Developer Tools
B
Showing 151–180 of 326
-
Beyond "ChatGPT Can Make Mistakes": Designing Interventions to Support Metacognitive Monitoring in AI-Assisted Work
-
Neuro-Symbolic Hierarchical Intention Anticipation in Human Behavior
-
Repurposing Unified Topological Signatures for Graph Representation Learning
-
Audio-Visual Turn-taking Prediction in Cocktail Party Scenarios
-
CLARE: Scalable Class-Incremental Continual Learning via a Sparsity-Based Framework
-
ThinkFlow: Self-Evolving Probabilistic Latent Memory for Lifelong Conversational Agents
-
Can LLMs Follow the Pulse of a Crisis? Evaluating Crisis Sentiment in Bangladesh's July Uprising
-
PaperDoctor: Evidence-Grounded and Actionable Feedback for Scientific Papers in Progress
-
The Role of Implicit and Explicit Demographic Signals in Large Language Model-based Student Assessment
-
Nameless Tokenization: A Lossless Tokenizer-Level Defense Against Control-Token Forgery in Open-Weight LLMs
-
Splitting the Difference: Interpretable Causal Forests for Treatment Effect Heterogeneity and Bias
-
HUMAID-NER: A Disaster Tweet Dataset for Joint Named Entity Recognition and Event Classification via Uncertainty-Weighted Multitask Learning
-
Beyond Token-Local Imitation: Reward-Compatible Temporal Credit Assignment for On-Policy Distillation
-
MedPCFM-TED: One-Step Point Cloud Flow Matching for Implant Generation via Teacher-Guided Endpoint Distillation
-
When Confidence Signals Disagree: Local and Global Confidence in Autoregressive Language Models
-
Causal Discovery via Transformed Low-Rank Quantile Surfaces
-
Repurposing Deep Limit Order Book Forecasting for Scenario-Conditioned Market Impact Modeling
-
Verbalizing Subliminal Learning Effects Using Text Optimization
-
Lit3R: Retrieve-Relate-Read for Evidence-Grounded Question Answering over Scientific Literature
-
Disrupted Companionship: A Risk Assessment Framework and Cross-Platform Quantitative Analysis of Psychosocial Responses to AI Companion Disruptions
-
Cascade: Hierarchical Recoverability Control for Large Language Model Unlearning
-
Reduplicative constructions in Mandarin: Socio-emotional profiling through distributional semantics
-
A Data-free Universal Prior over Syntactic Structures
-
ImpossibleRubrics: Stress-Testing Generated Rubrics as Reward Signals
-
Benchmarking Factual Robustness of LLMs via Multi-conversation Persuasion
-
TIAO: Token Importance-Aware Policy Optimization for Text Summarization
-
Japanese Stroke LLM Evaluation: A Conversational Benchmark for Safe Stroke Care in Japanese Using Large Language Models
-
Planning with Agents: Divided Worlds, Boundary Objects, and Thicker InterfacesGitHub Next argues agent planning needs thicker, visual interfacesMaggie Appleton of GitHub Next published a talk on collaborative planning with agents. She argues today's CLI plan mode buries humans in walls of text with no way to edit or debate decisions, and calls for visual, interactive and multiplayer planning interfaces.
-
【動画あり】Excel仕事がラクになるCopilot活用術、実務ですぐ使える3選 Microsoft MVP直伝Microsoft MVP demos three practical Copilot tricks for Excel workMicrosoft MVP Kazuaki Asada walks through three ways Microsoft 365 Copilot can speed up everyday Excel work, with live demos. The piece focuses on how to phrase instructions and how to check the results, rather than on listing features.
-
What blog posts influenced your thinking the most?Simon Willison names the blog posts that shaped his thinkingIn a Lobste.rs thread, Simon Willison lists the posts that shaped him: Joel Spolsky's Law of Leaky Abstractions, Will Larson's argument that migrations are the only scalable fix to tech debt, and Charity Majors' Engineer/Manager Pendulum, which gave him permission to move back to an IC role.