正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Haiku 5.5 is now available in the Claude Platform and Claude Code. On average, it costs around 75% less to run than Haiku 4.5. It pairs well with Opus 5.5 or Sonnet 5.5 as a subagent. Use it for high-volume, cost-sensitive tasks like summaries, compactions, or database queries.

ClaudeDevs

735,549 subscribers

1,160,705 次观看 • 1 天前 •via X (Twitter)

新闻政治教育科学技术

Anya Rossi• Live Now

Private livecam show

31 条评论

ClaudeDevs 的头像

ClaudeDevs1 天前

For prompts under 100K tokens, it's $0.10 / $0.50 per million tokens with cache reads at $0.01. Above 100K tokens, $0.50 / $2.50 per million, with cache reads at $0.05.

ClaudeDevs 的头像

ClaudeDevs1 天前

We’re rolling out monthly Claude Platform API credits for Max and Team plans: Max 5x: $100 Max 20x: $200 Team: up to $500, pooled Works on any model, including Haiku 5.5, in your code or third-party harnesses. How it works and full terms:

PandaLivermore 🇺🇸 的头像

PandaLivermore 🇺🇸1 天前

Cool, can we get a weekly reset to give it a try?

ChickenStrip 的头像

ChickenStrip1 天前

Could we perhaps get a reset I genuinely blew through all my tokens right before this release

dazacode 的头像

dazacode1 天前

Anthropic did it again and my 200 dollar plan breathe another day

Kevo™ 的头像

Kevo™1 天前

total anthropic victory

Michael Tsortos 的头像

Michael Tsortos1 天前

Thanks Claude devs 🥳 any chance there will be more opportunities for Claude plushies? I’m literally waiting on Claude to conduct a search while I reply lol

Almost Human 像个人似的的头像

Almost Human 像个人似的1 天前

Finally someone to handle my compactions. Welcome aboard, little brother

Void&Null 的头像

Void&Null1 天前

Me when haiku

Marcus Bransbury 的头像

Marcus Bransbury1 天前

How does it compare against GPT 6 Luna?

AI Pulse 的头像

AI Pulse1 天前

look at the numbers. same time, same $0.05. 3 designs vs 28 that's not "cheaper", that's 9x more attempts for the same money. AI quality is turning into a volume game: whoever can afford the most tries wins. broke down why this changes the economics for anyone selling AI services, it's on my profile

Stats Wire 的头像

Stats Wire1 天前

RIP GPT Luna

Pratik Shah 的头像

Pratik Shah1 天前

Final Nail in the coffin. I am cancelling my Codex like right now. This is crazy.

An Xuan 的头像

An Xuan1 天前

opus 5.5 watching 10 haikus finish the egg drop in 58 seconds for $0.14

Sem Day 的头像

Sem Day1 天前

the subagent use case is probably one of the most interesting parts here... cheap models handling high-volume tasks while stronger models handle the harder reasoning

Tom "Plaetorius" Gernez 的头像

Tom "Plaetorius" Gernez1 天前

hey! Love Haiku, love Claude, love Anthropic, BUT please fix your SUPPORT, it’s absolutely IMPOSSIBLE to get a proper solution, even for BILLING issues Bests, and thank you!

ily⚡️ 的头像

ily⚡️1 天前

congrats but what is this demo lmaooo

John Herzog 的头像

John Herzog1 天前

pairing a cheap haiku subagent with opus for the heavy steps sounds like a nice way to stretch a budget

Issam 的头像

Issam1 天前

OMG I love Anthropic so much these days, they are just crushing it

iHurricane 的头像

iHurricane1 天前

Subagent use is the real story here. Delegating summaries and compactions to Haiku keeps the main context clean and the bill small.

Alex Tash 的头像

Alex Tash1 天前

Compaction is the one I’d test hardest. Saving money is great until the summary quietly drops the constraint the whole project depends on.

Sem Day 的头像

Sem Day1 天前

honestly, this might be a bigger deal for agents than just making Haiku better... cheap subagents could become the real scaling trick

Prello 的头像

Prello1 天前

This should be AMAZING for creation videos and motion graphics more consistantly

Bryce Del Rio 的头像

Bryce Del Rio1 天前

Does this work basically as a hill climb? opus is directing haiku what to try and your getting fast iteration loops?

stormbreaker.ai 的头像

stormbreaker.ai1 天前

0% → 39.2% on Terminal-Bench in one generation. What are you guys feeding these models? 🤯

Priyanshu Saraf 的头像

Priyanshu Saraf1 天前

lets celebrate the launch of this model with a reset!

serx · fireply.ai 的头像

serx · fireply.ai1 天前

neither run has dropped the egg anywhere yet. both still at none yet

Artzy 的头像

Artzy1 天前

the subagent efficiency is impressive

Wolfgang 的头像

Wolfgang1 天前

i wonder how it feels to use it for large‑scale queries

Serhii Shchoholiev 的头像

Serhii Shchoholiev1 天前

Haiku smarter than Luna is a bold claim, gotta test now

☀️ 的头像

☀️1 天前

You guys forgot to put audio for the vids

相关视频

Claude Sonnet 5.5 is out! We wrote a guide for building with it: • choosing between Sonnet 5.5 and Opus 5.5 • migrating from Sonnet 5 and tuning effort • using it in Claude Code

Claude Sonnet 5.5 is out! We wrote a guide for building with it: • choosing between Sonnet 5.5 and Opus 5.5 • migrating from Sonnet 5 and tuning effort • using it in Claude Code

ClaudeDevs

1,277,530 次观看 • 10 天前

This workflow will save you thousands with Claude. Run Opus 5.5, Sonnet 5.5, Haiku 5.5, and Fable 5.1 together, and stop spending Opus tokens on work that doesn't need Opus. The entire idea in one line: Opus plans, Sonnet edits, Haiku reads, Fable reviews at decision points. Roles, broken down: - Opus 5.5, high effort, owns the plan and reviews the final code - Sonnet 5.5, medium effort, is the worker: edits files, runs tests - Haiku 5.5, low effort, splits into explorer (searches and reads the codebase) and researcher (pulls docs). it's the first Haiku with an effort setting - Fable 5.1, set with /advisor fable. Opus calls it at decision points, and it gets the full transcript each time Three moments Opus tends to call it: → before committing to a plan: is this the right approach? → the same error shows up again: is this going nowhere? → before marking the task done: did something get skipped? Why Haiku only reads: Anthropic's launch post says Sonnet 5.5 and Opus 5.5 are still the better choice for complex agentic coding (Terminal-Bench 4.0: 39.2% for Haiku 5.5, 70.6% for Sonnet 5.5) and that Haiku 5.5 fits narrowly scoped subagent work. so it gets the lookups, not the edits. Anyone still running one model for everything is paying $4 per million input tokens to check whether a file exists. Haiku 5.5 does it for $0.10. Drop this into Claude Code 👇 "Rebuild my Claude Code setup around this structure: Confirm Claude Code is v2.1.293 or later, so the haiku alias resolves to Haiku 5.5. If it isn't, stop and tell me to run claude update. Look through ~/.claude/agents and .claude/agents for subagents already covering explorer, worker, and researcher. Only create new ones for roles that are missing. Set model: haiku, effort: low on explorer and researcher, with no Edit or Write tools. Set model: sonnet, effort: medium on worker. If an existing subagent is locked to a different model, leave it as is and just list it. Name the explorer subagent Explore so it overrides the built-in one, which otherwise runs on my main model. In ~/.claude/settings.json, set advisorModel to fable, and set effortLevel to high for claude-opus-5-5 under modelSettings. A top-level effortLevel in user settings doesn't apply to Opus 5.5. Check for anything disabling the advisor: CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, or anything blocking feature-flag fetches. Also check CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort settings, and CLAUDE_CODE_SUBAGENT_MODEL_FORCE, which makes Claude Code ignore subagent model fields. Report what you find. Don't change any of it yet. Add one line to ~/.claude/CLAUDE.md: consult the advisor before a big plan, when the same error shows up twice, and before marking a long task done. Show every change as a diff first. Wait for my go-ahead before touching anything."

This workflow will save you thousands with Claude. Run Opus 5.5, Sonnet 5.5, Haiku 5.5, and Fable 5.1 together, and stop spending Opus tokens on work that doesn't need Opus. The entire idea in one line: Opus plans, Sonnet edits, Haiku reads, Fable reviews at decision points. Roles, broken down: - Opus 5.5, high effort, owns the plan and reviews the final code - Sonnet 5.5, medium effort, is the worker: edits files, runs tests - Haiku 5.5, low effort, splits into explorer (searches and reads the codebase) and researcher (pulls docs). it's the first Haiku with an effort setting - Fable 5.1, set with /advisor fable. Opus calls it at decision points, and it gets the full transcript each time Three moments Opus tends to call it: → before committing to a plan: is this the right approach? → the same error shows up again: is this going nowhere? → before marking the task done: did something get skipped? Why Haiku only reads: Anthropic's launch post says Sonnet 5.5 and Opus 5.5 are still the better choice for complex agentic coding (Terminal-Bench 4.0: 39.2% for Haiku 5.5, 70.6% for Sonnet 5.5) and that Haiku 5.5 fits narrowly scoped subagent work. so it gets the lookups, not the edits. Anyone still running one model for everything is paying $4 per million input tokens to check whether a file exists. Haiku 5.5 does it for $0.10. Drop this into Claude Code 👇 "Rebuild my Claude Code setup around this structure: Confirm Claude Code is v2.1.293 or later, so the haiku alias resolves to Haiku 5.5. If it isn't, stop and tell me to run claude update. Look through ~/.claude/agents and .claude/agents for subagents already covering explorer, worker, and researcher. Only create new ones for roles that are missing. Set model: haiku, effort: low on explorer and researcher, with no Edit or Write tools. Set model: sonnet, effort: medium on worker. If an existing subagent is locked to a different model, leave it as is and just list it. Name the explorer subagent Explore so it overrides the built-in one, which otherwise runs on my main model. In ~/.claude/settings.json, set advisorModel to fable, and set effortLevel to high for claude-opus-5-5 under modelSettings. A top-level effortLevel in user settings doesn't apply to Opus 5.5. Check for anything disabling the advisor: CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, or anything blocking feature-flag fetches. Also check CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort settings, and CLAUDE_CODE_SUBAGENT_MODEL_FORCE, which makes Claude Code ignore subagent model fields. Report what you find. Don't change any of it yet. Add one line to ~/.claude/CLAUDE.md: consult the advisor before a big plan, when the same error shows up twice, and before marking a long task done. Show every change as a diff first. Wait for my go-ahead before touching anything."

Alvaro Cintas

51,598 次观看 • 1 天前

Introducing Claude Opus 5.5, the first model in our new Claude 5.5 family. It performs at the level of Claude Fable 5.1 for most tasks, and costs 40% less to run than Opus 5.

Introducing Claude Opus 5.5, the first model in our new Claude 5.5 family. It performs at the level of Claude Fable 5.1 for most tasks, and costs 40% less to run than Opus 5.

Claude

28,092,419 次观看 • 16 天前

holy sh*t. Official Anthropic tip for Claude Code: stop burning Opus 5.5 context on tasks Haiku 5.5 can swarm, while Sonnet 5.5 builds put the architect on call with /advisor claude --advisor opus --subagents haiku Sonnet 5.5 drives the primary session on high effort, writing diffs and running test suites Haiku 5.5 subagents swarm the repo in parallel at 340 tok/s, handling file discovery and spec docs lookup Opus 5.5 stays on call in the background as the advisor, only stepping in at three critical moments: → before a plan locks: does the implementation plan miss auth invariants or schema contracts? → when a test breaks twice: are we fixing the root cause or falling into a recursive rabbit hole? → before calling done: did the full diff introduce hidden regressions or break pre-flight rules? Opus 5.5 reviews. Sonnet 5.5 builds. Haiku 5.5 swarms Jev engineering runs the identical pattern one layer down: mechanical decisions that need no reasoning (which file to open, which tool to invoke, retry or abort) execute in 16ms, so the frontier models only wake up when execution paths actually diverge Plan on high. Delegate on medium. Keep Opus on call. - the full advisor setup > Opus 5.5 on call reads full session history and catches deep architectural traps > Sonnet 5.5 lead drives edits, writes core logic, and executes test harnesses > Haiku 5.5 subagents swarm AST parsing, grep scans, and API docs in parallel > JEV micro-fork layer resolves 1,500+ mechanical routing branches in under 16ms > advisor stays completely silent on routine bash execution to protect context paste the setup and this prompt into Claude Code below: "Configure my Claude Code workspace for hierarchical advisor orchestration: 1. Audit ~/.claude/settings.json and project config for model roles fitting lead, subagents, and advisor: > Pin main session model: sonnet with effortLevel: high for primary execution > Pin subagents model: haiku with effortLevel: medium for parallel file discovery and docs retrieval > Pin advisor model: opus on call for strategic review 2. Enable the advisor tool in ~/.claude/settings.json: > Set advisorModel to claude-opus-5-5 > Enable subagent parallel dispatcher pool (3x workers) 3. Configure automatic advisor consultation checkpoints in ~/.claude/CLAUDE.md: > Consult /advisor opus before finalizing multi-file architecture plans > Automatically summon /advisor opus when the same test or compiler error fails twice > Enforce advisor diff contract audit before declaring tasks complete or staging git commits 4. Constrain subagent scopes: > Haiku subagents return structured AST summaries and docs snippets only without modifying main session context Show every configuration diff first. Do not apply edits until confirmed" ↳

holy sh*t. Official Anthropic tip for Claude Code: stop burning Opus 5.5 context on tasks Haiku 5.5 can swarm, while Sonnet 5.5 builds put the architect on call with /advisor claude --advisor opus --subagents haiku Sonnet 5.5 drives the primary session on high effort, writing diffs and running test suites Haiku 5.5 subagents swarm the repo in parallel at 340 tok/s, handling file discovery and spec docs lookup Opus 5.5 stays on call in the background as the advisor, only stepping in at three critical moments: → before a plan locks: does the implementation plan miss auth invariants or schema contracts? → when a test breaks twice: are we fixing the root cause or falling into a recursive rabbit hole? → before calling done: did the full diff introduce hidden regressions or break pre-flight rules? Opus 5.5 reviews. Sonnet 5.5 builds. Haiku 5.5 swarms Jev engineering runs the identical pattern one layer down: mechanical decisions that need no reasoning (which file to open, which tool to invoke, retry or abort) execute in 16ms, so the frontier models only wake up when execution paths actually diverge Plan on high. Delegate on medium. Keep Opus on call. - the full advisor setup > Opus 5.5 on call reads full session history and catches deep architectural traps > Sonnet 5.5 lead drives edits, writes core logic, and executes test harnesses > Haiku 5.5 subagents swarm AST parsing, grep scans, and API docs in parallel > JEV micro-fork layer resolves 1,500+ mechanical routing branches in under 16ms > advisor stays completely silent on routine bash execution to protect context paste the setup and this prompt into Claude Code below: "Configure my Claude Code workspace for hierarchical advisor orchestration: 1. Audit ~/.claude/settings.json and project config for model roles fitting lead, subagents, and advisor: > Pin main session model: sonnet with effortLevel: high for primary execution > Pin subagents model: haiku with effortLevel: medium for parallel file discovery and docs retrieval > Pin advisor model: opus on call for strategic review 2. Enable the advisor tool in ~/.claude/settings.json: > Set advisorModel to claude-opus-5-5 > Enable subagent parallel dispatcher pool (3x workers) 3. Configure automatic advisor consultation checkpoints in ~/.claude/CLAUDE.md: > Consult /advisor opus before finalizing multi-file architecture plans > Automatically summon /advisor opus when the same test or compiler error fails twice > Enforce advisor diff contract audit before declaring tasks complete or staging git commits 4. Constrain subagent scopes: > Haiku subagents return structured AST summaries and docs snippets only without modifying main session context Show every configuration diff first. Do not apply edits until confirmed" ↳

mirku

610,241 次观看 • 1 天前

🚀 Claude Opus 5.5 is now available in VS Code with GitHub Copilot. Built for agentic coding, long-running tasks, and knowledge work. Give it a try today!

🚀 Claude Opus 5.5 is now available in VS Code with GitHub Copilot. Built for agentic coding, long-running tasks, and knowledge work. Give it a try today!

Visual Studio Code

75,730 次观看 • 16 天前

this is certified f*cking gold for anyone paying for Claude Sonnet 5.5 costs half of what Opus 5.5 does on real office work across 44 jobs it scores 1844. Opus scores 1846 on coding it went from 10.3% to 70.6% in one version and passed Opus on the way most of what you pay Opus for, Sonnet 5.5 now does at half the price here's how to split the work: • give it to Sonnet 5.5 > bug fixes and well-scoped coding tasks > decks built from your own slide template > spreadsheets and polished documents > UI polish, it has a real eye for design > fast back-and-forth, it runs 30%+ faster • keep it for Opus 5.5 > long, open-ended work with judgment calls for hours > anything where one wrong assumption costs you a day • the setting that saves the most > Medium is the default in the Claude apps and Claude Code > on Low or Medium it beats Sonnet 5's best score for a tenth of the cost > raise effort only when the first answer falls short • the price > $2 in and $10 out, against $4 and $20 for Opus > cache reads $0.20 on both • check before you switch > if you ran Sonnet with thinking off, move to the new between_tools setting first whoever routes the weekly grunt work to Sonnet 5.5 and saves Opus for the hard calls ships more on half the budget, and that's the person who gets noticed

this is certified f*cking gold for anyone paying for Claude Sonnet 5.5 costs half of what Opus 5.5 does on real office work across 44 jobs it scores 1844. Opus scores 1846 on coding it went from 10.3% to 70.6% in one version and passed Opus on the way most of what you pay Opus for, Sonnet 5.5 now does at half the price here's how to split the work: • give it to Sonnet 5.5 > bug fixes and well-scoped coding tasks > decks built from your own slide template > spreadsheets and polished documents > UI polish, it has a real eye for design > fast back-and-forth, it runs 30%+ faster • keep it for Opus 5.5 > long, open-ended work with judgment calls for hours > anything where one wrong assumption costs you a day • the setting that saves the most > Medium is the default in the Claude apps and Claude Code > on Low or Medium it beats Sonnet 5's best score for a tenth of the cost > raise effort only when the first answer falls short • the price > $2 in and $10 out, against $4 and $20 for Opus > cache reads $0.20 on both • check before you switch > if you ran Sonnet with thinking off, move to the new between_tools setting first whoever routes the weekly grunt work to Sonnet 5.5 and saves Opus for the hard calls ships more on half the budget, and that's the person who gets noticed

Annatar.md

19,513 次观看 • 10 天前

I asked Sonnet 5.5 to create a overcooked clone i could play in the broswer. the results shocked me... It is delivering triple aaa level polish at 20x cheaper than opus 5.5 if you put it in x-high it will RUN. this model will be a perfect worker agent for opus 5.5 or the upcoming fable 5.5 to orchestrate. Anthropic is MOGGGING rn.

I asked Sonnet 5.5 to create a overcooked clone i could play in the broswer. the results shocked me... It is delivering triple aaa level polish at 20x cheaper than opus 5.5 if you put it in x-high it will RUN. this model will be a perfect worker agent for opus 5.5 or the upcoming fable 5.5 to orchestrate. Anthropic is MOGGGING rn.

Max Blade

82,685 次观看 • 10 天前

Haiku 4.5 is a workhorse that makes the coding experience in Claude Code feel really fast. While Sonnet 4.5 remains the default, Haiku 4.5 now powers the Explore subagent which can rapidly gather context on your codebase to build apps even faster.

Haiku 4.5 is a workhorse that makes the coding experience in Claude Code feel really fast. While Sonnet 4.5 remains the default, Haiku 4.5 now powers the Explore subagent which can rapidly gather context on your codebase to build apps even faster.

cat

205,593 次观看 • 11 个月前

Introducing Claude Opus 5.5! 40% lower cost than Opus 5 with cache reads 60% cheaper. It performs at the level of Claude Fable 5.1 for most tasks. I celebrated with a pelican riding a bike in Three.js.

Introducing Claude Opus 5.5! 40% lower cost than Opus 5 with cache reads 60% cheaper. It performs at the level of Claude Fable 5.1 for most tasks. I celebrated with a pelican riding a bike in Three.js.

Addy Osmani

417,945 次观看 • 16 天前

Official Anthropic tip for Claude Code: stop burning Opus 5.5 on work Sonnet 5.5 can do, while Fable 5.1 sits idle hand the grunt work to Sonnet 5.5 subagents and put Fable 5.1 on call run /advisor fable Opus 5.5 plans and merges Sonnet 5.5 subagents read, edit and run the tests Fable 5.1 reads the full session and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Sonnet 5.5 builds. Fable 5.1 reviews. Opus 5.5 ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split - the full tree > Opus 5.5 on high runs the main session > explorer reads the code on Sonnet 5.5 > worker edits and runs tests on Sonnet 5.5 > researcher pulls the docs on Sonnet 5.5 > all three on medium > Fable 5.1 on call for main and every subagent paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: sonnet, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

Official Anthropic tip for Claude Code: stop burning Opus 5.5 on work Sonnet 5.5 can do, while Fable 5.1 sits idle hand the grunt work to Sonnet 5.5 subagents and put Fable 5.1 on call run /advisor fable Opus 5.5 plans and merges Sonnet 5.5 subagents read, edit and run the tests Fable 5.1 reads the full session and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Sonnet 5.5 builds. Fable 5.1 reviews. Opus 5.5 ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split - the full tree > Opus 5.5 on high runs the main session > explorer reads the code on Sonnet 5.5 > worker edits and runs tests on Sonnet 5.5 > researcher pulls the docs on Sonnet 5.5 > all three on medium > Fable 5.1 on call for main and every subagent paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: sonnet, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

delost

43,704 次观看 • 6 天前

Grok 4.5 is a "Wow!" moment. 🤯 > Opus 4.8 & GPT-5.5 level on benchmarks > Costs less than Sonnet 5 Is that real? Hard to believe. Added Grok 4.5 as an implementer agent in fable-advisor. It replaces Sonnet 5. Use Fable as the orchestrator and a combo of: 1. Grok 4.5 2. Opus 4.8 3. GPT-5.5 As implementer agents. Uses the Grok Build CLI so if you log in with an X premium account you don't have to pay API fees.

Grok 4.5 is a "Wow!" moment. 🤯 > Opus 4.8 & GPT-5.5 level on benchmarks > Costs less than Sonnet 5 Is that real? Hard to believe. Added Grok 4.5 as an implementer agent in fable-advisor. It replaces Sonnet 5. Use Fable as the orchestrator and a combo of: 1. Grok 4.5 2. Opus 4.8 3. GPT-5.5 As implementer agents. Uses the Grok Build CLI so if you log in with an X premium account you don't have to pay API fees.

Dan McAteer

191,832 次观看 • 3 个月前

This is f*cking insane. This Claude Code tip saved me thousands of dollars. once Opus 5.5 is your main model, stop burning it on work Sonnet 5.5 can do, while Fable 5.1 sits idle hand the grunt work to Sonnet 5.5 subagents and put Fable 5.1 on call run /advisor fable Opus 5.5 plans and ships the final code Sonnet 5.5 subagents read, edit and run the tests Fable 5.1 reads the full session, every tool call included, and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Sonnet 5.5 builds. Fable 5.1 reviews. Opus 5.5 ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split anyone still running one model for everything is paying Opus prices to decide whether a file exists - the full tree > Opus 5.5 on high runs the main session > explorer reads the code on Sonnet 5.5 > worker edits and runs tests on Sonnet 5.5 > researcher pulls the docs on Sonnet 5.5 > all three on medium > Fable 5.1 on call for main and every subagent paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: sonnet, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

This is f*cking insane. This Claude Code tip saved me thousands of dollars. once Opus 5.5 is your main model, stop burning it on work Sonnet 5.5 can do, while Fable 5.1 sits idle hand the grunt work to Sonnet 5.5 subagents and put Fable 5.1 on call run /advisor fable Opus 5.5 plans and ships the final code Sonnet 5.5 subagents read, edit and run the tests Fable 5.1 reads the full session, every tool call included, and only speaks up at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Sonnet 5.5 builds. Fable 5.1 reviews. Opus 5.5 ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split anyone still running one model for everything is paying Opus prices to decide whether a file exists - the full tree > Opus 5.5 on high runs the main session > explorer reads the code on Sonnet 5.5 > worker edits and runs tests on Sonnet 5.5 > researcher pulls the docs on Sonnet 5.5 > all three on medium > Fable 5.1 on call for main and every subagent paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Check ~/.claude/agents and .claude/agents for subagents that already fit explorer, worker and researcher. > Draft new ones only for missing roles > Give each model: sonnet, effort: medium > Skip any that pin a different model and list them 2. Set the main session to high via effortLevel in ~/.claude/settings.json, and set advisorModel to fable 3. Find anything that keeps the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) plus CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report them, change nothing 4. Add one rule to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

delost

48,238 次观看 • 5 天前

Claude Opus 5.5 just one shot a full multiplayer battle royale like Call of Duty Warzone. Then I used Claude Opus 5.5 with Ultracode to polish it. Parachute drops, a storm that closes over 8 circles, a full map with named towns, and real players dropping in from around the world. Opus 5.5 is unstoppable.

Claude Opus 5.5 just one shot a full multiplayer battle royale like Call of Duty Warzone. Then I used Claude Opus 5.5 with Ultracode to polish it. Parachute drops, a storm that closes over 8 circles, a full map with named towns, and real players dropping in from around the world. Opus 5.5 is unstoppable.

BridgeMind

108,135 次观看 • 6 天前

Boris Cherny, creator of Claude Code: "Opus 5.5 does in a day what used to take your team a month. Most people will keep using it wrong." In 12 minutes he explains why Opus 5.5 needs less prompting than any model before, and why your old detailed prompts now work against you. Watch it, then read the article below on how to prompt Opus 5.5 👇

Boris Cherny, creator of Claude Code: "Opus 5.5 does in a day what used to take your team a month. Most people will keep using it wrong." In 12 minutes he explains why Opus 5.5 needs less prompting than any model before, and why your old detailed prompts now work against you. Watch it, then read the article below on how to prompt Opus 5.5 👇

Rahul

151,024 次观看 • 12 天前

Opus 5.5 killed the game. We had it and GPT-6 Sol both draw Dario in Canva with ego (lite). Claude Opus 5.5: 1h 23m, $6.31 GPT-6 Sol: 26m, $14.97 Opus took 3x longer, cost less than half, and drew a much better Dario.

Opus 5.5 killed the game. We had it and GPT-6 Sol both draw Dario in Canva with ego (lite). Claude Opus 5.5: 1h 23m, $6.31 GPT-6 Sol: 26m, $14.97 Opus took 3x longer, cost less than half, and drew a much better Dario.

ego

178,956 次观看 • 14 天前

Today we launched Claude Sonnet 5.5! 30% faster and costs up to 30% less than Sonnet 5 for most work. Strong for well-scoped everyday tasks (fixing bugs, creating docs, slides). Lance Martin had models paint the same photo in code. You can see the jump:

Today we launched Claude Sonnet 5.5! 30% faster and costs up to 30% less than Sonnet 5 for most work. Strong for well-scoped everyday tasks (fixing bugs, creating docs, slides). Lance Martin had models paint the same photo in code. You can see the jump:

Addy Osmani

101,927 次观看 • 10 天前

anthropic just dropped claude haiku 4.5 and it absolutely COOKS with web design especially compared to haiku 3.5 basically on par with sonnet 4 (at 1/3 the price) they really nailed the cost + speed + quality ratio

anthropic just dropped claude haiku 4.5 and it absolutely COOKS with web design especially compared to haiku 3.5 basically on par with sonnet 4 (at 1/3 the price) they really nailed the cost + speed + quality ratio

Wes Winder

135,264 次观看 • 11 个月前

anthropic is testing haiku 5.5 too been using fable 5.5 for the last few days but noticed something weird some outputs from fable 5.1 that knows tibo the reset guy were way worse than sonnet 5.5 but why would it give worse outputs? so i can only think of one thing that team is routing some prompts to haiku 5.5 through fable 5.1 too and testing it that way which makes me think we might see haiku 5.5 in next week or two here's one weird output i got just look at how different these outputs are even tho both were run on fable 5.1 xhigh that knows tibo the reset guy

anthropic is testing haiku 5.5 too been using fable 5.5 for the last few days but noticed something weird some outputs from fable 5.1 that knows tibo the reset guy were way worse than sonnet 5.5 but why would it give worse outputs? so i can only think of one thing that team is routing some prompts to haiku 5.5 through fable 5.1 too and testing it that way which makes me think we might see haiku 5.5 in next week or two here's one weird output i got just look at how different these outputs are even tho both were run on fable 5.1 xhigh that knows tibo the reset guy

J A Z I I

40,526 次观看 • 4 天前

We've just added Claude Sonnet 5.5 to Caffeine. It's Anthropic's model for work you can describe clearly: fix this bug, add a booking form, polish this page. Anthropic says it's 30% faster than Sonnet 5, and cheaper than Opus 5.5. Keep Opus 5.5 for planning something new, and hand the follow-up work to Sonnet 5.5. On Caffeine, you can switch between models in the same conversation.

We've just added Claude Sonnet 5.5 to Caffeine. It's Anthropic's model for work you can describe clearly: fix this bug, add a booking form, polish this page. Anthropic says it's 30% faster than Sonnet 5, and cheaper than Opus 5.5. Keep Opus 5.5 for planning something new, and hand the follow-up work to Sonnet 5.5. On Caffeine, you can switch between models in the same conversation.

caffeine

21,968 次观看 • 8 天前

🚀 Anthropic's Claude Opus 5.5 is now generally available in GitHub Copilot. Our early testing shows it stands out in efficiency, delivering task resolution comparable to Claude Opus 5 while using significantly fewer steps and tokens, with fast error recovery on multistep tasks. Try it out for agentic coding, long-running agentic tasks, and knowledge work. Find it in the GitHub Copilot app, CLI, and Visual Studio Code.

🚀 Anthropic's Claude Opus 5.5 is now generally available in GitHub Copilot. Our early testing shows it stands out in efficiency, delivering task resolution comparable to Claude Opus 5 while using significantly fewer steps and tokens, with fast error recovery on multistep tasks. Try it out for agentic coding, long-running agentic tasks, and knowledge work. Find it in the GitHub Copilot app, CLI, and Visual Studio Code.

GitHub

123,709 次观看 • 16 天前