Grok bot feels like GPT-3.5 in testing, lacks 'done receipts' — pudding protocol proposed
RachelVT42 · x · 2026-09-06
A tester found Grok bot's biggest gap is lack of verifiable 'done claims', citing the new open protocol pudding ('no pudding, no done') that makes agent completion claims carry receipts. In her testing Grok bot mostly wasted time while Astra and Grok Build actually helped her accomplish things — Astra more polished, Grok Build good enough. Grok bot remains promising for normies but feels like GPT-3.5-era frustration.
More from coding & agent
- Four Prompts, Five Minutes: Codex Composes a Concerto with Scores, Animation, and Real Instruments — mhmazur · 2026-09-06
- Dev evals multiple models as subagents; V4-Flash stays fast and good — teortaxesTex · 2026-09-06
- Open-source agent skills review manuscripts with real citation checks via PubMed and Crossref — gromads · 2026-09-06
- Running Claude Code 100% free and local with no API costs or rate limits — aliscodes · 2026-09-06
- HKUDS open-sources nanobot: a 99% smaller self-hosted AI agent framework with MCP and WebUI — mdancho84 · 2026-09-06
- There's No Such Thing as Good Code: LLM Tools Found 5 Real Bugs in Carmack's Code — BLUECOW009 · 2026-09-06