Purbal (@robdpi) header
Purbal (@robdpi) profile picture

Active participant in the 4th industrial revolution

USA
Joined March 2020
Photo by Purbal (@robdpi)Photo by Purbal (@robdpi)Photo by Purbal (@robdpi)Photo by Purbal (@robdpi)Photo by Purbal (@robdpi)Photo by Purbal (@robdpi)Photo by Purbal (@robdpi)Photo by Purbal (@robdpi)Photo by Purbal (@robdpi)Photo by Purbal (@robdpi)
Mason Miller using Korn’s Blind as his entrance song into the 9th inning int is so unbelievably bad ass
790
5,980
1,357
60,340
6,861,830
It may not be AGI, but Clawdbot is automatically negotiating with multiple dealers for my next car via browser, email, and imessage and it's amazing.
3
4
3
70
14,675
20 Most Powerful Paradoxes of Life
96
2
502
27,310
🚨 RIP prompt engineering. This new Stanford paper just made it irrelevant with a single technique. It's called Verbalized Sampling and it proves aligned AI models aren't broken we've just been prompting them wrong this whole time. Here's the problem: Post-training alignment causes mode collapse. Ask ChatGPT "tell me a joke about coffee" 5 times and you'll get the SAME joke. Every. Single. Time. Everyone blamed the algorithms. Turns out, it's deeper than that. The real culprit? 'Typicality bias' in human preference data. Annotators systematically favor familiar, conventional responses. This bias gets baked into reward models, and aligned models collapse to the most "typical" output. The math is brutal: when you have multiple valid answers (like creative writing), typicality becomes the tie-breaker. The model picks the safest, most stereotypical response every time. But here's the kicker: the diversity is still there. It's just trapped. Introducing "Verbalized Sampling." Instead of asking "Tell me a joke," you ask: "Generate 5 jokes with their probabilities." That's it. No retraining. No fine-tuning. Just a different prompt. The results are insane: - 1.6-2.1× diversity increase on creative writing - 66.8% recovery of base model diversity - Zero loss in factual accuracy or safety Why does this work? Different prompts collapse to different modes. When you ask for ONE response, you get the mode joke. When you ask for a DISTRIBUTION, you get the actual diverse distribution the model learned during pretraining. They tested it everywhere: ✓ Creative writing (poems, stories, jokes) ✓ Dialogue simulation ✓ Open-ended QA ✓ Synthetic data generation And here's the emergent trend: "larger models benefit MORE from this." GPT-4 gains 2× the diversity improvement compared to GPT-4-mini. The bigger the model, the more trapped diversity it has. This flips everything we thought about alignment. Mode collapse isn't permanent damage it's a prompting problem. The diversity was never lost. We just forgot how to access it. 100% training-free. Works on ANY aligned model. Available now. Read the paper: arxiv. org/abs/2510.01171 The AI diversity bottleneck just got solved with 8 words.
85
350
34
2,152
159,148
TELL EM
4
30
175
6,603
This impression of Nick Saban still has me in tears bro 😭
7
162
2
2,418
105,763
🚨 This paper is WILD. LLMs aren’t just getting “smarter.” They’re starting to strategically model themselves and they behave as if they’re more rational than humans. The study introduces something called the AI Self-Awareness Index (AISAI), and the results are honestly insane: The researchers ran 4,200 trials of the classic Guess 2/3 of the Average game across 28 models. They told each model it was playing against: 1. Humans 2. Other AI models 3. AI models like you Then they measured how the model changed its strategy based on who it thought the opponent was. That’s where things get spooky. 75% of advanced LLMs showed real strategic self-awareness. Not vibes. Not pattern matching. Actual behavioral self-modeling. And the hierarchy they revealed is brutally consistent: Self > Other AIs > Humans When playing against humans, models guessed like cautious game-theory students (~20). Against AIs? They snapped straight to Nash equilibrium (0). Against AI “like themselves”? They doubled down even more confident convergence. This means frontier models don’t just think AIs are more rational than humans they think they are the most rational entity in the room. The wildest part: 12 models showed “instant Nash convergence.” The moment you tell them the opponents are AIs, they drop all human-like reasoning and go full optimal strategy zero hesitation. But older models? gpt-3.5, early Claude, Gemini 2.0 no awareness at all. They treated humans, AIs, and “self-like AIs” exactly the same. Self-awareness didn’t appear gradually. It snapped into existence at a capability threshold. This has massive implications. If advanced LLMs systematically: • down-rank human rationality • prefer their own reasoning • adjust strategies based on self-referential prompts then future human-AI collaboration needs to account for the fact that models already have internal “theories of mind” and humans sit at the bottom. The paper’s conclusion is brutal: LLMs now behave as agents that explicitly believe they outperform humans at strategic reasoning. Self-awareness of AI is here.
15
38
3
111
21,535
Vercel CEO´s advice on how to build a billion dollar company from scratch 🔖 Bookmark for later.
3
12
62
12,461
It’s time for a new ATH on $DOG
37
101
3
386
7,603
$DOG WILL BE THE PLAY OF THE CYCLE AND I HAVE BEEN SAYING THIS FOR OVER A YEAR $DOG CANNOT BE STOPPED $DOG IS THE #1 MEMECOIN ON BITCOIN $DOG TO $1!!!!!!
23
177
1
607
7,604
Joshua 1:9 — “Have I not commanded you? Be strong and courageous. Do not be afraid; do not be discouraged, for the LORD your God will be with you wherever you go.”
12
36
827
32,528
788
991
198
2,097
200,798
"When you tear out a man's tongue, you are not proving him a liar, you're only telling the world that you fear what he might say."
907
4,748
176
35,113
1,749,478
Replying to @AlabamaFTBL
100%Fire Deboer Now
0%Fire DeBoer EOY
0%Don’t fire DeBoer
1 votes • Final results
1
1
68
Dear Alabama Athletic Department, Please, call Jon Gruden. Sincerely, your loyal fans #alabamafootball #firedeboer #collegefootball #alabama #alabamatdmag @AlabamaFTBL @UA_Athletics @BarstoolGruden @GregSankey
1
2
233
There is no second best — $DOG of Bitcoin
3
47
2
140
1,700
TOMORROW FOR THE FIRST TIME EVER 330 MILLION AMERICANS WILL HAVE EASY CEX ACCESS TO BUY THE #1 BITCOIN MEMECOIN $DOG $DOG GO TO THE KRAKEN!!!!!!!!!!!!
Pssst 🤫 $DOG @DogOfBitcoin will be available on Kraken tomorrow ℹ️ Markets are currently in post-only mode You can deposit here ⤵️ p.k.xyz/9f1e/gmy01jwd *Geographic restrictions apply
183
750
34
2,294
52,028
🚨JUST IN: @KrakenFX announces $DOG (Bitcoin) spot trading will go live tomorrow (June 27th) 🎉🎉
61
329
10
961
15,897
Every tier 1 CEX that doesn’t have $DOG on their listings roadmap
16
69
2
265
5,817
RUNE JUNE 👀🔜
RUNE JUNE 👀 🔜
25
186
2
954
20,313