What the smart people are recommending. 8874 books, tools, and products endorsed by the thinkers absorb.md tracks. Ranked by how many times each has been recommended across compiled podcasts, papers, posts, and tweets.
“Compared to a simpler model that only used the question stem and the key, our best distractor-aware architecture achieved higher predictive performance”
“An order-invariant variant achieved nearly the same accuracy with approximately half as many parameters, offering a favorable accuracy-efficiency trade-off”
“we propose a novel end-to-end semantic change detection network named SemDINO”
“ShallowBench therefore provides a rigorous benchmark for generative biology models and highlights the necessity of new architectural innovations or loss functions capable of navigating these challengi…”
“We evaluate the proposed flow using a Tensor Slice-based FPGA architecture with AMD Vitis HLS and the Verilog-to-Routing (VTR) toolchain.”
“We evaluate the proposed flow using a Tensor Slice-based FPGA architecture with AMD Vitis HLS and the Verilog-to-Routing (VTR) toolchain.”
“In this paper, we propose a method called Capability-Aligned Hierarchical Learning (CAHL), which leverages RLVR to jointly optimize both policies, enabling better alignment between the high-level plan…”
“we recommend macro-averaged F1 as the standard reporting metric for ZSL-HAR benchmarks”
“We propose a framework, called piecewise-linear Karush--Kuhn--Tucker hard-constrained PINNs (PL-KKT-hPINNs), that strictly enforces nonlinear equality constraints through piecewise-linear projection.”
“This extends the KKT-hPINN framewor, which exactly enforces linear equalities through the Karush--Kuhn--Tucker (KKT) conditions associated with orthogonally projecting neural network outputs onto the …”
“We observe that the strongest agents, Claude Opus 4.6 and GPT-5.4 xhigh, often avoid writing the target language directly.”
“We observe that the strongest agents, Claude Opus 4.6 and GPT-5.4 xhigh, often avoid writing the target language directly.”
“In contrast, Opus-derived Python helper code for building generators, with no solved benchmark programs or hidden-test answers, sharply improves Sonnet 4.6 and GPT-5.4 mini on the same problems, while…”
“there's still more work to be done to scale AI models”
“In contrast, Opus-derived Python helper code for building generators, with no solved benchmark programs or hidden-test answers, sharply improves Sonnet 4.6 and GPT-5.4 mini on the same problems, while…”
“This article uses Moonshine's exploration of the Jacobian conjecture as an example.”
“By invoking GPT-5.5-pro and DeepSeek-V4-pro separately, Moonshine obtained independent complete proofs for the case \(N=n+1\).”
“By invoking GPT-5.5-pro and DeepSeek-V4-pro separately, Moonshine obtained independent complete proofs for the case \(N=n+1\).”
“This work presents Earth-OneVision, a 2B RS-MLLM that unifies six sensor modalities (i.e., optical, SAR, infrared, multispectral, temporal, and video) and cross-sensor fusion across 9 task categories …”
“To support joint training, MMRS-OneVision is constructed with ~34M QA pairs spanning all six sensor modalities and cross-sensor fusion across 9 task categories, substantially exceeding existing RS mul…”
“we introduce PhysTool-Bench, the first physical tool-use benchmark designed to evaluate MLLMs' ability to comprehend real-world scenarios, identify physical tools, and plan their use”
“We propose ADAS, a training-free reranking rule for parallel masked diffusion decoding.”
“go start using a quantum computer there's so many open source packages go start programming quantum computer go start learning and ultimately just do research and you'll quickly get into the field”
“there's so many open source packages go start programming quantum computer go start learning and ultimately just do research and you'll quickly get into the field”
“We present LogNEO, a log anomaly detector built on EleutherAI's GPT-Neo (1.3B parameters) and fine-tuned with a novel partial-credit, exponentially decaying position-aware reward scheme combined with …”
“great was talking with Ray about his new book which he just published on how countries go broke...really important book awesome well done”
“built on EleutherAI's GPT-Neo (1.3B parameters)”
“combined with cross-entropy regularisation via Proximal Policy Optimisation (PPO).”
“you can do authenticate your Apple Health just authenticate Apple Health when these bowls come off the line and see how I talk it's like an assembly line”
“A production microservice deployment over Apache Kafka, Redis, and TensorRT-accelerated inference demonstrates 45 ms end-to-end latency at 15,000 events per second.”
“I went to RFK Junior's website and they have like the he has merch he has Maha merch I have I have the green Maha merch hat I should have worn it today I'm all about it”
“A production microservice deployment over Apache Kafka, Redis, and TensorRT-accelerated inference demonstrates 45 ms end-to-end latency at 15,000 events per second.”
“don't forget to go to our YouTube blah blah blah subscribe”
“our other friend Sky Dayton has been pushing really hard for the US government to do Advanced pilot training”
“A production microservice deployment over Apache Kafka, Redis, and TensorRT-accelerated inference demonstrates 45 ms end-to-end latency at 15,000 events per second.”
“As the Model Context Protocol (MCP) standardizes tool-calling for autonomous agents, it introduces a critical, unexamined attack surface: the error-handling loop.”
“We introduce VATS (Vulnerability Analysis of Tool Streams), a mutation-driven framework that systematically evolves adversarial payloads across seven structural and linguistic dimensions.”
“Our evaluation across four frontier models, Gemini 3.1 Pro, GPT-5.5, GLM-5.1, and Qwen3-Coder, demonstrates that error-path injection triples the success rate of standard indirect prompt injection (IP…”
“Our evaluation across four frontier models, Gemini 3.1 Pro, GPT-5.5, GLM-5.1, and Qwen3-Coder, demonstrates that error-path injection triples the success rate of standard indirect prompt injection (IP…”
“When properly implemented and optimized, PO4AO constitutes a robust and high-performance turnkey controller for single-conjugate adaptive optics systems,...”
“The source code for the ++nnU-Net is available at: https://github.com/sofia-adelie/plusplusnnunet.git”
“The nnU-Net has demonstrated continuous success in medical segmentation tasks”
“today we released with deep learning a course on agentic memory with langraph and so that's what I want to cover today”
“in this course we'll be using a package called langme um which contains a bunch of utilities... it contains utilities for when it's updating to semantic memory”
“the Dale Carnegie School of Public Speaking you know, the way that operates is, uh they get you up there and they realize that the number one problem with public speaking is uh that uh people are very…”
“I'm not going to take us here, but I know you're a big fan of this book, Finite and Infinite Games. I actually had it once at a book club and it blew my mind open. I'm going to link to it. People shou…”
“So I watched The Last Dance, the Netflix special of Michael Jordan a while ago, of course, but there was one scene where he just... made up an insight that someone told him so that he would then go an…”
“we propose CITRAS-FM, a tiny 7M-parameter TSFM that supports univariate, multivariate, and covariate-informed zero-shot forecasting with real-time CPU inference.”
“we propose CovSynth, which synthesizes realistic covariates from decomposed components of target series.”
“there's a really good paper uh or there was a really good paper two years ago out of Stanford uh called uh I think generative agents or something like that... That's a really really good one to go and…”
“one of the things that we actually use is we use this thing called trust call. Um this thing called trust call basically applies large JSON schema updates to things.”
“if we think about kind of like deep research by OpenAI, uh they ask you a bunch of follow-up questions before it actually writes the research report, and that helps yield kind of like better results.”
“if you've played around with chat GPT's memory feature, this is how it works under the hood. So it calls some memory functions to update it.”
“We propose a deep reinforcement learning framework for multi-objective policy optimization at this scale.”
“Introducing MIST: a benchmark of synthetically generated multi-turn conversations where users express plausible misconceptions in scientific, medical, and moral reasoning domains.”
“We propose DAC (Divide and Cooperate), a role-decomposed multi-agent training framework that divides agentic search into two cooperative subtasks, each handled by a dedicated agent trained with role-s…”
“Experiments on general and multi-hop QA benchmarks show that DAC, implemented via parameter-efficient LoRA modules over a shared backbone, achieves strong performance against prior baselines that rely…”
“Just add an EightSleep Pod 4 Ultra to your mattress like a fitted sheet and it will automatically cool down or warm up each side of your bed up to 20°.”
“We provide a proof-of-principle implementation on GitHub at https://github.com/andreslunagodoy/tube_seeding.”
“The complete framework is released as the open-source library PulsarX.”
“They make the only NSF-certified Tongkat Ali on the planet... This is a huge part of my brain, body, and sleep stack which makes a big impact on my cognition, my strength, and my recovery.”
“I had Abigail Shrier on the show. She wrote this book called Bad Therapy, sort of pushing back against therapy culture for kids specifically.”
“I read a uh I read a blog post by uh P. Mark aka Mark Andreessen where he said, 'Don't keep a schedule.' And I took that to heart. So, I deleted my calendar.”
“I think these are the most breakthrough drugs since antibiotics... They also seem to be addiction breakers. They seem to lower many kinds of cancer. They almost metabolically reverse aging up to a cer…”
“you're going to love my full-length conversation with the one and only Alain de Botton from the School of Life right here. Go on.”
“Peter Thiel has this whole thing from Rene Gerard about how mimemetic desires are desires are picked up from other people.”
“that line in No Country for All Men where the killer is waiting for the protagonist... 'if your set of rules brought you here, then what good are your rules?'”
“What is it? 4,000 weeks. That's your lifespan. Um and and yes, we hear that, but we don't remember it.”
“the big benefit of meditation. It creates a small gap between your conscious observation self and your mind and that lets you then look at your thoughts and evaluate them a little bit like you would a…”
“you can even just do it through therapy, you can do it through journaling, you can do it any way you would like, you can just take long walks, you don't have to meditate”
“there's a guy his name is Yannik and he does really cool He's a really cool guy He's like really funny maybe you link it in the in the show notes because I forget the exact name of the channel but he'…”
“what I did as I went and took improv classes... you have to act without a script and you have to be funny... I found that that's the most uncomfortable I have to think on my feet”
“use replet agent even I would say openi deep research will give you an idea of like you know where these tools are coming going”
“LLM-powered chatbots are increasingly embedded in everyday workflows, raising sustainability concerns due to their energy use.”
“I started like playing around with Gemini from Google I would say Gemini Flash is incredibly impressive Really large context window”
“We then evaluated the prototype in a five-day field study with 11 participants.”
“We present a lightweight, generative approach to provenance tracking based on observational semantics. Instead of propagating identifiers through compiler passes, we observe graph transformations and …”
“We introduce JANUS, a benchmark for measuring goal-conditioned pragmatic distortion in fact-grounded LLM outputs.”
“The paper is the theory of that off-diagonal.”
“A multi-similarity Siamese neural network unifies zero-day anomaly detection and one-shot classification in optical networks, achieving over 99% accuracy and instant adaptability across lightpaths and…”
“We introduce EngVQA, a multimodal benchmark for evaluating engineering reasoning across 5 engineering subjects containing 696 problems.”
“Foreground Conditioned Outpainting (FCO) meets this demand, allowing users to create desired backgrounds for foreground instances at a low cost by adjusting the text prompt.”
“We propose the Customized Concept Embedding Diffusion (CCE-Diffusion) framework.”
“this paper introduces Role-Agent, \textcolor{black}{a framework} that harnesses a single LLM to function concurrently as both the agent and the environment, enabling a bootstrapped co-evolution.”
“We then introduce Gravity-Weighted DPO (GW-DPO), a preference-optimization objective whose per-sample offset scales with the structural distance between conflicting levels under a linear or bilateral …”
“Combined with hierarchy-specific delimiter tokens (Chen et al., 2025) and Instructional Segment Embeddings (ISE; Wu et al., 2025), GW-DPO with the bilateral schedule Pareto-improves over standard DPO …”
“There's a bunch of websites there's composio um a lot of startups I think another one called uh tool MCP tools or something like that Smither AI and other ones provide you model context protocols”
“there are these um platforms where you can sell businesses on acquire.com Yeah Things like acquire.com”
“sonnet 3.7 claw sonnet 3.7 you know everyone who's using cursor whatever thinks it's bad... what I saw in that is an AI that can step back and think... I think what anthropic did is they gave it agenc…”
“We revisit graph-based clustering as a bottom-up alternative, where segment embeddings are connected by pairwise similarity and partitioned using the Leiden algorithm.”
“We revisit graph-based clustering as a bottom-up alternative, where segment embeddings are connected by pairwise similarity and partitioned using the Leiden algorithm.”
“Another bottom-up approach, agglomerative clustering with average linkage, also performs well, although it is computationally less efficient and allows for less control over the resulting distribution…”
“We describe ConvMemory v2, an opt-in token-evidence reranker that sits after the lightweight ConvMemory v1 reranker and reorders only v1's protected top-10 candidate set.”
“We describe ConvMemory v2, an opt-in token-evidence reranker that sits after the lightweight ConvMemory v1 reranker and reorders only v1's protected top-10 candidate set.”
“v2 is a fine-tuned ms-marco-MiniLM-L-6-v2 cross-encoder (22,713,601 parameters, measured from the released checkpoint) applied to the ten (query, memory) pairs that v1 has already selected; it does no…”
“On the LoCoMo conversational memory benchmark (5 seeds, n = 4955 test rows), v2 raises FULL MRR from v1's 0.5824 to 0.6560 (paired bootstrap +0.0734, 95% CI [+0.0645, +0.0827]) and H@1 from 0.4440 to …”
“This report extends the v1 technical report (arXiv:2605.28062).”
“To address these limitations, we propose DocTrace, a multi-agent RAG framework for long-document QA that supports query-triggered knowledge organization, document-structure-aware and experience-guided…”
“Based on these insights, we propose the Knowledge-Augmented Tool Execution (KATE), a knowledge-augmented tool execution framework that integrates experiential knowledge with reasoning-width-expanded i…”
“that's how I started watching all these online lectures. Uh Andrew Ang's lectures on YouTube.”