Bourbon
βgem 'bourbon'β
What the smart people are recommending. 7867 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.
βgem 'bourbon'β
βgem 'normalize-rails'β
βgem 'rspec-rails'β
βgem 'guard-zeus'β
βgem 'capybara'β
βgem 'rb-fsevent', :require => falseβ
βgem 'growl'β
βgem 'factory_girl_rails'β
βgem 'shoulda-matchers'β
βgem 'better_errors'β
βgem 'binding_of_caller'β
βgem 'meta_request'β
βgem 'pry-rails'β
βgem 'annotate'β
βgem 'letter_opener'β
βgem 'devise'β
βgem 'cancan'β
βgem 'omniauth'β
βgem 'omniauth-facebook'β
βThis study presents a systematic evaluation of retrieval-augmented medical question answering using the MedQA USMLE benchmark and a structured textbook-based knowledge corpus.β
βgem 'zurb-foundation'β
βgem 'compass-rails'β
βgem 'foundation-icons-sass-rails'β
βgem 'bootstrap-sass'β
βRecommended terminal emulators include: - **Ghostty** (Linux and macOS)β
βI also recommend subscribing to Katie's sub stack called Work in Process for her wonderful weekly essays.β
βfrom langchain.vectorstores import Pineconeβ
βfrom langchain.chat_models import ChatOpenAIβ
βfrom langchain.embeddings.openai import OpenAIEmbeddingsβ
βllamaindex_agentic_rag.ipynbβ
βprompt_optimization.ipynbβ
βfrom langchain.schema.output_parser import StrOutputParserβ
βimport requestsβ
βfrom bs4 import BeautifulSoupβ
βfrom langchain.schema.runnable import RunnablePassthroughβ
βfrom langchain_core.output_parsers import StrOutputParserβ
βfrom langchain.schema.runnable import RunnableLambdaβ
βfrom langchain_core.runnables import RunnableLambdaβ
βfrom langchain.utilities import DuckDuckGoSearchAPIWrapperβ
βimport jsonβ
βfrom langchain_core.runnables import RunnablePassthroughβ
βfrom langchain_core.runnables import RunnableBindingβ
βfrom langchain_core.runnables import ConfigurableFieldβ
βIf you're not using Keras with JAX you're ngmiβ
βfrom langchain.chains.openai_functions import create_structured_output_runnableβ
β# MW is Short Eurofins (ERF.FP)β
βfrom langchain.chat_models import ChatOpenAIβ
βfrom langchain.pydantic_v1 import BaseModel, Fieldβ
βfrom langchain.schema.messages import AIMessage, HumanMessageβ
βA fast, easy-to-use implementation of the new method is available in the open-source 'lumbermark' package for Python and R. We show that Lumbermark performs well on benchmark data and hope it will proβ¦β
βfrom langchain.memory.chat_message_histories import ChatMessageHistoryβ
βfrom langchain.schema.runnable.history import RunnableWithMessageHistoryβ
βSHapley Additive exPlanations (SHAP) analysis is an explainable AI method growing in popularity for its ability to explain model predictions in terms of the original features.β
βfrom langchain.prompts import PromptTemplateβ
βfrom langchain.chat_models import ChatAnthropicβ
βfrom langchain.agents import XMLAgentβ
βfrom langchain.agents import XMLAgent, tool, AgentExecutorβ
βfrom langchain.agents import XMLAgent, tool, AgentExecutorβ
βfrom langchain.schema.runnable import RunnableBranchβ
βInstall virtualenv(wrapper) on Debian Squeezeβ
βInstall virtualenv(wrapper) on Debian Squeezeβ
βfrom langchain.agents import load_tools from langchain.agents import initialize_agent from langchain.agents import AgentTypeβ
βToy demonstration of chain-of-thought and consensus prompting using OpenAI API.β
βfrom langchain.vectorstores import Chromaβ
βfrom langchain.schema.runnable import RunnablePassthroughβ
βfrom langchain.schema.runnable import RunnableMapβ
βfrom langchain.schema import format_documentβ
βfrom langchain.memory import ConversationBufferMemoryβ
βit uses FX Twitter's API, which is apparently free.β
βThen I use the expensive tier three as another fallback. The official X API v2.β
βRelease of Gemini 3.1 Flash Lite to Developers in the Google APIβ
βMy name is Neil Agarwal and I'm excited to present Mowgli, passively learned rate control for realtime video.β
βI highly recommend heading to jackcornfield.com and signing up for his year-long program, Living the Dharma in a Troubled World.β
βAnd the equivalent of a move 37 would be like alpha tensor finding a new algorithm that makes you know matrix multiplication faster.β
βIntroducing Fidelity Trader Plus, the next generation of advanced trading from Fidelity. Customize your tools and charts and access them seamlessly across desktop, web, and mobile. For faster trades aβ¦β
βHe has a fantastic website called I think grateful or gratitude dot org full of practices of gratitude.β
βThis framework provides a compact and physically transparent tool for analyzing and optimizing digitally stabilized lasers in integrated photonic systems.β
βTo address this challenge, we present CADENCE, an adaptive system that dynamically scales the computational complexity of a slimmable monocular depth estimation network in response to navigation needsβ¦β
βWe conduct evaluations on our released open-source testbed that integrates Microsoft AirSim with an NVIDIA Jetson Orin Nano.β
βThese results show that SBBTS provides a practical and effective framework for realistic time series generation and data augmentation in financial applications.β
βPropositional Linear Temporal Logic (LTL) is a popular formalism for specifying desirable requirements and security and privacy policies for software, networks, and systems.β
βTo explore this concept, we implement Contextify as a probe system and conduct a user study examining users' context management behaviors, attitudes toward AI initiative, and overall collaboration expβ¦β
βWe formalize this view as AEROS (Agent Execution Runtime Operating System), in which each robot corresponds to one persistent agent and capabilities are provided through Embodied Capability Modules (Eβ¦β
βWe propose the Separation of Power (SoP) model, a constitutional governance architecture deployed on public blockchain that breaks this monopoly through three structural separationsβ
βBy open-sourcing both the engine and the 3M-scale dataset, we provide a robust foundation to accelerate future research in spatial intelligence.β
βTo enhance the understanding and interaction with UIs, we propose an innovative GUI reasoning paradigm called UI-in-the-Loop (UILoop).β
βthis study introduces Continuous Interpretive Steering (CIS), a method that probes graded pragmatic interpretation by treating activation-level steering strength as a continuous experimental variable.β
βTo support this analysis, this study introduces a new dataset, GraSD, which encodes graded scalar diversity.β
βOur approach introduces a unified framework, termed DP-TOST, for conducting differentially private equivalence testing of both means and proportions.β
βTo address these challenges, we introduce O3LS, a framework for optimizing lattice surgery through automatic layout search and loose scheduling.β
βWe release a reproducible benchmark pipeline, aggregated results, and paired statistical analyses to support deployment-oriented evaluation of reasoning LLMs under real resource constraints.β
βWe present the Skill Automation Feasibility Index (SAFI), benchmarking four frontier LLMs -- LLaMA 3.3 70B, Mistral Large, Qwen 2.5 72B, and Gemini 2.5 Flash -- across 263 text-based tasks spanning alβ¦β
βCross-referencing with real-world AI adoption data from the Anthropic Economic Index (756 occupations, 17,998 tasks), we propose an AI Impact Matrix -- an interpretive framework that positions skills β¦β
βAdditionally, we introduce Marmoka, a family of lightweight 8B-parameter clinical LLMs for English and Spanish, developed via continual domain-adaptive pretraining on medical corpora and instructions.β
βWe propose WRAP++ (Web discoveRy Amplified Pretraining), which amplifies the associative context of factual knowledge by discovering cross-document relationships from web hyperlinks and synthesizing jβ¦β
βCombining it with a traditional approach for the causal mechanism, we introduce a new bivariate causal discovery method, termed rate-distortion MDL (RDMDL).β
βWe present fastml, an R package that provides a single-call interface for leakage-aware machine learning through guarded resampling, where preprocessing is re-estimated inside each resample and applieβ¦β
βHere, we introduce the Jeffreys Flow, a robust generative framework that mitigates this failure by distilling empirical sampling data from Parallel Tempering trajectories using the symmetric Jeffreys β¦β
βOn the algorithmic side, we propose QPAlign, an algorithm based on a quadratic programming relaxation, and demonstrate its strong empirical performance on both synthetic and real datasets. Moreover, wβ¦β
βTo address this, we propose the Nexus optimizer, which encourages the closeness of these minima by maximizing gradient similarity during optimization. Experiments across models ranging from 130M to 3Bβ¦β