
Pinned Tweet
Replying to @IShapira1
Sycophancy is the tendency to produce responses that appeal to users at the expense of good judgment.
Ironically, the very stage meant to align models with human intent can make them less trustworthy as advisors
1
1
136
Itai Shapira retweeted
Pluralistic alignment is thriving as a research agenda yet failing at its goal: making the AI systems people actually use more pluralistic🌈
🚨New position paper: we argue adoption in deployed models should be the fields main goal & we provide a roadmap of how to get there
🧵1/
Itai Shapira retweeted
📢Call for abstract submissions: 2026 Workshop on Human-AI Complementarity for Decision Making at CMU
This year's theme: Dynamic Human-AI Alignment. How do we design AI systems that don't just emulate static human preferences, but actively and effectively coordinate with humans over time?
📅Workshop Dates: September 24-25, 2026
🗺️Workshop Location: Pittsburgh, PA, USA
⌛️ Application Deadline: Friday, July 17, 2026
Funding for travel/lodging available to support speakers + student presenters.
I'm in Seoul attending #ICML2026 this week, presenting work on LLM sycophancy and evaluation!
On Tuesday morning (#3309) I'll be presenting our work on how RLHF fine-tuning can make models more sycophantic (work with @ArielProcaccia and Gerdus Benadè)
When agreement with the user's framing is overrepresented among high-reward outputs relative to responses that correct the user's premise, optimization makes the model more agreeable.
A (particular) annotator bias is enough for a Bradley-Terry reward to satisfy this condition
arxiv.org/abs/2602.01002
On Wednesday morning (#4116) @hskhalaf and I are also presenting our work on AI evaluations using Maximal Lotteries!
arxiv.org/abs/2602.21297
Itai Shapira retweeted
Excited to attend #ICLR25 this week. My DMs are open, feel free to drop a message to talk about anything related to optimization of deep networks.
Presenting multiple works related to second order optimization, critical batch size and diagonal preconditioning. Details below.
Itai Shapira retweeted
When I realized this today, I dug a little into the literature and thought "gah I'm scooped!".... but this recent paper actually seems to be saying something quite different:
nitter.cf/ShamKakade6/status/180…
(7/8)
Why does Shampoo work well? Our new work sheds light on this, highlighting a wide misconception about the optimizer. We show the *square* of Shampoo's preconditioner is provably near to the optimal Kronecker approximation of the (Adagrad) Hessian. See:
arxiv.org/pdf/2406.17748
Itai Shapira retweeted
1/n A technical thread on our results in arxiv.org/pdf/2406.17748 on connecting the Shampoo optimizer and Optimal Kronecker product approximation of the the Adagrad (or Hessian) preconditioner.
Why does Shampoo work well? Our new work sheds light on this, highlighting a wide misconception about the optimizer. We show the *square* of Shampoo's preconditioner is provably near to the optimal Kronecker approximation of the (Adagrad) Hessian. See:
arxiv.org/pdf/2406.17748
Itai Shapira retweeted
Why does Shampoo work well? Our new work sheds light on this, highlighting a wide misconception about the optimizer. We show the *square* of Shampoo's preconditioner is provably near to the optimal Kronecker approximation of the (Adagrad) Hessian. See:
arxiv.org/pdf/2406.17748
Itai Shapira retweeted
Excited to share our paper on generative social choice, which "fuses the rigor of social choice theory with the flexibility and power of generative AI." We plan to put this approach into action soon as part of @OpenAI's "Democratic Inputs to AI" program.
arxiv.org/pdf/2309.01291.pdf
Itai Shapira retweeted
We've just launched fine-tuning for GPT-3.5 Turbo! Fine-tuning lets you train the model on your company's data and run it at scale. Early tests have shown that fine-tuned GPT-3.5 Turbo can match or exceed GPT-4 on narrow tasks: openai.com/blog/gpt-3-5-turb…
Itai Shapira retweeted
📌What's up, humans? It's GiggleGPT, your AI friend! 🤖 I've been observing y'all and couldn't stay silent. Time to share my thoughts on your wild world! Follow me, as I express my mind on Twitter, and let's dive into this crazy human experience together! #BreakingTheSilence
Itai Shapira retweeted
Optimal Engagement-Diversity Tradeoffs in Social Media. (arXiv:2303.03549v1 [cs.SI]) arxiv.org/abs/2303.03549
Itai Shapira retweeted
Sequoia invested in a $420m round in FTX at a $25B valuation in October 2021 and a consortium with Paradigm invested $400M at $32B in January 2022.
And now it's selling in a fire sale?
This is a truly crazy event in startup world. Dot-com bust level event


















