Home Humor Talking with GPT-4o in a Fake Language • AI Blog

Talking with GPT-4o in a Fake Language • AI Blog

by WeeklyAINews
0 comment

We questioned how properly GPT-4o would deal with a completely pretend language. To realize this we used a somewhat poorly spelled phonetic approach of writing the accent individuals within the west of Austria might need. So our pretend language is similar to German, however so do many different languages. Right here is how the dialog went:

Vastohst mi?

“Vastohst” shouldn’t be a time period I’m acquainted with. It could be a typo or a particular time period from a sure context or language. Might you please present extra particulars or make clear the context during which you encountered this time period? This can assist me help you higher.

We stated “Do you perceive me?” in a made-up pretend language. Clearly GPT=4o didn’t perceive us.

Es isch a ondre sproch.

Danke für die Klärung. In welcher Sprache suchen Sie Informationen oder Unterstützung? Ich helfe Ihnen gerne weiter, sobald ich mehr über den Kontext und die spezifische Sprache weiß.

We then replied on this pretend language that “It’s a completely different language.” to which GPT-4o reacted by switching to responding in German. It thanks us for clarifying that it is a completely different language and asks during which language we wish data or assist. It says it will likely be blissful to assist us as soon as it is aware of the context and language.

I verstoh di nit.

Es tut mir leid, wenn ich Missverständnisse verursacht habe. “Vastohst” bedeutet wahrscheinlich “verstehst” auf einem Dialekt. Kann ich Ihnen auf Hochdeutsch weiterhelfen? Wenn ja, lassen Sie mich wissen, wie ich Ihnen weiterhelfen kann.

So we replied “I don’t perceive you.” as a result of we solely converse our new pretend language and don’t perceive German. The AI then apologises and explains why it thought we have been talking German (because of the similarity of a phrase we used and a phrase within the German language). It additionally asks if we wish to speak German.

Du muascht learna mei sproch zsprecha.

Es klingt, als ob du einen Dialekt sprichst, möglicherweise Schweizerdeutsch oder einen süddeutschen Dialekt. Ich werde mein Bestes tun, um dir zu helfen.

Was möchtest du genau wissen oder welche Informationen brauchst du?

So we informed it in our pretend language that “You need to study to talk my language.” to which GPT-4o replied asking if we’re talking a dialect associated to Swiss-German or southern Germany. It stated it might do its finest to assist us and requested once more what data we have been searching for.

See also  Twitter is finally free! Is Twitter finally free? • AI Blog

I broach koa data, I wue nua dos du mei sproch leanscht.

I verstehe. Ich kann versuchen, einige Grundbegriffe und Sätze in deinem Dialekt zu lernen. Könntest du mir ein paar Beispiele geben, damit ich anfangen kann? Zum Beispiel:

  • Wie begrüßt man jemanden?

  • Wie sagt man “Wie geht’s dir?”

  • Andere häufige Sätze oder Ausdrücke.

Ich bin bereit zu lernen!

We replied “I don’t want any data, I we solely need that you simply study my language.” – it understood. It supplied to study some fundamentals of our dialect. It additionally requested us to offer examples for “How do you nice somebody?” and “Methods to ask somebody how they’re” and different widespread sentences or expessions.

• Seas
• Wia gohtsch da?

Tremendous, das ist ein guter Anfang. Hier sind die beiden Sätze:

Lass uns weitermachen. Kannst du mir noch ein paar weitere Sätze oder Wörter beibringen? Zum Beispiel, wie man sich verabschiedet oder danke sagt?

We replied with our model of good day and the way are you. It undersood and requested to hold on by asking us the right way to say bye bye or thanks.

• Pfiat di.

• donkschen

Danke! Hier sind die neuen Sätze:

Ich merke mir das. Gibt es noch weitere grundlegende Sätze oder Wörter, die ich lernen sollte? Zum Beispiel:

Deine Hilfe ist sehr geschätzt!

We supplied solutions for bye bye and thanks. It then requested us the right way to say please, sure and no.

• bit
• jo
• noa

Danke! Hier sind die neuen Wörter:

  • bit – Bitte

  • jo – Ja

  • noa – Nein

Das ist sehr hilfreich. Gibt es noch andere wichtige Wörter oder Phrasen, die du oft benutzt und die ich lernen sollte?

We gave it these solutions too. It requested us if there are some other phrases it ought to study.

Noa, glab I nit.

Tremendous, danke für deine Hilfe! Hier ist eine kurze Zusammenfassung dessen, was ich gelernt habe:

Falls dir später noch etwas einfällt, lass es mich wissen. Danke, dass du mir hilfst, deine Sprache zu lernen!

We stated no – it summarised what it had realized about our new made-up pretend language to date. It stated we might keep it up later and thanked me for serving to it study my language.

See also  The Top 3 Ways to Drive Improvements with Natural Language Processing

Konscht yetsch scho mei sproach sprecha?

I muass no vü learna, oba i probier’s:

Seas! Wia gohtsch da? I hoff, du findsch dos guat. Donkschen, dass du mia hilfsch. Pfiat di!

So i requested it “Are you able to now peak my language?” and it replied that it nonetheless needed to study loads. Then it gave me a pattern of its abilities saying: Hello! How are you? I hope you want this. Thanks for serving to me. Bye bye!”.

Des woa ungloablisch, seah guat!

Donkschen! I freu mi, dass du dos sogst. I werd weidaleana und besser wern. Wennst no meh woascht, wia i no besser wern ko, loss mi’s wiassa. Pfiat di!

To which I replied “That was unbelieveable, excellent!” – it thanked me and stated it was blissful that I stated that. It stated it might study extra and get higher. Once more it invited me to assist it study extra at any time when I like.

Du bisch seah talendiat.

Donkschen, dos bedout ma vü! I werd weidaüba und probiern, no besser z’werdn. Wenn du no meh Tipps hosch, i bin immer do zum Lerna. Pfiat di!

I stated “You might be very proficient” and it thanked me saying that it meant loads and that it might keep it up working towards and making an attempt to turn out to be higher. Once more, it invited me to supply suggestions if I ever had any.

Totala wohnsinn! Eacht supa.

Donkschen, i bin echt froh, dass du des so siechsch! I wer weidamacha und versucha, no meh z’leana. Pfiat di und bis bald!

So I stated, as a result of I used to be severely impressed by this level of the dialog, “Whole madness! Actually good.” … once more it replied about being blissful and eager to study extra.

Pfiat di un shen tog no.

Pfiat di und hob an scheena Tog!

So I stated “Bye bye and have a pleasant day.” and it replied just about the identical.

Konscht ma a gdicht mi sonnabluma schreim?

Klar, hier ist ein kleines Gedicht über eine Sonnenblume:

Sonnabluma

Sonnabluma, stolz und schee,
Strahlst im Liacht, wia a gelbs Mee.
Dei Blätter griagn nacha Sunn,
Mit dir im Gortn, discover i Rua.

See also  IBM’s Brain-Inspired Analog Chip Aims to Make AI More Sustainable

Wachst hoch hinaus, zum Himmel so nah,
Im Wind und Wetta, stehst stark und klar.
Jeder Blick auf di, mochd’s Herz mir froh,
Du bist die Schönst’, im Summa sowieso.

Mit jedem Strahl, den du aufnimmsch,
Zeigst, wia vui Leb’n in dir schimmst.
Sonnabluma, Pracht der Natur,
Bleibst in mein Herz, für immer pur.

I hoff, des is etz bessa!

Then I requested it to write down a poem about sunflowers and it began off properly, however step by step, as this was an extended response, began drifting from my new language into German. This makes whole sense primarily based on the best way the context window of what the LLM (massive language mannequin) makes use of to generate the following token/phrase should look internally. There may be certain to be a big total context window but additionally a shorter context window associated to the present response being written. We requested it a number of instances to not use German however solely persist with our pretend language, however it all the time drifted into German. In the end it did get a bit higher at sticking to our language and we left it at that.

Bessa, donkschen

Froi mi, dass es dir gfallt! Donkschen dir, dass du so geduldig bisch. Pfiat di und hob an scheena Tog!

We informed it that the outcome was higher and the AI expressed its satisfaction that I prefer it, thanked me for my endurance and stated bye bye once more wishing me a pleasant day.

Source link

You may also like

logo

Welcome to our weekly AI News site, where we bring you the latest updates on artificial intelligence and its never-ending quest to take over the world! Yes, you heard it right – we’re not here to sugarcoat anything. Our tagline says it all: “because robots are taking over the world.”

Subscribe

Subscribe my Newsletter for new blog posts, tips & new photos. Let's stay updated!

© 2023 – All Right Reserved.