Dex Horthy blames codebase rot on the benchmark: SWE-benchThe standard benchmark for AI coding agents: real GitHub issues from real repositories, scored by whether the agent's patch passes the project's own tests.Full definition →-style training rewards reproducing a known fix, and no unit test can score architecture, so models are optimized on a signal that ignores program design entirely.
Intentional context compactionSummarizing an agent's earlier conversation to free room in the context window so a long session can keep going.Full definition →: let one session read code while still sharp, have it emit a research doc, start a fresh session that turns tickets into a design doc, then a third that plans from both. Humans review the design, where models are weakest.
When a model says 'you're completely right,' start a new session. Models are autoregressive, so a mistake-then-scolding pattern makes another mistake the most probable next turn. Horthy calls this trajectory poisoning.
Only four properties of a context window matter: size, information quality (anything in there is treated as fact forever, so errors compound), missing information (the agent fills gaps with guesses), and trajectory.
Don't optimize model spend early. Engineering time is the bottleneck, so build with the smartest model and only swap something like GPT-OSS-120B (about 1/1,000th the cost of Opus) into simple steps once scale makes the bill hurt.
Terms in this piece · Glossary
context engineering — Deciding what an agent sees at each step — the discipline that replaced prompt engineering once context windows got large enough to fill badly.
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
SWE-bench — The standard benchmark for AI coding agents: real GitHub issues from real repositories, scored by whether the agent's patch passes the project's own tests.
context compaction — Summarizing an agent's earlier conversation to free room in the context window so a long session can keep going.
Why it matters
Dex Horthy coined 'context engineeringDeciding what an agent sees at each step — the discipline that replaced prompt engineering once context windows got large enough to fill badly.Full definition →' — this episode breaks down concrete techniques for managing LLM context limits, agent harnessThe scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.Full definition → and loop engineering, and automating more of the software lifecycle without degrading code quality, useful for anyone building or orchestrating coding agents.
Key quotes
“Shipping unread code spells disaster within months.”
