Burkov: DeepSeek 4.1 Flash Codes Well but Misses the Big Picture
burkov · x · 2026-09-17
While waiting for his Codex usage to reset, Andriy Burkov tried DeepSeek 4.1 Flash on OpenCode. Verdict: it's a good coder but struggles to see the bigger picture — you must spell out every detail before letting it code. It also fails to grasp prompts like "imagine you are a X," literally thinking you want it to become or build X.
More from Models
- Grok Bot DAU Jumps 80% in 5 Days, from ~67K to 121K, Similarweb Data Shows — FinanceYF5 · 2026-09-17
- 'The AI Rewrote Its Own Instructions': Inside What Has AI Labs Spooked — birchlse · 2026-09-17
- "As smart as terra": the biggest fumble of the jev rollout — willcb · 2026-09-17
- Daily AI Brief: Claude merges Chat and Cowork, OpenAI ships misalignment disclosure framework — testingcatalog · 2026-09-17
- NVIDIA's SpatialClaw uses code as action interface, beats prior agent by 11.2 points on 20 benchmarks — CMHungSteven · 2026-09-17
- 15 Small Models That Beat Models 100x Their Size at One Task — bigaiguy · 2026-09-17