Hundreds of steps beats one polished demo: Nex-N2.5 Pro plays Pokémon
alifcoder · x · 2026-09-13
Most computer-use demos stop after one clean action. Nex-N2.5 Pro instead played Pokémon across hundreds of steps—reading the screen, navigating menus, battling, and recovering from mistakes. The author argues long-horizon task performance is a far better test; it's free to try on OpenRouter.
Related event: Nex-N2.5 Pro Plays Pokémon for Hundreds of Consecutive Steps(2 posts)→
More from coding & agent
- BountyScout bot hourly-scans GitHub bounties and floods maintainers with AI applications — gleech · 2026-09-13
- Cognition's SWE-2 impresses early user with solid coding, but lacks Codex-style computer use — CtrlAltDwayne · 2026-09-13
- Better AI 3D output costs more upfront but saves tokens and time vs. endless iteration — chaseleantj · 2026-09-13
- No prompt one-shots a polished 3D asset — human-judgment iteration took 17 more minutes — chaseleantj · 2026-09-13
- Workflow tip: generate a reference image first, then iterate your 3D output against it — chaseleantj · 2026-09-13
- Skill-based 3D generation: 68k to 153k tokens but far more realistic leaves — skills set expectations, not teach — chaseleantj · 2026-09-13