Grok Bot, Ox Alpha GLM 5.3, M5 Ultra Mac Studio — AI Daily Aug 26

577 messages · 76 active members

577
messages
76
active members
@jcartu, @fuckyesiwannatalkbusiness, @Kieran
top contributors

Overview

Wednesday's conversation centered on the Grok ecosystem and model choice. @jasonakatiff recommended running Grok alongside Codex for code reviews — Grok consistently surfaces more real issues — while a reconstructed open-source Grok Bot 0.18 hit GitHub, letting builders swap Claude Code, Codex, or local models as the backend engine. Bloomberg reporting tied the stealth 'Ox Alpha' model to Z.AI, with @jcartu arguing it's GLM 5.3 with image/video towers bolted on; weights will be released free. On local inference, @dragodimitrov pulled the trigger on a maxed M5 Ultra 256GB Mac Studio, sparking discussion about running GLM 5.3 Flash at 256k context and ~50 tok/sec approaching Opus 4.5 quality. GLM 5.3 Flash API pricing landed at $0.15/$0.50 per M tokens, with cheaper resale via Surplus Intelligence. @jonmacofficial shared his Orca + OMP + Grok stack with three custom OMP skills (Bug Fix, QA Test, New Feature) as the current best agentic combo. Agent hygiene got attention too: @jcartu pushed a workflow where Fable produces an ADR with gates and rubrics before any build agent touches the repo — his fix for Codex overengineering complaints from @scalingfrog. @thewildzeno (FunnelFlux) warned against vibe-coding trackers, citing edge cases from thousands of affiliates. Builders also endorsed EmailEngine/imapflow for IDLE-based Gmail integration, and FAL's H3 MAX video model drew praise for beating Seedance-tier output.

Topics

A reconstructed open-source Grok Bot 0.18 on GitHub lets builders swap Claude Code, Codex, or local models as the engine while keeping the polished UX. Separately, @jasonakatiff recommends running Grok alongside Codex on every code review — Grok consistently finds more real issues, even if you build with Claude Code or Fable. Consensus: Grok's coding quality has jumped noticeably.

Bloomberg reporting ties the stealth Ox Alpha model to Z.AI, with weights to be released free. @jcartu says it's GLM 5.3 with image and video towers added — he's already running text-only GLM 5.3 direct from z.ai and finds it faster. GLM 5.3 Flash pricing landed at $0.15/$0.50 per M tokens, with resale via Surplus Intelligence even cheaper.

@dragodimitrov bought a maxed M5 Ultra 256GB Mac Studio with 4TB storage. Discussion centered on running GLM 5.3 Flash at 256k context and ~50 tok/sec reaching Opus 4.5-level quality, plus the trade-off of buying now vs waiting for the 512GB variant in late October or M6 MacBooks.

@jonmacofficial shared his Gemini 3.7 Flash orchestrator (Jarvis personality) assigning tasks to Grok sub-agents inside Orca with OMP. He released three Grok-authored OMP skills — Bug Fix, QA Test, and New Feature. Others reported strong results using GLM in OMP as well.

@scalingfrog complained about Codex adding absurd scope like '5-minute rechecks for 24 hours' unprompted. @jcartu's fix: have Fable spec an ADR with gates and rubrics first, then hand it to the build agent, which cannot exceed scope. @thewildzeno added that auditing peer-review logs and building a failure-pattern tally sharpens both planning and review determinism.

Key Takeaways

  • Grok Bot 0.18 has been reconstructed on GitHub — run it with Claude Code, Codex, or local models as the engine while keeping the polished UI
  • Run Grok as a second-pass code reviewer even if you build with Claude Code or Fable — it catches issues Codex misses
  • Ox Alpha is Z.AI's GLM 5.3 with multimodal towers; weights will be free, and API is $0.15/$0.50 per M tokens ($0.05/$0.15 via Surplus Intelligence resale)
  • M5 Ultra 256GB Mac Studio runs GLM 5.3 Flash at 50 tok/sec with 256k context, approaching Opus 4.5 quality for many local tasks
  • Force agents to work from a Fable-authored ADR with explicit gates and rubrics to eliminate scope creep — and don't vibe-code trackers to save $49/mo

Hot Threads

@ariangrtyistarted

Is Grok Bot actually useful, or just for the masses?

18 replies8 participants
@dragodimitrovstarted

Pulling the trigger on maxed M5 Ultra Mac Studio

12 replies5 participants
@jcartustarted

Fable ADRs to constrain build agents and stop Codex overengineering

10 replies4 participants

Linked Items