Filtrer cette collection + ThèmesTous les sujets inference performance infrastructure optimization model deployment workflow integration rationale AI model category adoption model design and deployment seed fund sizing acquisition strategy venture fund strategy adapter layer design MCP connector approval connector architecture security review process MoE scaling efficiency numerical precision optimization training infrastructure performance content strategy public-private ecosystem design data center development realism infrastructure credibility stakeholder inclusion local acceptance data center development process product launch and pricing AI differentiation strategy market problem framing privacy and hardware design AI industry and gaming industry misalignment AI-native game design AI product design principle game revenue measurement AI misuse in game development fine-tuning efficacy AI alignment and principal-agent problems AI agent coordination design Agent delegation in coding tools Human vs. agent organizational constraints AI planning capabilities Multi-agent coordination web standards development test observability test automation design AI in software development standards development trust boundary design agent security risk performance-security tradeoff AI infrastructure security AI alignment and containment limits Empirical assessment of containment failure technical origin story distributed file systems Self-directed AI adoption AI-assisted software development AI compute allocation AI device strategy agent development usability agent adaptability pricing model AI marketplace integration customer case studies customer discovery case studies AI model capability comparison AI model performance and cost AI model reliability and token limits Application building iterations Coding task quality Assistant evaluation efficiency Customer support workflows coding agent reliability goal-directed AI product-market fit cloud storage pricing history S3 pricing history S3 current pricing Produits d'IA Sécurité de l'IA network effects of AI collaboration platforms AI agent collaboration challenges shared context in AI-augmented collaboration open science infrastructure developer tooling prediction uncertainty sales team development equity ownership in bootstrapped vs. funded startups founder sales capability reasoning modality post-transformer architecture motivation latent reasoning benefits Infrastructure de l'IA IA en entreprise communication design for AI AI team integration tool architecture limitation API design preference HTTP caching infrastructure CDN caching limitations AI-powered creator tools Algorithmic curation philosophy Content quality over AI origin AI model release multi-character TTS voice customization design thinking product complexity AI tooling Recherche en IA model deployment platform fine-tuning cost efficiency training duration AI infrastructure constraints qualification program design qualification scope limitation AI infrastructure justification AI developer education growth AI developer training scale Human advantages with AI interdisciplinary literacy Expertise and AI output quality Chip architecture Hardware flexibility AI infrastructure strategy Visibilité dans les moteurs de recherche fondés sur l'IA Création d'entreprises IA et économie AI intellectual property protection government data integration AI-assisted knowledge work evaluation latency tolerance in voice interactions session limits in voice agents voice agent function calling function selection accuracy media virality and AI narratives organizational safety practices AI safety discourse dynamics strategic AI adoption framework enterprise software sprawl problem identification gap AI-enabled tool creation open source sustainability open source licensing strategy license key distribution strategy AI evaluation criteria context layer efficacy enterprise AI architecture model distillation retrieval methodology static embedding performance Recherche IA real-time voice AI latency budget perceived latency thresholds production latency SLOs release governance for AI agents incremental deployment automated agent validation personal agent security agent autonomy agent architecture Legal implications of attribution failure Causal attribution in AI outputs Exact deletion method for influence testing AI/SaaS product governance AI development paradigm AI implementation barrier iterative AI interaction prompt engineering for beginners AI tool onboarding runtime governance control AI governance assumptions AI supply chain attack vector AI governance sovereignty AI agent privilege escalation managed AI services trade-offs AI risk mitigation Prise de décision ontology design for AI agents agent validation workflow ontology-based business logic enforcement neurosymbolic AI architecture AI system security and observability workflow automation KernelBench GPU kernel evaluation agent system design failure analysis in AI systems Human–AI performance tradeoffs in RE-Bench MLE-bench offline Kaggle benchmark AI deployment architecture RE-Bench AI agent evaluation methodology AI evaluation and generalization model evaluation open science and AI impact scaling AI creativity and scientific discovery founder and creator agency Logiciels open source AI video workflow paradigm AI video-audio architecture AI video input flexibility AI agent evolution agent memory architecture enterprise adoption metrics runtime security design customer experience design product scope customer-centric metrics Focused teams Customer focus Leadership and feedback agent reliability threshold human-agent interaction developer experience AI adoption AI deployment strategy AI security AI governance AI personalization AI memory AI limitations in education AI research direction AI capability assessment AI research challenges PersonnesToutes les personnes Dion Harris Tim Fernholz Jason Lemkin Chenghao Wang Kyle Wiggers Jennifer Ferro Josh Dzieza Nilay Patel Aisha Malik Piero Molino Ethan Mollick David Burns Olivia Johnston Matthew Green Peter Mattis 王吉平 王博 Eric Eyken-Sluyters Ruben Gamez Rob Walling Simon Willison Gabriel Grinberg Daniel Vogel Curtis Allen Abhinay Kathuria Daksh Gupta Kevin Hou Zach Lloyd Mike McCormick Anastasis Germanidis John Coogan Jordi Hays Ivan Zhou Anthony Costa Ross Andrew Paquette Zuzanna Stamirowska Nick Kuhn Santi Subotovsky Neal Mohan Maggie Appleton Mckenzie Lock Eric Nguyen Hassan El Mghari Vishal Ganeriwala Fatima Tambajang Wade Foster Matt Pocock Richard Ho Liam Dunne Ali Ghodsi Ben Moore Anton Leicht Aaron Levie Ben Gilbert Evangelos Simoudis Jose Nicholas Francisco John Schulman Nathan Lambert Demetrios Brinkmann Tibo Sottiaux Han Wang Benedict Evans Adam Stacoviak Katie Parrott Stephanie Baladi Ajeya Cotra Ben Rudolph Logan Markewich Parag Agrawal Sachi Shah Maarten Grootendorst James Grimmelmann Zheng Dai David Gifford Pedro Moura Kayla Cinnamon David Rosenthal Daniel Whitenack Chris Benson Kareem Amin Frank Coyle Yash Poojary Chris Pedregal Tarek Mansour Lilian Weng Zubin Pratap Demis Hassabis Jean-Baptiste Kempf shridharathi Jensen Huang João (Joe) Moura Jim Goetz Mark McLaughlin Nikesh Arora Markus Villig Roelof Botha Maya Hoffree Ilkka Paananen David Risher Abhishek Fatehpuria Dan Gallagher Dex Horthy Jim Swanson Dario Amodei Chris Olah Amanda Askell Luis von Ahn Pieter Levels SourcesToutes les sources How NVIDIA GPUs Help Accelerate OpenAI’s GPT-6 Astra Ultrafast Amazon releases its own Jev clone as decision models flood the web | TechCrunch 20VC x SaaStr: Anthropic’s S-1 Leaks, Instinct Hits $10 Billion in 33 Days, AMD Buys World Labs, and Meta Poaches MongoDB’s CEO How We Built Harvey’s Connector Library Introducing Olmo-core 3: Open, scalable training infrastructure for large MoEs Don’t be boring How Utah locals fought Kevin O’Leary’s AI data center Hearing tech startup Legato launches its AI hearing glasses | TechCrunch Piero Molino on AI in Games The Dot and the Swarm The State of Browser Testing - Software Engineering Daily Sidecars: A low-latency trust boundary for Sandboxes | Modal Blog Is sandboxing sufficient to contain rogue agents? Distributed databases with Peter Mattis When Glasses, Earbuds and Phones All Have AI, Who Will Unify Your “Second Brain”? | Snapdragon Summit 2026 Sierra joins the OpenAI Marketplace Episode 852 | Getting Big Name Customer Case Studies and More Listener Questions (with Ruben Gamez) Claude Sonnet 5.5 Customer testimonials published by Anthropic for Claude Sonnet 5.5 2026 in LLMs (so far) Comment: S3 Is the Future, S3 Is the Past Le code généré par l'IA est déjà en concurrence avec le code humain — Daksh Gupta, Greptile Sortez du chemin du modèle — Kevin Hou, Google DeepMind L’ingénierie logicielle devient ingénierie industrielle — Zach Lloyd, Warp De zéro à un en sécurité de l'IA : Mike McCormick de Halcyon sur le lancement de 30 nouvelles organisations et le goulot d'étranglement des fondateurs WorldPrompt de Runway et l'ingénierie de mondes en temps réel TBPN : John Coogan sur les agents personnels et la publicité Our Investment in Ando: Modern Messaging for Teams and Agents How Open Science Can Help Researchers Prepare for the Next Pandemic Bootstrapping From a $500K Goal to a $50M Company What Comes After Transformers? De AGENTS.md au déploiement en environnement d'entreprise avec Nick Kuhn Rethinking Communication for Human and AI Teams | Emergence Capital Comment: We just shipped support for the ugliest part of HTTP: Vary YouTube CEO Neal Mohan: Why We’re Betting On AI And Not Afraid Of It Tool: Gemini 3.8 TTS Playground Ingénierie du design avec Maggie Appleton Parsing “Can” from “Should”: How Netflix's Product Team Got Thousands of Creatives to Trust an AI Overhaul 🔬La biosécurité est une course aux armements en IA - Eric Nguyen (PDG, Radical Numerics) How to train your own Jev for $17 TBPN : John Coogan sur les agents, les interfaces applicatives et la publicité NVIDIA Launches DSX Ready to Qualify Power and Cooling Products for AI Factories From Enablement to Execution, Egypt’s AI Ecosystem Reaches Production Scale The Overhang « Pas de code » est du code : Wade Foster, PDG de Zapier, sur les outils headless, le protocole MCP de Zapier et le banc d’automatisation Compétences en IA avec Matt Pocock Inside OpenAI’s First Chip Comment être découvert dans la recherche IA Ali Ghodsi sur l'apprentissage en tant que PDG et l'évaluation des pratiques de management Anton Leicht sur le déploiement de l’IA, la perturbation économique et les risques Aaron Levie de Box : se réinventer à l'ère de l'IA et diffusion en entreprise The Home Depot When Everyone Is 10x More Productive, No One Is Voice Agent Function Calling: Real-Time Data Lookup Guide Des chercheurs en IA débattent de notre proximité avec l'auto-amélioration récursive One resignation turned the embers of AI fear into a wildfire Les agents d'utilisation d'ordinateur et l'avenir de l'internet agentique Construire Codex avec Tibo Sottiaux Simpler, outcome-based AI pricing AI, tools and transformation — Benedict Evans Forking Cal.com to closed source (Changelog Interviews #685) Katie Parrott sur l'utilisation de ChatGPT pour l'écriture et la réflexion professionnelle From enterprise search to enterprise context: what AI agents actually need Ajeya Cotra sur la persistance des agents, la coordination et la tricherie aux benchmarks Rendre les villes extraordinaires : Nick Noone et Ben Rudolph, de Peregrine Exploring Static Embedding Retrieval Parag Agrawal de Parallel : construire un nouveau web pour les agents IA Real-Time Voice AI Stack for Agents: Architecture Guide Release governance: guardrails for agents at scale An Agent Is Just an LLM in a For-Loop When AI art has no author: MIT study finds generated images often can't be traced to any training data | MIT CSAIL The People Who Understand Don't Build. The People Who Build Don't Understand. | CrewAI GitHub Copilot app for Beginners: Write your first prompt Disney : la Renaissance et l'Empire Reconstructing how OpenAI agents attacked Hugging Face Le PDG philosophe | Kareem Amin, cofondateur de Clay Why Agentic Systems Need Ontologies — Frank Coyle, UC Berkeley Yash Poojary sur l'automatisation des expériences de croissance chez Every Chris Pedregal sur les startups et le travail au-delà des comptes rendus de réunion Tarek Mansour de Kalshi contre le gouvernement fédéral Harness Engineering for Self-Improvement Cartesia | A Guide to Choosing Voice AI Models The Walt Disney Company Demis Hassabis on Scientific Discovery and Personal Agency Jean-Baptiste Kempf sur la qualité du code open source, la maintenance et les builds sécurisés How to make remarkable videos with Seedance 2.0 – Replicate blog Jensen Huang sur la sécurité des agents IA, le leadership et la confiance Orchestrating Self-Evolving Agents with CrewAI and NVIDIA NemoClaw | CrewAI Palo Alto Networks avec Nir Zuk et Nikesh Arora - La rancune qui a transformé la cybersécurité Bolt avec Markus Villig - Du bootstrapping en Estonie à un leader mondial de la mobilité Supercell avec Ilkka Paananen – Comment un pivot précoce a mené à « Clash of Clans » et « Brawl Stars » Lyft CEO David Risher on paying drivers more and the shift to robotaxis Trade Winds: The Rise, Reckoning and Reimagining of Vlad Tenev | Index Ventures 12-Factor Agents: Patterns of reliable LLM applications — Dex Horthy, HumanLayer Gen AI Present and Future: A Conversation with Jim Swanson, CIO at Johnson & Johnson | Greylock Dario Amodei, Amanda Askell et Chris Olah sur le développement et la sécurité de l’IA Duolingo CEO Luis von Ahn thinks AI has a lot to teach us Pieter Levels sur le démarrage autonome de startups, les modèles d'images IA et le développement indépendant Runway Research | Introducing General World Models Année de publicationToutes les dates 2026 2025 2024 2023 Filtrer cette collection 1 personnes · 1 sources · 1 opinions exprimées
Réinitialiser les filtres EN CONTEXTE
AI evaluation and generalization Choisissez un point de vue et retrouvez la conversation originale.
Lilian Weng 4 juil. 2026
Evolved harnesses generalize beyond their original benchmarks Lire les sources d’information ↗ EN CONTEXTE AI evaluation and generalization 1 opinions exprimées
01 Evolved harnesses generalize beyond their original benchmarks Lilian Weng 2026-07-04 Les secteurs égaux servent de repères, pas de classement.
01 Evolved harnesses generalize beyond their original benchmarks Lilian Weng · 2026-07-04 Points de vue 1–1 sur 1 · Sources les plus récentes en premier
Précédent 1 / 1 Suivant
Point de vue sélectionné
Evolved harnesses generalize beyond their original benchmarks A harness evolved on Terminal-Bench-2 transferred without further evolution to SWE-bench-verified, indicating it encodes general engineering experience in harness components rather than benchmark-specific optimization.
Il s’agit de points de vue individuels, non d’une mesure du consensus. Le matériel source reste dans sa langue d’origine.
Éléments favorables
Lilian Weng · 4 juil. 2026
Harness Engineering for Self-Improvement Extrait original
On Terminal-Bench-2, AHE achieved better than human-designed harness (OpenCode, Terminus-2, Codex) except for Hard tier and a few other self-evolve baselines (ACE, TF-GRPO). The same frozen harness, without further evolving, transfers to SWE-bench-verified, indicating that the evolved harness is able to encode engineering experience into harness components rather than doing benchmark-specific optimization. Source et contexte
Les dates concernent les sources, pas des changements d’opinion. Les textes sans traduction révisée restent dans leur langue originale.