Developer Tools
B
Showing 271–300 of 403
-
Structural Pattern Mining in Inka Khipus: A KFG Re-Analysis
-
Quoting Terk TerkowitzAmazon leader: where AI doesn't help is a finding, not a failingAn Amazon engineering leader says that if someone's work doesn't benefit from current AI tooling, that is a finding rather than a failing. Engineers should document why, share it with peers and managers, and seek solutions. Explaining where AI doesn't yet help shows the judgement the company wants.
-
CALM: Conflict-Aware Lifecycle Memory Governance for Long-Horizon Language Agents
-
Do Audio LLMs HEAR Pain? Tracing Acoustic Evidence from Speech to Language Reasoning
-
A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement
-
The future of the firmOpenAI explores how AI could enter the firm's org chartIn “The future of the firm,” OpenAI considers how AI might enter the org chart: beneath, beside and between people. The piece looks at how that could reshape the way companies are organized and work.
-
PT$^3$: Prototype-Guided Self-Supervised Pretraining for Generalizable mmWave Human Point Cloud Representation
-
Implicit Minor Detection from Multi-Turn Dialogue in High-Risk AI Interactions: A Constrained Self-Evolving LLM Harness
-
An Alignment Benchmark for Enterprise Agents on Era by Eon
-
From Leniency to Suspicion: How an Open Post-Training Recipe Changes Whom LLM Fact-Checkers Believe
-
Value Probes: Learned Value Functions for Beam-Search Red Teaming
-
What Hallucinations Have We Measured? Semantic Illusion, Confabulation, and Expressed Uncertainty
-
Legora is building the agentic operating system for legal workLegora builds an agentic OS for legal work on OpenAI modelsOpenAI showcases how legal-tech company Legora uses its models, ChatGPT, and Codex to speed up legal workflows and broaden contract analysis, aiming to free lawyers to focus on higher-value work.
-
AtomSteer: Test-Time Constraint Steering for Atomistic Generative Models
-
Similar Scores, Opposite Failures: Human Correction as an Instrument for Video Caption Evaluation
-
SaiVLA-JEPA: Evaluating Future Latent Prediction in JEPA-Conditioned VLA Control
-
Accelerating Nonlinear MPC by Behavior Cloning with Separated Timescales: Application to Nuclear Reactor Load-Following
-
Tracekit Box: Running AI Agents in Micro-VMs Where Every Way Out Is Decided and Signed
-
Benchmarking decision models against generative large language models on medical multiple-choice questions
-
Predict the Reward, Not the World: World Reward Models for ML Agents
-
RoleFUZZER: User-Behaviour Fuzzing for Role-Specification Adherence in Large Language Models
-
DecisionUnlearn-Bench: Unlearning Probabilistic Decisions under Changing Schemas
-
Governance-Aware Federated Learning for Multi-Agent AI Systems: A Policy-Driven Framework for Trustworthy Collaborative AI
-
LLMs as Judges and Examinees for Medical Item Difficulty Prediction
-
Agent Transfer Protocol: Server-Mediated Agent-to-Agent Communication Architecture for the Agentic Web
-
PFNの国産フラッグシップモデル「PLaMo 3.1 Prime」発表 オンプレでDeep Research対応 API無料プランも開始PFN launches PLaMo 3.1 Prime, a domestic LLM with on-prem Deep ResearchPreferred Networks has released PLaMo 3.1 Prime, its domestically developed flagship generative AI foundation model. It adds Deep Research that can run on-premises and is said to reduce hallucinations. A free API plan is also available for trying it out.
-
Big Red gets cozy with Google to offer TPUs to AI customersOracle to offer Google TPUs on OCI alongside Nvidia and OpenAI expansionsOracle will be the first cloud outside Google to offer Google's TPUs, available on OCI from 2027. It also announced Nvidia Vera Rubin NVL72 availability, new OpenAI-based products, and a Snowflake partnership.
-
Game Boy Color on My Conference BadgeGame Boy Color emulator runs on GitHub Universe badgeThe GitHub Universe badge is a colour-screen computer. Steve Francia used Gemini to run an NES emulator on it, then added Game Boy and Game Boy Color emulators. With a ROM, Zelda: Link's Awakening plays on it.
-
Honeycomb-Surfels: Compact Hexagonal Primitives for Efficient Scene Rendering and Reconstruction
-
ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning