Two years later: the bet on LLMs for decompilation and program understanding paid off
paul_cal · x · 2026-10-09
@paulcal revisits his December 2023 thread asking whether LLMs for program understanding and decompilation "could be big" — noting that fine-tuning an LLM for it would be easy with synthetic data, working on binaries via assembly or minified JS.
His verdict now: "Turns out — yes." The direction he flagged was largely overlooked by the community at the time, and coverage of it remains sparse.
More from coding & agent
- OpenAI's math results released as open source RL environments — SergioPaniego · 2026-10-09
- Dev builds two playable games in a week with Claude Haiku and GPT small models, with cost breakdowns — chongdashu · 2026-10-09
- Stop vibe coding to 80%: pool your tokens so one person ships it to 100% — arjunrajlab · 2026-10-09
- dhh prefers Codex as main coding model with Claude secondary, praises Sol 6.1 — npew · 2026-10-09
- Leaked Claude Code Setup: Sonnet Builds, Haiku Swarms, Opus Architects — Arindam_1729 · 2026-10-09
- Users claim Codex harness, not the models, is the bottleneck: zcode 5x faster on same tasks — bdsqlsz · 2026-10-09