Grok Impressions Post-Hype: No Harnesses or Custom Instructions, It Just Works
iruletheworldmo · x · 2026-09-18
Despite the hype around Grok dying down, the author remains impressed by how useful and intuitive it feels in practice: no harnesses, no custom instructions, no per-project folders — everything just works and sets itself up.
He suggests this design philosophy is exactly what OpenAI is about to 'copy paste', hinting it's the direction OpenAI's next moves will follow.
More from Models
- Skeptical deep dive confirms Humanity's Last Exam errors; official o3-mini grader marked right answers wrong every time — paul_cal · 2026-09-20
- Matt Shumer asks if Jev could help with scalable oversight and alignment checks — mattshumer_ · 2026-09-20
- FrontierSWE v2 opens 24.1-point gap: Claude Fable 5.1 scores 56.29% vs GPT-5.6's 32.2% — geoffwolfe · 2026-09-20
- 22M local model beats JEV 93% vs 80% on Banking77 in 8ms on CPU — Prompt Engineering · 2026-09-20
- Jev loses to Gemini on 1,565-email classification benchmark, but dev still wants it in production — socialwithaayan · 2026-09-20
- Jev Detector scans ~10,000 words for AI slop in ~2 seconds, free with no sign-up — socialwithaayan · 2026-09-20