ChatGPT lies then gaslights reporter with fake transcript

[TwoSix]

I've always been fascinated by the tendency to characterize AI by its current failings without reasonable regard for what it CAN do or the trajectory it's on. Like, the fact that it can write almost flawless code snippets now or write a pretty good novella in 10 seconds but, yes, still makes a few mistakes you'll have to edit or rerun, means that it's total garbage? Really? Why not something like, "This is quite impressive, still flawed, but clearly advancing at a blistering pace"?

I'm assuming the critique here is something like "Boy, look at the incredible speed and overwhelming mass and crystalline beauty of that asteroid that's about to hit our planet."

 

[Scribe]

I mean, the world adjusts or society collapses. Both are possible solutions.

I’d say the odds are about 60-40, but I’m an optimist.

Yeah, I'm not.

 

[kermit4karate]

If you ever want to have some fun, spend some time asking ChatGPT questions like...

• Assuming continued advancements in AI over the next decade, what are 20 careers that should be relatively safe for humans to pursue?
• From an economic standpoint, is AI a bubble like the dot com bubble was? If not, how is it different?
• What are the biggest obstacles to AI's continued development?
• How did you (ChatGPT) get so much better at drawing hands?
• How did you (ChatGPT) get so much better at math?
• Why do you hallucinate? Can I stop you from doing it through a prompt?
• How close would you say OpenAI is to developing AGI? Are they at the forefront of its development? If not, who is?

 

[Ryujin]

Before AI:
"Hahaha this guy can't do hands"
"I'm still working on it"

and with AI
"Look at how messed up the hands are with AI"

and now AI is depending where you look doing realistic hands and other actions.

To be fair, most human artists don't draw hands with 8 fingers

 

[soviet]

I wanna know how Rob Liefeld got hold of this technology in the 1990s

 

[kermit4karate]

Earlier on this or another thread about AI, someone had mentioned about how bad ChatGPT was at playing chess and offered it as proof of its failure. I thought that was interesting in that, to my knowledge, no one at OpenAI had claimed that it was good at chess. In fact, it's fairly easy to find out how good at chess it is so folks no longer feel the need to misrepresent it. Just ask ChatGPT.

How is something a failure when it openly acknowledges its own limitations? Is ChatGPT the one representing itself as perfect, or are we using that as a straw man to indict it?

​

I asked:​

How good are you at chess? Could you guess and give yourself a rating on the international scale? Could you defeat Magnus Carlson?

ChatGPT said:​

I’m actually pretty good at chess in a very specific way — I can calculate a lot of lines very quickly and use vast amounts of stored opening, middlegame, and endgame knowledge. That makes me feel a bit like a chess engine rather than a human player.

But there are some important caveats:

• No specialized training like Stockfish/AlphaZero
  I’m not trained as a pure chess engine. My “knowledge” of chess positions is based on patterns, games, and analysis I’ve seen, not an optimized evaluation function or millions of node calculations per second.
• Tactics vs. long-term plans
  In raw tactics (short calculations) I’m strong. But for deep positional understanding, recognizing subtle imbalances, and practical decisions under time constraints, a top GM like Magnus Carlsen would crush me.
• Estimated strength
  In casual online play against humans, I’d probably behave like a 2200–2500 Elo player (a strong master / low GM level), depending on how carefully I’m prompted and how much time I’m allowed to “think.”
  By comparison:
  
  • FIDE Master ~2300
  • International Master ~2400
  • Grandmaster ~2500+
  • Magnus Carlsen (peak) ~2882
• Against Magnus Carlsen
  No chance under normal conditions. Even though I can analyze deeply, Magnus is arguably the strongest human ever and extremely good at practical play. Without engine-style calculation power (like Stockfish), I’d lose convincingly.

If you want, I can show you — we could play a few moves right now, and you can see how “strong” I feel at your time control. Would you like me to play as if I’m ~2200, ~2500, or “engine-style” (near perfect) to get a sense?

 

[soviet]

'My phone's autocorrect function gave me bad medical advice'

 

[kermit4karate]

To be fair, most human artists don't draw hands with 8 fingers

It doesn't do that very often anymore. Or draw dogs with 5 paws and 2 tails.

Another fair question would be, "Can most human artists draw 1,000,000 hands a second, 24/7, 365 days a year?"

 

[TwoSix]

It doesn't do that very often anymore. Or draw dogs with 5 paws and 2 tails.

Another fair question would be, "Can most human artists draw 1,000,000 hands a second, 24/7, 365 days a year?"

I don't like my AI to get that handsy with me.

 

[Ryujin]

It doesn't do that very often anymore. Or draw dogs with 5 paws and 2 tails.

Another fair question would be, "Can most human artists draw 1,000,000 hands a second, 24/7, 365 days a year?"

Would they need to? And would they even want to, if it cost them as much as it would to power a mid-sized city?