in threads like these or blog articles that were generated from systems trained based on threads like these from the previous iteration of scrapers and generative language models.
Re:What happens when an LLM never sees material beyond fifth... by Gud on Sunday August 16, 2026 @10:47AM (#49320634)
Gemini sucks though. Are you using the paid version? The free one that has basically replaced the regular search, is totally useless because of how shallow it searches.

ChatGPT, which is usually quite reliable, refuses to answer me because law.

In the end, an extraction should work any plant material depending on potency, skill and available equipment.

After the extraction you can evaporate the ethanol(carefully since it’s highly flammable) and increase potency.

A mix of own research(basically emulating others) combined with strong models we can do a lot more than we can do ourselves.

Re:What happens when an LLM never sees material beyond fifth... by KeplerBoy on Sunday August 16, 2026 @05:04AM (#49318262)
That is in the training data. Confidently and correctly answering in-distribution questions (possiibly with a tool call) is expected by now.
Re:What happens when an LLM never sees material beyond fifth... by pistoriusp on Sunday August 16, 2026 @05:02AM (#49318251)
Aren't you missing OP's point entirely? Which is: If the LLM didn't have useful information it would still give you an answer... Helpful or not.
Re:What happens when an LLM never sees material beyond fifth... by Gud on Sunday August 16, 2026 @05:29AM (#49318392)
Not really, since any LLM will answer all those questions competently. It's a known fact that LLMs sometimes are wrong and hallucinates an answer, but this is exceedingly rare. Having access to a decent LLM is like having an expert with me. Are they always right? No, but the analogy with a two year old simply doesn't hold up.
Re:What happens when an LLM never sees material beyond fifth... by pistoriusp on Sunday August 16, 2026 @05:40AM (#49318466)
> Since any LLM will answer all those questions competently

That's false. The LLM will only answer competently if it was trained on that data; and if it has enough data to make the correct connections between your question and the "correct" answer.

In the case of this article they're specifically saying the LLM has limited training.

Re:What happens when an LLM never sees material beyond fifth... by budsniffer952 on Sunday August 16, 2026 @07:49AM (#49319154)
Look at the responses in this thread and others, arguing with these people is futile.

I now read the absolute dumbest shit on HackerNews when it comes to AI. "It can't write code! It's always wrong!" And no one ever demonstrates any of it, even if it is counter to the experiences of others.

I'd feel bad if most of these people weren't total jerks...

Re:What happens when an LLM never sees material beyond fifth... by throw0101a on Sunday August 16, 2026 @07:05AM (#49318904)
> Not really, since any LLM will answer all those questions competently.

How would you know if it didn't?

Re:What happens when an LLM never sees material beyond fifth... by Gud on Sunday August 16, 2026 @08:27AM (#49319418)
I normally research topics thoroughly, if they are important. I don't trust a single source of truth.
Re:What happens when an LLM never sees material beyond fifth... by throw0101a on Sunday August 16, 2026 @11:02AM (#49320752)
> I don't trust a single source of truth.

A prudent strategy, but I'm not sure how prevalent it is in the general population. (Or even if people do look at multipole "sources", they're in a self-reinforcing echo chamber that may reject contradictory information.)

Re:What happens when an LLM never sees material beyond fifth... by desterothx on Sunday August 16, 2026 @07:07AM (#49318918)
yes, except experts are capable of saying I don't know, while LLMs will rather give any answer than do so most of the time
Re:What happens when an LLM never sees material beyond fifth... by ben_w on Sunday August 16, 2026 @04:07PM (#49323175)
Claude and ChatGPT have between them identified one mystery plant in my garden confidently as about a dozen different things.

Even though they will get chemistry right more often than me, I still wouldn't want to ingest the result of it walking me through that on a drug, psychoactive or otherwise.

Any given answer might be right, but I'm not a trained chemist and don't know how to safely test things.