21–30 of 233 posts
It’s not really hallucinating though, is it? It’s repeating a pattern in its training data, which is wrong but is presented in that training data (and by the author of this piece, but unintentionally) as being the solution to the problem. So this has more in common with an attack than a hallucination on the LLM’s part.
It’s not really hallucinating though, is it? It’s repeating a pattern in its training data, which is wrong but is presented in that training data (and by the author of this piece, but unintentionally) as being the solution to the problem. So this has more in common with an attack than a hallucination on the LLM’s part.
So anyone can make up some random syntax/fact and post it once, and in some cases the model will take it as truth. I don't know if there's a widely agreed-on definition of "hallucination", but if this isn't one, then the distinction is meaningless imo.
https://www.tomshardware.com/tech-industry/artificial-intell...
It’s not really hallucinating though, is it? It’s repeating a pattern in its training data, which is wrong but is presented in that training data (and by the author of this piece, but unintentionally) as being the solution to the problem. So this has more in common with an attack than a hallucination on the LLM’s part.
No, it’s presented in the training data as an idea for an interface - the LLM took that and presented it as an existing solution.
ChatGPT used to assure me that you can use JS dot notation to access elements in a Python dict. It also invented Redocly CLI flags that don't exist. Claude sometimes invents OpenAPI specification rules. Any time I ask anything remotely niche, LLMs are often bad.
Yeah this is so common that I've already compiled a mental list of prompts to try against any new release. I haven't seen any improvement in quite a long while now, which confirms my belief that we've more or less hit the scaling wall for what the current approaches can provide. Everything new is just a microoptimization to game one of the benchmarks, but real world use has been identical or even worse for me.
It would never get the answer right. Often transposing the scores, getting the game location wrong and on multiple occasions saying a 38-38 draw was an England win.
As in literally saying " England won 38-38"
ChatGPT used to assure me that you can use JS dot notation to access elements in a Python dict. It also invented Redocly CLI flags that don't exist. Claude sometimes invents OpenAPI specification rules. Any time I ask anything remotely niche, LLMs are often bad.
I once asked Perplexity (using Claude underneath) about some library functionality, which it totally fabricated. First, I asked it to show me a link to where it got that suggestion, and it scolded me saying that asking for a source is problematic and I must be trying to discredit it. Then after I responded to that it just said “this is what I thought a solution would look like because I couldn’t find what you were as…
ChatGPT used to assure me that you can use JS dot notation to access elements in a Python dict. It also invented Redocly CLI flags that don't exist. Claude sometimes invents OpenAPI specification rules. Any time I ask anything remotely niche, LLMs are often bad.
Well, it makes sense. The smaller the niche, the lesser weight in the overall training loss. At the end of the day, LLMs are (literally) classifiers that assign probabilities to tokens given some previous tokens.
ChatGPT used to assure me that you can use JS dot notation to access elements in a Python dict. It also invented Redocly CLI flags that don't exist. Claude sometimes invents OpenAPI specification rules. Any time I ask anything remotely niche, LLMs are often bad.
Sometimes humans “hallucinate” in a similar way - their memory mixes up different programming languages and they’ll try to use syntax from one in another… but then they’ll quickly discover their mistake when the code doesn’t compile/run
Earlier quoted context omitted.
I once asked Perplexity (using Claude underneath) about some library functionality, which it totally fabricated. First, I asked it to show me a link to where it got that suggestion, and it scolded me saying that asking for a source is problematic and I must be trying to discredit it. Then after I responded to that it just said “this is what I thought a solution would look like because I couldn’t find what you were as…
It baffles me how the LLM output that Google puts at the top of search results, which draws on the search results, manages to hallucinate worse than even an LLM that isn't aided by Web results. If I ask ChatGPT a relatively straightforward question, it's usually more or less accurate. But the Google Search LLM provides flagrant, laughable, and even dangerous misinformation constantly. How have they not killed it off…
It’s a public service: helping the average person learn that AI can’t be trusted to get its facts right