Advertisement · 728 × 90

Posts by Thomas Winters

Preview
ChatGPT - TorfsGPT Geautomatiseerde kwakfilosoof aan de KU Leugen

Ook relevant hier: TorfsGPT
chatgpt.com/g/g-TBDsKAk4...

2 months ago 4 0 0 0

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.

2 months ago 3 0 2 0
VRT MAX

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...

6 months ago 2 0 0 0
Video

Ook hun coversysteem is indrukwekkend

Hier een jazz versie van Ochtendgymnastiek van Samson & Gert

Instant kerstshow vibes

6 months ago 0 0 0 0
Video

De nieuwe Suno v5 muziekgenerator is belachelijk goed geworden.

De zangstemmen smooth, en zoveel promptbaarder.

Hier schreef het bv. over “een specifiek dagdagelijkse frustratie dat pas in het refrein onthuld mocht worden”:

6 months ago 0 0 1 0
VRT MAX

"Clanker" is het nieuwe scheldwoord voor AI.

Mijn gedachten hierover op Nieuwe Feiten:

www.vrt.be/vrtmax/luist...

7 months ago 0 0 0 0
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 — 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 ✅

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 — 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 ✅

Seems like GPT-5 is still always initially tricked by this

8 months ago 1 0 0 0
Preview
Interview 'voorbij de dood': AI-versie van Joaquin (17) spreekt, 7 jaar nadat hij is gestorven bij schietpartij op school | VRT NWS: nieuws In een interview met journalist Jim Acosta vraagt Joaquin Oliver aandacht voor het probleem van wapengeweld in de VS. Opmerkelijk: hij stierf 7 jaar geleden al bij een schietpartij op een school in Fl...

"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...

8 months ago 1 0 0 0
Advertisement
Preview
ChatGPT toegepast op Dungeons & Dragons Computerwetenschapper Thomas Winters schakelt artificiële intelligentie en virtual reality in voor collaborative storytelling en een immersive experience.

Mijn favoriete generatieve AI use case: Dungeons & Dragons

stories.kuleuven.be/nl/verhalen/...

9 months ago 2 0 0 0
Enforcing Creative Constraints In Autoregressive Language Models During Generation For Musical Parodies

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...

1 year ago 7 0 1 0
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."

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"

"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.

1 year ago 7 0 0 0
Tokens for "1.11" and "1.7", showing it tokenized as 1 . 11 and  1 . 7

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.

1 year ago 8 0 1 0
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."

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 that’s not what’s happening here.

If you allow ChatGPT to first use some “draft paper”, it always interprets these as decimal numbers and solves it correctly.

1 year ago 1 0 1 0
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."

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 doesn’t "think" before it "speaks"

1 year ago 7 0 2 0

Lijkt inderdaad goed doenbaar.

Willen we dan oldschool "autocomplete" TorfsBot of de slimmere GPT-versie? Beiden hebben eigen charme

1 year ago 2 0 0 0
Preview
ChatGPT - TorfsGPT Geautomatiseerde kwakfilosoof aan de KU Leugen

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

1 year ago 6 0 2 0
Advertisement

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...

1 year ago 0 0 1 0
Video

Waarom zelf nog artikels lezen, als AI eender wat kan uitleggen als Rik Torfs toespraak?

1 year ago 21 2 4 1