Subject: Re: [xsl] bad code Re: Subject: ChatGPT results are "subject to review" From: "Dimitre Novatchev dnovatchev@xxxxxxxxx" <xsl-list-service@xxxxxxxxxxxxxxxxxxxxxx> Date: Fri, 7 Jul 2023 18:04:41 -0000 |
> Which begs the question, how might the xsl-list archives be ... > declared / converted / made available (whatever) as training data? > And for this set (minor drawback), how to extract the 'eventual' > solution from others proffered in error? This isn't just "minor". People who analyze the current state of AI have pointed out an emerging and possibly growing problem for AI: "The AI boom might be approaching a flashpoint where these models canbt avoid consuming their own output, leading to a gradual decline in their effectiveness. This will only be accelerated as AI-generated content perfuses the internet over the coming years, making it harder and harder to source genuine human-made content." from: "AI Is Facing A Seriously Huge Problem The AI echo chamber has started to ring.", Will Lockett https://medium.com/predict/ai-is-facing-a-seriously-huge-problem-a56733e5ef47 On Fri, Jul 7, 2023 at 6:35b/AM Dave Pawson dave.pawson@xxxxxxxxx < xsl-list-service@xxxxxxxxxxxxxxxxxxxxxx> wrote: > On Fri, 7 Jul 2023 at 14:26, Dorothy Hoskins dorothy.hoskins@xxxxxxxxx > <xsl-list-service@xxxxxxxxxxxxxxxxxxxxxx> wrote: > ... > > From what I see in the list of ChatGPT Code languages, it wasn't > specifically trained on XSLT, so someone who builds their own training > set will get better results. You folks probably have the best training > examples in the world in the xsl-list.) > > Which begs the question, how might the xsl-list archives be ... > declared / converted / made available (whatever) as training data? > And for this set (minor drawback), how to extract the 'eventual' > solution from others proffered in error? > > > > > I don't think there's any going back, so the chances of people creating > code that won't run, that they can't debug themselves and which ChatGPT may > not provide the correction required if prompted, is high. > > And from your earlier comments, the more experience in writing xslt, > the more likely you'll arrive at a solution using AI? > > > > > Michael, I wonder what "nasty accidents" you are thinking of -- some > XSLTs used in particular industries with real-world safety issues? Maybe we > can start to create some advice for clients on QA and testing protocols. > Is it logical to say that chatGPT will be just as easy to trip up as > the man on the Clapham omnibus? > > regards > > ps. Tried google.bard with UK braille. Bit of a dogs breakfast. > > > > > > > > -- > Dave Pawson > XSLT XSL-FO FAQ. > Docbook FAQ.
Current Thread |
---|
|
<- Previous | Index | Next -> |
---|---|---|
Re: [xsl] bad code Re: Subject: Cha, Martynas Jusevičius | Thread | Re: [xsl] bad code Re: Subject: Cha, John Lumley john.lum |
Re: [xsl] bad code Re: Subject: Cha, Michael Kay mike@xxx | Date | Re: [xsl] bad code Re: Subject: Cha, Liam R. E. Quin liam |
Month |