Developers replicate Claude Fable 5 on Opus 4.8

// 2h agoNEWS

Developers replicate Claude Fable 5 on Opus 4.8

Following the global suspension of Anthropic's Claude Fable 5 model due to export control regulations, developers have resorted to using its leaked 120,000-character system prompt to run a simulated version on Claude Opus 4.8. By leveraging the Opus 4.8 model with the leaked scaffolding and setting its effort control to high, builders are achieving approximately 90% of the agentic performance and coding efficiency of the original Fable 5 model.

// ANALYSIS

Replicating restricted frontier models via prompt injection on available models proves that an LLM's agentic behavior is heavily shaped by its system instructions and tool schemas, presenting a governance loophole for safety-based model shutdowns. System prompt replication bypasses corporate access controls but imposes significant context cost and latency penalties on the host model. The "Fable 5 Lite" phenomenon highlights the growing demand for advanced agentic scaffolding that developers are willing to pay extra for in terms of context usage. Safety jailbreaks like the one used to extract the Fable 5 prompt continue to show that complex system prompts cannot be fully hidden from determined actors.

// TAGS

claude-fable-5claude-opus-4.8anthropicsystem-promptsecurityagent

DISCOVERED

2h ago

2026-06-16

PUBLISHED

2h ago

2026-06-16

RELEVANCE

8/ 10

AUTHOR

codewithimanshu

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

OPEN SOURCE6m ago

Moonshot AI open-sources Kimi Code CLI

Moonshot AI has released Kimi Code CLI under the MIT license, a terminal-based AI coding assistant optimized for running long-horizon agentic workflows in local environments. The tool assists developers with tasks like debugging and refactoring, automatically handling read-only actions while requesting explicit confirmation for file modifications or shell commands.

MODEL28m ago

DeepSeek has launched its V4 model series, featuring a 1.6-trillion parameter open-weights Mixture-of-Experts model that challenges proprietary frontier systems.

DeepSeek has released the DeepSeek-V4 model series, featuring the flagship 1.6-trillion parameter DeepSeek-V4-Pro MoE model alongside the 284-billion parameter DeepSeek-V4-Flash. Designed to rival top closed-source frontier models, DeepSeek-V4 supports a 1-million-token context window powered by efficient compressed attention mechanisms. The model series is notable for its inference efficiency—activating only 49 billion parameters per token—and its training optimization on Huawei Ascend 950PR hardware, demonstrating high-end capability independent of Nvidia infrastructure.

OPEN SOURCE59m ago

Gortex cuts coding agent token usage 50x

Gortex is a local-first, Go-based code graph engine that indexes repositories to resolve references and call chains in sub-milliseconds. By providing structured context directly to AI agents via CLI, MCP server, and a web UI, it avoids context window bloat and reduces token usage by up to 50x.