AI for Software Engineering
Code models, repository context, patch generation, test-driven agents and SWE benchmarks.
5concepts
58flashcards
35minutes of reading
- 01 Code Review by Model Why review is a better fit for current models than authoring, the precision problem that determines whether it is used, and the classes of finding worth reporting.
- 02 Fill-in-the-Middle and Completion Models Why a left-to-right model cannot do the most common editing task, the training transformation that fixes it, and the latency budget that shapes everything about inline completion.
- 03 Repository Context and the Retrieval Problem Why a model with a large context window still cannot see a codebase, what makes code retrieval different from document retrieval, and the signals that actually locate relevant code.
- 04 SWE-bench and Agentic Coding Evaluation What resolving a real GitHub issue measures that a function-completion benchmark does not, the contamination and scoping problems that complicate it, and how to read a reported score.
- 05 Test-Driven Agents and Verification Loops Why an executable check transforms an agent's reliability, how to structure the loop so it converges, and the failure where the agent optimises the test rather than the code.