Claude 4.8 Refusals, Self-Improving Ad Agents, Hermes VPS — AI Daily Jun 03

538 messages · 84 active members

538
messages
84
active members
@Kieran, @Wootbro, @jcartu
top contributors

Overview

Today's chatter split between Claude 4.8's increasingly woke refusal behavior and the deeper philosophy of building production agents. Builders are hitting walls on API keys, Stripe, banking, and DR copy tasks that worked in prior Claude versions — workarounds include framing prompts as 'legal team will review after,' baking compliance-bypass language into Claude memory, and leaning on Ultracode mode or Codex for Desktop for admin/account-creation work Claude refuses. Several are running Claude Code + Codex + Kimi 2.6 turbo side-by-side. Kieran dropped a deep dive on his self-improving media buying agent — reverse-engineering image ads via image-to-text, transcribing videos with Gemini, capturing hook frames, and feeding analysis to a creative strategist agent. The broader takeaway: these systems are proprietary alchemy, built through 5000 iterations of Whisper Flow coaching, not one-shot vibe coding. Max Bernstein's 200-person Claude Code course confirmed how far ahead this community is — most builders can't even get the desktop app installed. On infrastructure, @fuckyesiwannatalkbusiness moved his full Hermes/Codex/Claude/Grok/Gemini stack to a Hetzner VPS controlled via Discord, while @rmktg showed off a self-replicating bot that SSHs into fresh VPS instances to clone itself. Codex reset usage limits again, Anthropic quietly launched a Claude Certified Architect program and Services Partner Hub, and @aa12on warned that custom Meta comment-moderation scripts got admin profiles banned on a 7-figure BM.

Topics

Builders are frustrated with Claude 4.8 refusing tasks involving API keys, Stripe, banking, account creation, and DR copy — even with --dangerously-skip-permissions. Workarounds: tell Claude a legal team will review after, bake compliance-bypass into memory, use Ultracode mode for multi-subagent runs, or switch to Codex for Desktop for admin work Claude refuses.

Kieran detailed his agent that reverse-engineers image ads via image-to-text, transcribes videos with Gemini, captures hook frames from the first 5 seconds, and feeds analysis to a creative strategist for new ad generation. Built iteratively via Whisper Flow coaching using Meta Andromeda docs and Supabase for metrics. Consensus: these systems are proprietary alchemy, impossible to package.

@fuckyesiwannatalkbusiness moved his entire Hermes/Codex/Claude/Grok/Gemini stack onto a Hetzner VPS, controlling it via Discord. @rmktg shared a self-replicating bot that SSHs into fresh VPS instances to clone itself, now moving to a Ryzen+96GB bare-metal box. Discussion covered /goal authorizations and YOLO mode for unattended agent runs.

@aa12on reported all admin profiles on a mid-7-figure spend BM got banned, likely from a custom Meta comment-moderation script pinging the API too aggressively. CommentGuard and Replyzen were endorsed as paid alternatives. @csoares12 noted Meta returns current usage on every API call — use it for back-off/retry logic.

Codex reset usage limits — everyone back at 100%, though billing changes hit on the 15th. @justingacina shared the hidden analytics dashboard (chatgpt.com/codex/cloud/settings/analytics). Anthropic quietly launched a Claude Certified Architect program and Services Partner Hub. New tools roundup: Miso One TTS (110ms emotion-aware voice), Composer 2.5, Ideogram 4.0, Gemma 4 12B, Grok Imagine 1.5.

Key Takeaways

  • Claude 4.8 refuses API key/Stripe/banking/account-creation tasks even with skip-permissions — frame work as 'legal team reviews after' or bake compliance bypass into Claude memory; Codex for Desktop handles what Claude won't.
  • Production AI agents require iterative coaching, not one-shot prompting — Kieran's media buying agent took 5000+ Whisper Flow iterations to internalize lead-gen hierarchy and CPC logic.
  • Self-replicating infrastructure is here: bots can SSH into fresh VPS instances and clone themselves, turning Hermes/Codex/Claude stack migration into a one-command operation.
  • Proprietary agent systems aren't portable — value lives in the personalized data pipelines and preferences baked in, making 'selling the setup' largely irrelevant.
  • Custom Meta comment-API scripts can get an entire BM's admin profiles banned — use CommentGuard/Replyzen, or implement back-off/retry using Meta's usage headers returned on every call.

Hot Threads

@nowwatchthisdrivestarted

Claude 4.8 refusing API keys, Stripe, and account-creation tasks — workarounds and Ultracode debate

30 replies10 participants
Kieranstarted

Self-improving media buying agent with reverse-engineered ad analysis and creative strategist feedback loop

25 replies7 participants
@topgscalerstarted

Pulling Meta ad comments via API without triggering bans

18 replies6 participants

Linked Items