Codex vs Claude, $50k Consulting, Hermes SDK Fix — AI Daily May 26

565 messages · 90 active members

565
messages
90
active members
@arielletolome, @launchmanmathias, @rmktg
top contributors

Overview

Today's discussion was dominated by the Codex vs Claude Code debate, with several long-time Claude Max subscribers reporting full migrations to Codex citing better instruction-following and compaction — while defenders held the line on Claude's autonomous multi-step orchestration. @geilt detailed Codex session/worktree pairing and cross-device SSH sync, while @justingacina shared strategies for exploiting forced-context files (claude.md, agents.md) as entry points to progressive-disclosure directories. Consensus: use AGENTS.md since most platforms now fall back to it. On the business side, members shared eye-popping enterprise consulting rates — $50k for 2-day insurance training, $1M for a 4-month build, $25k/day Wall Street AI courses — with the takeaway that under-pricing kills credibility. @arielletolome opened a parallel thread on firing devs and VAs in the AI era, surfacing both wins and the emotional difficulty of letting tenured team go. Meanwhile @Wootbro shared a fully-formed Hermes /goal OMO Ultrawork + TEAM MODE prompt template orchestrating 5-10 parallel agents per wave with collision control and fan-in verification. A mid-afternoon Hermes outage from a pinned older OpenAI SDK breaking GPT-5.5 was community-patched (upgrade to openai==2.38.0). Infrastructure talk covered Mac Studios vs Hetzner/OVH/Contabo VPS setups, with Mosh + Tmux + Termius emerging as the nomad-friendly stack. Builders also shared animated/claymation FB ad workflows (GPT Image 2 storyboards → Seedance 1.5 Pro frame animation) and debated whether single-feature AI SaaS survives the next foundation model update.

Topics

Power users reported fully switching to Codex for stubborn bugs and tight instruction sets, while Claude defenders held ground on fire-and-forget multi-step orchestration. @geilt detailed how Codex syncs CLI/app/phone sessions, pairs with worktrees, and shares SSH connections. @justingacina explained using AGENTS.md (now read by Codex natively) as an entry point to progressive-disclosure context directories rather than dumping everything inline.

Members shared real numbers: $50k for 2-day insurance training, $1M for a 4-month build, $25k/day Wall Street courses. Key insight: under-pricing kills credibility, and abrasive pitches ('any Indian dev can build it for $100, you're paying for knowing what to build') close deals. Biggest projects come from billionaire desires, not typical SaaS budgets.

@Wootbro shared a /goal OMO Ultrawork + TEAM MODE template covering preflight, planning, 5-10 parallel agent swarms with collision control, fan-in verification, and closeout audits. Separately, Hermes users hit 'NoneType is not iterable' errors with GPT-5.5 because Hermes pins openai==2.24.0 — community fix: pip install openai==2.38.0 in the venv, restart gateway and TUI.

@tylertrowbridge sparked comparisons between Mac Studios, Hetzner (recently raised prices), OVH ($10/16GB), and Contabo. @Tz1888 recommended Mosh + Tmux via Termius for persistent sessions accessible from laptop and phone, with zram tricks suggested for doubling effective RAM on tight-budget boxes.

Workflow shared: 10-15 GPT Image 2 storyboards → Seedance 1.5 Pro (cheaper) or Kling 3 start/end frame animation, fully scriptable via Codex/Claude. Veo 3 voice consistency remains painful. Parallel debate sparked by an OpenAI vs Anthropic profitability article: single-feature SaaS gets one-shot by foundation model updates, so skills stacking and client relationships beat niche-tool bets.

Key Takeaways

  • Codex is winning power users for stubborn bugs and instruction-heavy work; Claude still leads for autonomous multi-step orchestration. Use AGENTS.md — most platforms now fall back to it.
  • Enterprise AI consulting clears $25k-$50k/day for basic dashboards and automations — credibility scales with price, not complexity. Under-pricing kills deals.
  • If your Hermes broke on GPT-5.5 today: pip install openai==2.38.0 in the venv, restart gateway and TUI. Rollback path documented.
  • Exploit forced-context files (claude.md, agents.md) as entry points to a progressive-disclosure directory; pair with Mosh+Tmux+Termius on a $10-20/mo VPS for nomad-friendly persistent sessions.
  • Single-feature AI SaaS is high-risk against foundation model updates — stack skills and client relationships that compound across model generations.

Hot Threads

@launchmanmathiasstarted

$50k for 2 days teaching basic AI to insurance execs — how to price and pitch enterprise consulting

22 replies9 participants
@tylertrowbridgestarted

Mac mini vs VPS for nomading AI builders

18 replies8 participants
@jarvisballerstarted

GPT-5.5 + Hermes SDK breakage — community-debugged patch and rollback

14 replies6 participants

Linked Items