Results for “agents”

2024 in Agents: From Executable Actions to Useful Software Work A practical account of coding agents: how they use tools, recover from errors, reuse workflows, and turn human feedback into completed work.

Cursor’s Third Era: From Writing Code to Operating Agents Configured cloud computers let agents run applications, demonstrate changes, and work in parallel. The harder handoff is turning that output into software people can confidently…

Designing Inference Around Agents — Part 2 of 3 Part 2 of the NVIDIA Brev and Dynamo conversation: adapting inference to changing workloads, giving agents access to compute, and distinguishing longer runs from useful autonomous work.

Dust: Building Workplace Agents from Tasks That Already Work Useful workplace agents depend on bounded instructions, carefully prepared company data, and a product employees can shape around their own work.

From Browsers to Agents: Unlocking the Computer’s Existing Capabilities AI’s accumulated breakthroughs, the Unix architecture behind personal agents, and the institutional work between technical capability and widespread adoption.

From Computer Use to Agents in Production — 2024 Year in Review, Part 3 of 3 The final part of Latent Space’s 2024 review examines what keeps agents from everyday use, revisits the year’s lasting technical lessons, and sets out the…

How Computer-Use Agents See, Act and Recover Ari Weinstein and Nikunj Handa explain the interface and API choices behind faster agents, and where their limits remain.

ICLR 2024, Part 1 of 5: Finding the Tasks Agents Still Cannot Do Part 1 follows the path from rebuilding an NLP course after ChatGPT to web agents, social evaluation, code optimization and the compute constraints shaping academic research.

Mistral’s path from streaming speech to verifiable agents Voxtral TTS generates speech one frame at a time. The same conversation connects specialized models, enterprise training, formal proofs, and learning from agents that work for hours.

Multi-Turn RL: Rewarding Agents for Useful Work From coding agents that do too much to tools that get called but ignored, the training problem is deciding which actions deserve credit.

OpenAI’s Agents Platform: From Tool Calls to Observable Workflows The March 2025 launch conversation explains why Responses became a new API, how its tools compose, and how handoffs and traces could support better agents.

Red teaming agents: from malicious inputs to consequential actions Gray Swan connects adversarial testing, specialized guard models and system permissions to make agents safer without stripping away their usefulness.