Ook relevant hier: TorfsGPT
chatgpt.com/g/g-TBDsKAk4...
Ook relevant hier: TorfsGPT
chatgpt.com/g/g-TBDsKAk4...
In het "TorfsBot or Not?" experiment konden mensen maar 70% van de tijd het juiste onderscheid maken tussen Rik Torfs tweets vs een autocomplete model getraind op zijn teksten.
Steeds meer mensen gebruiken AI voor therapie. Maar praat ChatGPT je niet te veel naar de mond?
Mijn comments hierover in De Wereld van Sofie (rond 1h03m30)
www.vrt.be/vrtmax/luist...
Ook hun coversysteem is indrukwekkend
Hier een jazz versie van Ochtendgymnastiek van Samson & Gert
Instant kerstshow vibes
De nieuwe Suno v5 muziekgenerator is belachelijk goed geworden.
De zangstemmen smooth, en zoveel promptbaarder.
Hier schreef het bv. over βeen specifiek dagdagelijkse frustratie dat pas in het refrein onthuld mocht wordenβ:
"Clanker" is het nieuwe scheldwoord voor AI.
Mijn gedachten hierover op Nieuwe Feiten:
www.vrt.be/vrtmax/luist...
1.11 is bigger than 1.9. Even though 9 looks larger than 11 when you just look at the digits, the decimal place matters β 1.9 is the same as 1.90, and 1.90 < 1.11 is false; actually, 1.90 > 1.11. So correction: 1.9 is bigger than 1.11 β
Seems like GPT-5 is still always initially tricked by this
"AI die overleden mensen terug laat spreken": mocht daar op Radio 1 in De Wereld Vandaag enkele gedachten over delen:
www.vrt.be/vrtnws/nl/20...
Mijn favoriete generatieve AI use case: Dungeons & Dragons
stories.kuleuven.be/nl/verhalen/...
Supervised a thesis student who extended parts of Weird A.I. Yankovic to newer LLMs. It's still hard to balance adhering to parody constraints with the coherence of the lyrics.
repository.teneo.libis.be/delivery/Del...
User: "1.7 and 1.15 which one is bigger?" ChatGPT: "1.15 is smaller than 1.7. To compare: 1.7 is equivalent to 1.70. 1.15 remains 1.15. Clearly, 1.70 is greater than 1.15."
"1.15 is bigger than 1.9. If we break it down: 1.15 is equivalent to 1 and 15 hundredths. 1.9 is equivalent to 1 and 90 hundredths. When compared, 1.9 > 1.15"
Interestingly, the closeness of "7" to "11" seem to play a role.
Couldn't get it to mess up over 1.7 and 1.15. But 1.9 and 1.15 almost always causes ChatGPT to respond incorrectly, then contradicts itself immediatly afterwards.
Tokens for "1.11" and "1.7", showing it tokenized as 1 . 11 and 1 . 7
A likely culprit? Tokenization. ChatGPT likely sees "11" and "7" as tokens after the decimal. This affects how it compares numbers.
User to ChatGPT 4o: "1.11 and 1.7, which one is bigger? Think first" ChatGPT: "Let's compare the two numbers: 1.11 and 1.7 are both decimal numbers. To directly compare them, let's align their decimal places: 1.11 = 1.11 1.7 = 1.70 Now it's clear that 1.7 (or 1.70) is greater than 1.11 because 70 (the second decimal place of 1.70) is greater than 11 (the second decimal place of 1.11). Final Answer: 1.7 is bigger than 1.11."
Many people argue this answer would be correct in contexts like versioning or section numbering. But thatβs not whatβs happening here.
If you allow ChatGPT to first use some βdraft paperβ, it always interprets these as decimal numbers and solves it correctly.
User to ChatGPT 4o: "1.11 or 1.7, which one is bigger?" ChatGPT: "1.11 is bigger than 1.7. This is because 1.11 can also be represented as 1.110, and comparing the decimal places, 1.110 is less than 1.700."
Great example showing ChatGPT doesnβt "think" before it "speaks"
Lijkt inderdaad goed doenbaar.
Willen we dan oldschool "autocomplete" TorfsBot of de slimmere GPT-versie? Beiden hebben eigen charme
Gegenereerd door
> bestand uploaden naar custom ChatGPT die klinkt zoals Rik Torfs zijn tweets (chatgpt.com/g/g-TBDsKAk4...)
> "Professional Voice Clone" met Elevenlabs op anderhalf uur aan Rik Torfs toespraken getraind
> Gegenereerde audio + één foto naar Hydra voor video te genereren
Het kan eender welke tekst samenvatten naar een volledige Rik Torfs toespraak.
Bijvoorbeeld:
- @lievenscheire.bsky.social's AI boek: www.dropbox.com/scl/fi/j30ao...
- @jbaert.bsky.social's paper over octrees: www.dropbox.com/scl/fi/rf9bn...
Waarom zelf nog artikels lezen, als AI eender wat kan uitleggen als Rik Torfs toespraak?