Register and share your invite link to earn from video plays and referrals.

Search results for Metacognition
Metacognition community
One keyword maps to one global community path.
Create community
People
Not Found
Tweets including Metacognition
Skills that have nothing to do with money but are worth dedicating an immense amount of practice to: - Charisma - Metacognition - Critical thinking - Sitting with discomfort - Articulating what you believe and why - Changing your beliefs when presented with new information Almost nobody actually practices these and it shows.
Show more
0
259
8.6K
957
Forward to community
Schmidhubers argument for consciousness in LLMs: - the one constant in training and during RL rollouts that influences the next token prediction is the model itself, so models should learn to model themselves to better predict what comes next claiming that this results in conscious AI is silly I think at best this gives you self-awareness/some metacognition which models already have, but not consciousness
Show more
I also had the chance to test the early access version of GPT 5.6 Sol. After spending time with both models, I think they excel in very different ways. Fable 5 stands out because of the intelligence that comes from its sheer model scale. It constantly surprises you with unexpected directions, proposes alternative approaches, and even refines your ideas before you ask. It feels highly metacognitive, with rich language, expressive writing, and a broad way of thinking. In many ways, it reminds me of the feeling I had when GPT-4.5 first arrived. GPT 5.6 Sol feels completely different. I'm not sure I'd describe it as having the same level of metacognition, but when you give it a concrete problem, it becomes incredibly persistent about finding the best possible solution. It doesn't wander—it stays focused. Where Sol really shines is structured execution. If the workflow is clear, it follows it almost perfectly, breaking complex tasks into logical steps, creating sub-agents when appropriate, and systematically solving the problem from start to finish. It feels less like a creative collaborator and more like a dedicated research engineer. Because of that, I think GPT 5.6 Sol is the ideal model when you already know the problem you're trying to solve. Give it a research paper, a technical specification, or a difficult engineering task, and it feels like it'll keep working until it's implemented correctly. The persistence, execution quality, and overall performance are genuinely impressive. The main reason I kept using Fable was its expansive thinking, writing style, and frontend generation capabilities. But if my goal is coding or solving difficult engineering problems, GPT 5.6 Sol would very naturally become my primary model. And at this point, with AGENTS.md and Skills, we already have the tools to teach GPT the workflows and reasoning patterns we want. Sol follows those instructions with remarkable consistency, which makes it an exceptionally strong foundation for agentic coding.
Show more
What AI scientists may be missing is the ability to know what they don't know. Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery 🔭 Overview An architecture that adds a metacognitive layer to a scientific-discovery AI, monitoring and controlling the search itself. 🧩 The problem Earlier AI scientist systems fail to retain findings, evidence and applicability conditions across search branches. They can overlook shared dependencies and past failures, and overreact to recent outcomes. ⚙️ The approach ・The search side has a Target Tree (question decomposition), an Idea Graph (idea lineage) and an Evidence State (sourced evidence) ・The regulation side keeps a Cognitive State of current understanding and uncertainty, and picks next moves from ten heuristics 🧪 Results On the authors' own Taiyi-Bench (265 tasks, 10 disciplines) it scores 54.0 overall vs 47.9 for the strongest baseline, AI Scientist-v2, with a 66.3% pairwise win rate. 🔬 Use cases In five expert-collaborative cases, for example, a photocatalytic allylic amination yield rose from 13% to 69%. Note that scoring relies on the same authors' benchmark and an LLM verifier, and the cases are individual examples. #AIScientist# #Metacognition#
Show more
What should a search agent learn from when deciding whether to search? 🔎 Search When Needed, Proceed When Reliable: Metacognitive Reliability Supervision for Efficient Agentic Search ❓ What goes wrong when the reward is just final-answer correctness? 💡 A lucky guess, a correct answer with needless searches, and a wrong answer after useful retrieval all look alike, so the reward says little about each search decision. That leads to under-searching on unreliable states and over-searching on reliable ones. ❓ What does this paper reward instead? 💡 The estimated reliability of the intermediate conclusions the model writes at each step. Uncertainty is the mean negative log-likelihood of the tokens, and a mapping fitted beforehand on sampled data turns it into a reliability score. ❓ How are search and no-search decisions scored? 💡 ・If the agent proceeds without searching, the score is its current reliability minus a calibration reference ・If it searches, the score is reliability with the retrieved evidence minus reliability without it The average becomes a process reward added to GRPO. Probing is used only in training, so inference has no extra cost. ❓ How well does it work? 💡 With Qwen2.5-7B it averages 69.3 CEM over seven QA benchmarks, versus 67.2 for the strongest baseline, HiPRAG, with 1.64 searches per question (6.8% fewer). Multi-hop searches rise about 6.6%, and training is about 14.6% slower per step. #AgenticRAG# #ReinforcementLearning#
Show more