Claude 4.7 Backlash, Meta Ad Bans, $1 Adsets — AI Daily May 03

619 messages · 68 active members

619
messages
68
active members
@mb29266, @jasonakatiff, @jcartu
top contributors

Overview

Saturday's 619 messages were dominated by a near-revolt against Claude 4.7. Builders (@nowwatchthisdrive, @jonmacofficial, @mb29266, @jrizzolo) reported the model lecturing them, lying about working code, and degrading on hard problems — many are migrating to Codex (medium for speed, high/xhigh for hard bugs), with @namtalks calling GPT 5.5 superior to Opus on both limits and intelligence. The emerging playbook: plan in Claude/Opus, execute in Codex or local models. @samb69 was a lone early-positive voice on Opus 4.7. Media buyers went deep on Meta. @mb29266 and @drcopybymatt detailed system-user token setups inside private dev apps, 50-ad batch uploads, portable creative drafts that strip account-specific fields, and 2-minute adset publish delays to dodge automation flags. A parallel thread on the Brazilian '$1.28 adset' mass-launch strategy reported significantly lower CPMs/CPCs, with winners promoted into 1-50-1 and 1-250-1 prescale campaigns. Consensus on bans: they're effectively random — redundancy in profiles, BMs, and ad accounts beats trying to stay 'clean.' On infra and agents, @jcartu detailed dropping Anthropic spend from €7k/mo to €200/mo on €16k of home GPUs running Qwen 3 Coder Next and Gemma 27B via official Nvidia vLLM containers. @weslindquist runs 3 Claude Code + 8 OpenClaw + 1 Hermes orchestrator agent fleet over Slack. Security tradeoffs surfaced too: @jasonakatiff burned a weekend on Claude Code secrets management and flagged prompt-injection-via-research-websites as a real exfiltration vector, while builders debated raw DB keys vs scoped admin API endpoints for agent access.

Topics

Builders are abandoning Claude 4.7 en masse, citing slowness, refusals ('time to go to sleep' lectures), and confidently broken output. @jonmacofficial, @namtalks, and @jrizzolo report Codex xhigh and GPT 5.5 outperforming Opus on hard bugs with far better usage limits. The emerging pattern: plan in Claude, execute in Codex, or downgrade to 4.6 high. @samb69 reported positive early results on Opus 4.7 as a contrarian data point.

@mb29266 and @drcopybymatt shared production setups: private Meta dev apps with system user tokens shared to BMs, batched 50-ad uploads, portable creative drafts that strip page/pixel/optimization fields so adsets move freely across farmed BMs, and 2-minute adset delays to dodge automation flags. Consensus on bans is they're effectively random — keep multiple admins, BMs, and ad accounts ready, and protect your pixel on a safe BM. System user tokens may reduce profile ban risk vs user tokens.

A strategy of launching huge volumes of $1.28 single-ad adsets — popularized by Brazilian media buyers on YouTube — was tested and validated by several members, with reports of significantly lower CPMs/CPCs. Winners get promoted into 1-50-1 then 1-250-1 prescale campaigns. Main constraint is needing many pages and ad accounts to handle 250-ad page limits.

@weslindquist runs 3 Claude Code + 8 OpenClaw + 1 Hermes orchestrator agent over Slack — CC is more precise but OC tries to one-shot everything. @jasonakatiff burned a weekend trying to harden Claude Code env var handling (ultimately reverting to .env.local), while @expadz shared a 1Password CLI workflow with prod secrets in Railway/Vercel. Jason also flagged prompt injection from researched websites as a real exfiltration vector; @navuud argued frontier models defend well, and most builders prefer scoped admin API endpoints over raw DB service-role keys for agents.

@jcartu detailed cutting Anthropic spend from €6-7k/mo to €200/mo by running Qwen 3 Coder Next and Gemma 27B on €16k of home GPUs via official Nvidia vLLM containers for production-grade reliability. He also flagged OpenCode + GLM 4.7 on Cerebras hitting 1500 tps for cheap auditable bulk coding. Pair with Opus for planning and auditing.

Key Takeaways

  • Claude 4.7 is regressing for many builders — migrate to Codex (medium for speed, high/xhigh for hard problems) or fall back to 4.6 high while Anthropic sorts it out.
  • Meta bans are effectively random — redundancy in profiles, BMs, and ad accounts matters more than 'clean' behavior; system user tokens via private dev apps reduce surface area.
  • The Brazilian $1.28 adset mass-launch strategy is producing notably lower CPMs and feeding 1-50-1 / 1-250-1 prescale ladders — but requires page and account inventory.
  • Hermes is emerging as a viable orchestrator above Claude Code and OpenClaw fleets; communicate via Slack/Telegram and treat prompt injection from researched sites as a real exfil vector.
  • Local inference (Qwen 3 Coder Next, GLM 4.7, Gemma 27B) on official Nvidia vLLM containers can replace 90%+ of Anthropic spend if you keep Opus for planning and auditing.

Hot Threads

@killainstinctstarted

$1 adset strategy results and 1-50-1 / 1-250-1 scaling mechanics

40 replies6 participants
@drcopybymattstarted

Portable Meta ad drafts across farmed BMs with system user tokens

35 replies6 participants
@nowwatchthisdrivestarted

Claude 4.7 is broken — cancelling and moving to Codex

30 replies8 participants

Linked Items