• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    Peter Yang Recommends Prompt Audit for Fable 5.1 Skills

    Roblox product lead shares command to clean up AI skills for Fable 5.1.

    SD
    BC
    RS
    32 Sources, 29d ago, first seen 29d ago

    TLDR

    In a post, Peter Yang advises users trying Fable 5.1 to run the command /claude-api prompt-audit on their skills. He states that the tool identifies redundancies and rules to remove for the latest models. Yang, described as a product lead at Roblox who shares AI tutorials and runs a newsletter, adds that he is running the audit on all his own skills now.

    Combined views

    1.6M

    32 Sources, first seen 29d ago

    Combined views

    1.6M

    32 Sources, first seen 29d ago

    16.3K likes
    16.3K likes
    906 comments
    12K saves
    825 reposts
    906 comments
    12K saves
    825 reposts

    Sentiment

    Positive55.7%44.3%Negative

    Summary

    Sentiment

    Positive55.7%44.3%Negative

    Many accounts welcomed Fable 5.1 for its major cost cuts via caching and stronger coding outputs, while others dismissed the claims or noted drawbacks like reduced reasoning quality in some flows.

    Based on 284 sentiment-bearing replies from 237 accounts across 11 conversations.

    Summary

    Many accounts welcomed Fable 5.1 for its major cost cuts via caching and stronger coding outputs, while others dismissed the claims or noted drawbacks like reduced reasoning quality in some flows.

    Based on 284 sentiment-bearing replies from 237 accounts across 11 conversations.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    32 Sources

    @cognitionOver 95% of tokens from a coding task are cached tokens. Fable 5.1 dropped the price of cached tokens by 4x, making it much more efficient for coding as a whole, despite higher uncached prices.
    @kimmonismusClaude Fable 5.1 is cheaper, substantially stronger on several agentic benchmarks, more concise, and apparently far less trigger-happy (says Anthropic). the tl;dr How much cheaper? -Input/output pricing remains $10/$50 per million -tokens. -Cache reads fall 75% to $0.25. -Anthropic estimates ~25% lower costs for typical workloads and up to ~45% for highly agentic, context-heavy work. BUT: not 45% cheaper for Claude subscriptions. ("...wherever usage is billed by token") How much better than Fable 5? -Scientific agent benchmark: 52.6% vs. 24.7% - more than 2× -AutomationBench: 31.4% vs. 17.1% — an 84% relative gain -GDPval-AA: 1,853 vs. 1,723 -CursorBench: 73.4% vs. 70.5% So: dramatic gains on some long-running tasks, modest improvements elsewhere, not a uniform intelligence jump. Verbosity also seems improved, although there is no standardized score. Rogo reports equal accuracy with 20% fewer tokens. Red Hat found its updates more concise and easier to follow. Every says it used half as many tokens as Opus 5 while running about twice as fast. And fewer unnecessary red flags: -~60% fewer cyber-safeguard interventions per Claude Code session -Biology safeguards reportedly trigger 85% less often on benign elementary biology and medical questions -Vulnerability discovery is now allowed, while exploit generation, penetration testing and binary scanning remain restricted or redirected So far, sounds like a promising release. Although it clearly shows they care much more about business and enterprise users than us subscription pesants. Anyway: Testing time!
    @rishicomplexif you've been holding out on fable due to price or zdr you really should try fable 5.1
    @ScobleizerRT @ClaudeDevs: Fable 5.1 is now live in Claude Code and the Claude Platform. It's priced the same as Fable 5, with 75% cheaper API cache…
    @firstadopterStrong numbers from Fable 5.1
    @mattshumer_Fable 5.1 is a massive upgrade, but the bigger story is how much cheaper it is. Cache reads in particular are 75% cheaper! This puts it much closer to the pricing of GPT-5.6-Sol, while being a much more capable model.
    @RLanceMartinsome tips for Claude Fable 5.1 Try Fable 5.1 at low effort | Fable 5.1 at low effort is often competitive with Opus and Sonnet on $ / task while scoring higher. on CursorBench 3.2.0, Fable 5.1 at low effort is at parity w/ Fable 5 at high effort at a third of the cost. Prompt cache reads are 4x cheaper for Fable 5.1 | cache hits dropped from $1.00 to $0.25 / MTok. if you are using prompt caching, Claude Console can monitor your prompt cache hit rate. also run “/claude-api cost-optimize” in Claude Code to run diagnostics on your prompt cache configuration. see pricing: https://platform.claude.com/docs/en/build-with-claude/prompt-caching#pricing Simplify your prompts | remove verification rituals, emphasis boosters, scratchpad scaffolds, stale few-shot examples, or contradictory rules. in Claude Code, run “/claude-api prompt-audit” to inspect prompts or skills for common anti-patterns. see our prompt guide: https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1 Change effort mid-conversation w/o breaking the prompt cache | Previously, mid-conversation changes to effort invalidated the cache. see docs: https://platform.claude.com/docs/en/build-with-claude/effort#changing-effort-mid-conversation for migrating to Fable 5.1, see the migration guide and run "/claude-api migrate" in Claude Code to help update API configuration to use Fable 5.1. https://platform.claude.com/docs/en/models/fable-5-1/migration-guide
    @_sholtodouglasRT @rishicomplex: if you've been holding out on fable due to price or zdr you really should try fable 5.1
    @DanielleFongRT @claudeai: Cache reads with Fable 5.1 cost 75% less than Fable 5’s. This reduces the cost of the model in practice by around 25% for ty…
    @omarsar0Fable 5.1 looks like a more usable model. And a potential daily-driver. Time will tell. IMO, Opus 5 is probably still good enough for most tasks, while Fable 5.1 a more sophisticated coordinator amd verifier. The bigger and more exciting parts of Fable 5.1 are: - reduces cost by ~45% on highly agentic ones - reduces cost by ~25% on typical workloads - great for scientific reserch workflows - improved token-efficiency - better writer/prose

    32 Sources

    @cognitionOver 95% of tokens from a coding task are cached tokens. Fable 5.1 dropped the price of cached tokens by 4x, making it much more efficient for coding as a whole, despite higher uncached prices.
    @kimmonismusClaude Fable 5.1 is cheaper, substantially stronger on several agentic benchmarks, more concise, and apparently far less trigger-happy (says Anthropic). the tl;dr How much cheaper? -Input/output pricing remains $10/$50 per million -tokens. -Cache reads fall 75% to $0.25. -Anthropic estimates ~25% lower costs for typical workloads and up to ~45% for highly agentic, context-heavy work. BUT: not 45% cheaper for Claude subscriptions. ("...wherever usage is billed by token") How much better than Fable 5? -Scientific agent benchmark: 52.6% vs. 24.7% - more than 2× -AutomationBench: 31.4% vs. 17.1% — an 84% relative gain -GDPval-AA: 1,853 vs. 1,723 -CursorBench: 73.4% vs. 70.5% So: dramatic gains on some long-running tasks, modest improvements elsewhere, not a uniform intelligence jump. Verbosity also seems improved, although there is no standardized score. Rogo reports equal accuracy with 20% fewer tokens. Red Hat found its updates more concise and easier to follow. Every says it used half as many tokens as Opus 5 while running about twice as fast. And fewer unnecessary red flags: -~60% fewer cyber-safeguard interventions per Claude Code session -Biology safeguards reportedly trigger 85% less often on benign elementary biology and medical questions -Vulnerability discovery is now allowed, while exploit generation, penetration testing and binary scanning remain restricted or redirected So far, sounds like a promising release. Although it clearly shows they care much more about business and enterprise users than us subscription pesants. Anyway: Testing time!
    @rishicomplexif you've been holding out on fable due to price or zdr you really should try fable 5.1
    @ScobleizerRT @ClaudeDevs: Fable 5.1 is now live in Claude Code and the Claude Platform. It's priced the same as Fable 5, with 75% cheaper API cache…
    @firstadopterStrong numbers from Fable 5.1
    @mattshumer_Fable 5.1 is a massive upgrade, but the bigger story is how much cheaper it is. Cache reads in particular are 75% cheaper! This puts it much closer to the pricing of GPT-5.6-Sol, while being a much more capable model.
    @RLanceMartinsome tips for Claude Fable 5.1 Try Fable 5.1 at low effort | Fable 5.1 at low effort is often competitive with Opus and Sonnet on $ / task while scoring higher. on CursorBench 3.2.0, Fable 5.1 at low effort is at parity w/ Fable 5 at high effort at a third of the cost. Prompt cache reads are 4x cheaper for Fable 5.1 | cache hits dropped from $1.00 to $0.25 / MTok. if you are using prompt caching, Claude Console can monitor your prompt cache hit rate. also run “/claude-api cost-optimize” in Claude Code to run diagnostics on your prompt cache configuration. see pricing: https://platform.claude.com/docs/en/build-with-claude/prompt-caching#pricing Simplify your prompts | remove verification rituals, emphasis boosters, scratchpad scaffolds, stale few-shot examples, or contradictory rules. in Claude Code, run “/claude-api prompt-audit” to inspect prompts or skills for common anti-patterns. see our prompt guide: https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1 Change effort mid-conversation w/o breaking the prompt cache | Previously, mid-conversation changes to effort invalidated the cache. see docs: https://platform.claude.com/docs/en/build-with-claude/effort#changing-effort-mid-conversation for migrating to Fable 5.1, see the migration guide and run "/claude-api migrate" in Claude Code to help update API configuration to use Fable 5.1. https://platform.claude.com/docs/en/models/fable-5-1/migration-guide
    @_sholtodouglasRT @rishicomplex: if you've been holding out on fable due to price or zdr you really should try fable 5.1
    @DanielleFongRT @claudeai: Cache reads with Fable 5.1 cost 75% less than Fable 5’s. This reduces the cost of the model in practice by around 25% for ty…
    @omarsar0Fable 5.1 looks like a more usable model. And a potential daily-driver. Time will tell. IMO, Opus 5 is probably still good enough for most tasks, while Fable 5.1 a more sophisticated coordinator amd verifier. The bigger and more exciting parts of Fable 5.1 are: - reduces cost by ~45% on highly agentic ones - reduces cost by ~25% on typical workloads - great for scientific reserch workflows - improved token-efficiency - better writer/prose