Introducing Composer 2.5 · Cursor
A substantial improvement in intelligence and behavior over Composer 2, particularly on long-horizon agentic tasks.
Fonte
cursor.com
25articoli totali nell'archivio
Development environments for your cloud agents · Cursor
Cloud agents are easier to parallelize than local agents, continue working when your laptop is closed, and can run autonomously…
Updates to Bugbot for Teams and Individuals · Cursor
Bugbot is switching from seat-based subscriptions to usage-based billing for Individual and Teams plans.
Bootstrapping Composer with autoinstall · Cursor
How Composer autoinstall bootstraps runnable RL environments by using earlier model versions to automate setup and verification.
Continually improving our agent harness · Cursor
Models need a harness to become fully useful, and improving that harness means continuously iterating on context, evaluation, and…
Build programmatic agents with the Cursor SDK · Cursor
Launch, steer, and compose custom agents with the Cursor SDK.
Cursor partners with SpaceX on model training · Cursor
Cursor is partnering with SpaceX to accelerate our model training efforts.
Keeping the Cursor app stable · Cursor
How we measure crash and OOM rates, debug memory issues with top-down and bottom-up strategies, and ship mitigations and…
Amplitude ships 3x more production code with Cursor · Cursor
Amplitude uses Cursor to build an autonomous development pipeline that takes software from idea to production with minimal…
Interact with agent-created visualizations in canvases · Cursor
Agents can now create interactive canvases to visually represent information.
Speeding up GPU kernels by 38% with a multi-agent system · Cursor
Our multi-agent system autonomously optimized 235 CUDA kernels for NVIDIA Blackwell 200 GPUs, achieving a 38% geomean speedup…
Bugbot now self-improves with learned rules · Cursor
Bugbot can now learn from PR feedback in real time by turning live code review signals into learned rules.
Introducing Composer 2 · Cursor
Frontier-level coding with strong CursorBench results, higher token efficiency, and a faster default variant.
PlanetScale protects production reliability with Bugbot · Cursor
Bugbot saves PlanetScale the equivalent of two full-time engineers worth of review effort.
Towards self-driving codebases · Cursor
We're making a part of our multi-agent research harness available to try today in preview.