✳flâneur — a map of the web's best reading
Unlocking Real-Time Bug Detection at Cognition | Applied Compute
appliedcompute.com · 2,927 words · saved by 1 readers
How Applied Compute post-trained a specialized model that enabled 10x faster bug detection.
The training recipe was precisely tailored to our product and use case. Applied Compute's approach to dataset, environment, and harness construction gave us confidence that the model would perform well in the production setting with real users. Moritz Stephan Engineering Lead, Cognition Launching SWE-check Cognition is the team behind Devin and Windsurf, the AI-native IDE. One of their newest features is SWE-Check ⌝ , a real-time bug detection agent that reviews a developer's code upon invocation and produces structured bug descriptions that render natively in the IDE. Cognition’s vision is to
Explore this link on the map →related reading
- Composer2.pdfcursor.com
- Improving Composer through real-time RL · Cursorcursor.com
- RL Pet Peeves Part 1 · Aurielaurielws.github.io
- My picture of the present in AI — LessWronglesswrong.com
- Natural-emergent-misalignment-from-reward-hacking-paper.pdfassets.anthropic.com
- AI Model & API Providers Analysis | Artificial Analysisartificialanalysis.ai
- Recent Frontier Models Are Reward Hacking - METRmetr.org
- PostTrainBenchposttrainbench.com
- Introducing SWE-grep and SWE-grep-mini: RL for Multi-Turn, Fast Context Retrieval | Cognitioncognition.ai
- Kevin-32B: Multi-Turn RL for Writing CUDA Kernels | Cognitioncognition.ai
- Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscationarxiv.org
- The Verification Horizon: No Silver Bullet for Coding Agent Rewardsarxiv.org