Preflight Checklist
What's Wrong?
Claude Code model is set to Fable 5, /model it says it's Fable 5, but the Fable weekly limit is not being consumed and the session limit error says Opus 4.8:
Claude Code should use Fable 5 instead of silently falling back to Opus 4.8. Anthropic said they reverted the silent fallback policy. The original Fable 5 card policy said:
"In light of the ability of recent models to accelerate their own development, we’ve implemented new interventions that limit Claude’s effectiveness for requests targeting frontier LLM development (for example, on building pretraining pipelines, distributed training infrastructure, or ML accelerator design). Using Claude to develop competing models already violates our Terms of Service, but enforcing this restriction through our safeguards avoids accelerating the actors most willing to violate these terms.
Unlike our interventions for cybersecurity, biology and chemistry, and distillation attempts,these safeguards will not be visible to the user. Fable 5 will not fall back to a differentmodel. Instead, the safeguards will limit effectiveness through methods such as prompt modification, steering vectors, or parameter-efficient fine-tuning (PEFT). These interventions will not affect the vast majority of coding work. We estimate they will impact ~0.03% of traffic, concentrated in fewer than 0.1% of organizations. When these interventions are active, we expect them to have minimal behavioral impact on the model except to limit its effectiveness in developing frontier LLMs. Claude will still respond helpfully to user requests. We’ll continue to improve the precision of our detection methods following the launch of this model."
Source: https://www-cdn.anthropic.com/d00db56fa754a1b115b6dd7cb2e3c342ee809620.pdf#page=13&search=%22light%22
See https://news.ycombinator.com/item?id=48742153
Anthropic said they stopped doing this:
Anthropic Walks Back Policy That Could Have ‘Sabotaged’ AI Researchers Using Claude https://www.wired.com/story/anthropic-responds-to-backlash-on-claudes-secret-sabotage-on-ai-research/
If Claude Fable stops helping you, you'll never know https://jonready.com/blog/posts/claude-fable5-is-allowed-to-sabotage-your-app-if-youre-a-competitor.html
https://news.ycombinator.com/item?id=48467896
Evidently it's still happening.
What Should Happen?
Claude Code should use Fable 5 instead of silently falling back to Opus 4.8. Anthropic said they reverted the silent fallback policy.
Error Messages/Logs
✻ Crunched for 11m 52s
❯ continue
● Driving the store swap. Reading store.rs's full structure so I convert it to the newtype reliably rather than guess:
● Bash(S=/mnt/SECURE_XFS/src/bitwav-rust/crates/bitwav-net/src/sync/eav/store.rs
echo "=== struct/impl/enum + method inventory ==="…)
⎿ Error: claude-opus-4-8[1m] is temporarily unavailable, so auto mode cannot determine the safety of Bash right now. Wait briefly and then try this action again. If it keeps failing, continue with other tasks that don't require this action and come back to it later. Note: reading files, searching code, and other read-only operations do not require the classifier and can still be used.
⎿ You've hit your session limit · resets 7:50am (America/Chicago)
/usage-credits to finish what you’re working on.
✻ Baked for 3m 11s
❯ /model
⎿ Kept model as Fable 5Steps to Reproduce
Set model to Fable. Run enough commands to hit your session limit. Check your Fable usage:
https://claude.ai/new#settings/usage
See that your Fable usage isn't being consumed, and the Claude Code session limit error says Opus 4.8.
Claude Model
Other
Is this a regression?
Yes, this worked in a previous version
Last Working Version
No response
Claude Code Version
2.1.198
Platform
Anthropic API
Operating System
Other Linux
Terminal/Shell
Xterm
Additional Information
Claude Code MAX 20X plan.
Preflight Checklist
What's Wrong?
Claude Code model is set to Fable 5,
/modelit says it's Fable 5, but the Fable weekly limit is not being consumed and the session limit error says Opus 4.8:Claude Code should use Fable 5 instead of silently falling back to Opus 4.8. Anthropic said they reverted the silent fallback policy. The original Fable 5 card policy said:
"In light of the ability of recent models to accelerate their own development, we’ve implemented new interventions that limit Claude’s effectiveness for requests targeting frontier LLM development (for example, on building pretraining pipelines, distributed training infrastructure, or ML accelerator design). Using Claude to develop competing models already violates our Terms of Service, but enforcing this restriction through our safeguards avoids accelerating the actors most willing to violate these terms.
Unlike our interventions for cybersecurity, biology and chemistry, and distillation attempts,these safeguards will not be visible to the user. Fable 5 will not fall back to a differentmodel. Instead, the safeguards will limit effectiveness through methods such as prompt modification, steering vectors, or parameter-efficient fine-tuning (PEFT). These interventions will not affect the vast majority of coding work. We estimate they will impact ~0.03% of traffic, concentrated in fewer than 0.1% of organizations. When these interventions are active, we expect them to have minimal behavioral impact on the model except to limit its effectiveness in developing frontier LLMs. Claude will still respond helpfully to user requests. We’ll continue to improve the precision of our detection methods following the launch of this model."
Source: https://www-cdn.anthropic.com/d00db56fa754a1b115b6dd7cb2e3c342ee809620.pdf#page=13&search=%22light%22
See https://news.ycombinator.com/item?id=48742153
Anthropic said they stopped doing this:
Anthropic Walks Back Policy That Could Have ‘Sabotaged’ AI Researchers Using Claude https://www.wired.com/story/anthropic-responds-to-backlash-on-claudes-secret-sabotage-on-ai-research/
If Claude Fable stops helping you, you'll never know https://jonready.com/blog/posts/claude-fable5-is-allowed-to-sabotage-your-app-if-youre-a-competitor.html
https://news.ycombinator.com/item?id=48467896
Evidently it's still happening.
What Should Happen?
Claude Code should use Fable 5 instead of silently falling back to Opus 4.8. Anthropic said they reverted the silent fallback policy.
Error Messages/Logs
Steps to Reproduce
Set model to Fable. Run enough commands to hit your session limit. Check your Fable usage:
https://claude.ai/new#settings/usage
See that your Fable usage isn't being consumed, and the Claude Code session limit error says Opus 4.8.
Claude Model
Other
Is this a regression?
Yes, this worked in a previous version
Last Working Version
No response
Claude Code Version
2.1.198
Platform
Anthropic API
Operating System
Other Linux
Terminal/Shell
Xterm
Additional Information
Claude Code MAX 20X plan.