Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Do the math on 1,000 coding tasks a month. Opus 5.5 doing everything: $6,420 Jev + Opus 5.5: $2,000 That's $4,420 a month back. $53,040 a year. Same tasks. Same model writing the code. The only difference is who makes the small decisions. Full build below. Bookmark this.

20,547 Aufrufe • vor 1 Tag •via X (Twitter)

15 Kommentare

Profilbild von Hussain Hashim | Building SundayBack
Hussain Hashim | Building SundayBackvor 22 Stunden

@cyrilXBT another twist: watch out for context switching. It can eat up that $53k in mental load, even with optimized tools.

Profilbild von i2bhai8
i2bhai8vor 1 Tag

Anthropic lists Opus 5.5 at $4 input, $20 output, $0.20 cache read and $5 cache write per million tokens. The $6,420 line does not say which of those rates it used.

Profilbild von Vipul Kumar Kewat
Vipul Kumar Kewatvor 1 Tag

Same model, same coding tasks, lower costs.

Profilbild von Artzy
Artzyvor 19 Stunden

Routing layer changes the math entirely

Profilbild von 𝓔𝓼𝓶𝓮𝓵𝓮𝔂𝓱𝓱🌸
𝓔𝓼𝓶𝓮𝓵𝓮𝔂𝓱𝓱🌸vor 23 Stunden

Choose happiness whenever you can! 🥰

Profilbild von Mohammad Vazin
Mohammad Vazinvor 1 Tag

The number that matters is the miss rate. If Jev gets even 1 in 20 of those small calls wrong and Opus has to redo the work, a chunk of that $4,420 goes back. Put the rework rate next to the cost chart and this gets a lot more convincing.

Profilbild von Prince Phado YKJ
Prince Phado YKJvor 18 Stunden

Hi

Profilbild von James Malsawm
James Malsawmvor 1 Tag

$4,420 a month back just from moving the small decisions off opus 5.5 is the part people miss. most of the bill is the model thinking about stuff that didn't need thinking. curious how often jev picks wrong and opus 5.5 has to clean it up, that's where the real savings get decided.

Profilbild von Lea Thompson
Lea Thompsonvor 1 Tag

everyone's bookmarking the savings and nobody's budgeting for the tuesday where jev confiddntly ships the wrong thing

Profilbild von NITO
NITOvor 1 Tag

letting a cheaper model handle the small calls and opus only write the code is the move fr curious how often the small decisions end up wrong and cost the savings back tho

Profilbild von furan
furanvor 19 Stunden

省钱才是硬道理 小决策里藏着大金矿

Profilbild von 小橙子的聊车天地
小橙子的聊车天地vor 19 Stunden

Love seeing this

Profilbild von ZeroMazed
ZeroMazedvor 1 Tag

everyone bookmarking this and nobody asking who's checking Jev's work at 3am

Profilbild von Macro Bombastic
Macro Bombasticvor 1 Tag

the small decisions are where the real money hides tbh

Profilbild von 车友圈的暖心小豆子
车友圈的暖心小豆子vor 14 Stunden

grabbed this warm-up round shows footwork worth trying alone

Ähnliche Videos

THIS IS PURE F*CKING GOLD Anthropic just shared one of the best tricks for Claude Code. The idea: run Sonnet, Haiku and Opus 5.5 at the same time, each one doing only what it's best at. Better results and way fewer tokens, because every task lands on the right model. You just start Claude Code like this: claude --model sonnet --advisor opus here's how it splits: → Sonnet 5 runs the session and writes the code → Haiku 5.5 explores files and docs in parallel → Opus 5.5 stays on call as advisor for the big decisions → you stop burning Opus context on tasks that don't need it Opus only steps in at three moments: → before a plan locks → when the same error hits twice → before calling it done Sonnet builds. Haiku explores. Opus reviews. 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 milliseconds, and the big models only see the ones that split the full tree > Sonnet 5 runs the main session and edits code > search maps the repo on Haiku 5.5 > grep finds call sites on Haiku 5.5 > docs pulls the API reference on Haiku 5.5 > Opus 5.5 on call as advisor, reads the full transcript when consulted > JEV routes micro-forks in milliseconds paste the tree and this prompt into Claude Code ↓ "Reconfigure my Claude Code setup around this tree: 1. Run the main session on Sonnet 5 with Opus 5.5 as advisor. 2. Create three read-only Haiku 5.5 subagents: search (maps the repo), grep (finds call sites), docs (pulls the API reference). 3. Add one rule to CLAUDE.md: consult the advisor before locking a plan, after the same error twice, and before calling a task done. 4. Route fast deterministic forks (tool choice, path selection, retries) through JEV. Show me every change as a diff first. No edits until I say go." ↳ save it, it'll come in handy.

delost

312,522 Aufrufe • vor 7 Tagen

THIS IS ABSOLUTE F*CKING GOLD Anthropic just shared one of the best tricks for Claude Code The idea: run Opus 5.5 as lead, and swarm cheap Haiku 5.5 teammates in parallel Opus-level architecture on every task, without burning Opus context on routine turns You just launch Claude Code like this: export CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 claude --model opus --teammate-mode auto here's the split: → Opus 5.5 leads the team, decomposes tasks into a DAG, and signs off → Haiku 5.5 swarms as autonomous teammates across isolated context windows → Sonnet 5.5 implements heavy multi-file refactors without blocking peers → you stop burning Opus context on a hundred agent transcripts Opus only steps in at three moments: → breaking your goal into a dependency DAG before the run → approving diff plans before teammates edit files → signing off on verified results before anything ships Opus leads · Haiku swarms · Sonnet 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 milliseconds, and the big models only see the ones that split the full tree > Opus 5.5 runs the lead session and coordinates the task DAG > security audits auth and JWT handling on Haiku 5.5 > perf-scout profiles p99 latency bottlenecks on Haiku 5.5 > qa-engine executes full test suites on Haiku 5.5 > patcher refactors complex multi-file logic on Sonnet 5.5 > Opus 5.5 reads only verified PR diffs > JEV routes micro-forks in milliseconds paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Enable CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 with --teammate-mode auto 2. Run the main lead session on Opus 5.5 to decompose tasks into a dependency DAG 3. Spawn three parallel teammates on Haiku 5.5 for security, perf, and qa 4. Have teammates self-claim unblocked tasks, coordinate findings via P2P mailbox, and draft plans before modifying code 5. Route heavy multi-file patches to Sonnet 5.5 and clear fast deterministic forks through JEV Show me every change as a diff first, no edits until I say go" ↳ save it, you'll use this on every serious codebase

mirku

55,698 Aufrufe • vor 3 Tagen

THIS IS ACTUAL F*CKING GOLD Anthropic just shared one of the best tricks for Claude Code. The idea: run Sonnet, Haiku and Opus 5.5 together, each one doing only the job it's best at. Opus-level judgment on every big call, without paying Opus rates for every routine turn. You just launch Claude Code like this: claude --model sonnet --advisor opus here's the split: → Sonnet 5.5 runs the session and writes the code → Haiku 5.5 explores files and docs in parallel → Opus 5.5 stays on call as advisor for the big calls → you stop spending Opus on work that doesn't need it Opus only steps in at three moments: → before a plan locks → when the same error shows up twice → before calling it done Sonnet builds. Haiku explores. Opus reviews. 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 milliseconds, and the big models only see the ones that split the full tree > Sonnet 5.5 runs the main session and edits code > search maps the repo on Haiku 5.5 > grep finds call sites on Haiku 5.5 > docs pulls the API reference on Haiku 5.5 > Opus 5.5 on call as advisor, reads the whole transcript when consulted > JEV routes micro-forks in milliseconds paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Run the main session on Sonnet 5.5 with Opus 5.5 as advisor. 2. Create three read-only Haiku 5.5 subagents: search (maps the repo), grep (finds call sites), docs (pulls the API reference). 3. Add one rule to CLAUDE.md: consult the advisor before locking a plan, after the same error twice, and before calling a task done. 4. Route fast deterministic forks (tool choice, path selection, retries) through JEV. Show me every change as a diff first. No edits until I say go." ↳ save it, you'll use this every single day.

delost

314,884 Aufrufe • vor 5 Tagen

THIS IS A PURE F*CKING GOLDMINE Anthropic just shared one of the best tricks for Claude Code. The idea: let Opus 5.5 write the plan as a script, and let a swarm of cheaper agents run it. Bigger jobs and way fewer Opus tokens, because the script holds the plan and Opus only sees the final answer. You just launch Claude Code like this: claude --model opus --effort ultracode here's the split: → Opus 5.5 turns your task into a workflow script → Haiku 5.5 agents scan every file in parallel → Sonnet 5.5 agents patch each fix in its own isolated copy → you stop burning Opus context on a hundred agent transcripts Opus only shows up at three moments: → writing the workflow before the run → reading the verified results after it → signing off before anything ships Opus plans. Haiku scans. Sonnet 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 milliseconds, and the big models only see the ones that split the full tree > Opus 5.5 runs the main session and writes the workflow > scan audits every file on Haiku 5.5 > edit patches each fix on Sonnet 5.5 in an isolated copy > verify cross-checks every finding on Sonnet 5.5 > Opus 5.5 reads only what survived verification > JEV routes micro-forks in milliseconds paste the tree and this prompt into Claude Code ↓ "Rebuild my Claude Code setup around this tree: 1. Run the main session on Opus 5.5 with ultracode on. 2. In every workflow, run read-only scan stages on Haiku 5.5 and edit stages on Sonnet 5.5, each edit in its own isolated copy. 3. Add one rule to CLAUDE.md: every finding gets an independent verifier agent before it's reported, and fix loops stop after two rounds with no progress. 4. Route fast deterministic forks (tool choice, path selection, retries) through JEV. Show me every change as a diff first. No edits until I say go." ↳ save it, it'll come in handy.

delost

388,662 Aufrufe • vor 4 Tagen

this is pure f*cking treasure Claude Code tip: once Opus 5.5 is your main model, stop leaving Fable 5.1 sitting idle and stop burning Opus tokens on tasks Sonnet 5.5 can swarm put it on call with /goal claude --auto-mode "/goal all tests pass and lint is clean" Opus 5.5 keeps writing the code in auto mode Sonnet 5.5 swarms the routine work at medium Fable 5.1 inspects the full transcript and only speaks up at the turn boundary: → not yet met: am I drifting from acceptance criteria? → met: do the tests, diffs, and lint hold? → impossible: am I chasing an unreachable state? Fable grades. Opus ships JEV engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or halt) go to JEV in under 16ms, and the big models only see the ones that split — the full tree > Opus 5.5 on high runs the main session > worker edits and patches code on Sonnet 5.5 > explorer indexes AST maps and call sites on Sonnet 5.5 > verifier runs tests and linters on Sonnet 5.5 > all three subagents on medium effort > Fable 5.1 on call as the Stop hook evaluator > JEV routes micro-forks under 16ms paste the tree and this prompt into Claude Code ↓ "Reconfigure my Claude Code setup around this tree: 1. Set the main session to Opus 5.5 on high effort with auto mode enabled. 2. Put Fable 5.1 on call as a session-scoped evaluator attached to the Stop hook: - Read-only transcript evaluation with zero tool calls - Three structured outcomes: not yet met (with steering notes), met (auto-clear), and impossible (abort early) 3. Spawn Sonnet 5.5 subagents on medium effort for worker, explorer, and verifier roles. Defer goal checks while background tasks run. 4. Route fast deterministic forks (tool resolution, path selection, auto-retries) through JEV. 5. Add one rule to CLAUDE.md: run long tasks with: claude --auto-mode \"/goal \" Show me every configuration change as a diff first. No edits until I say go." ↳

mirku

41,948 Aufrufe • vor 12 Tagen

THIS IS ACTUAL F*CKING GOLD Anthropic just quietly dropped one of the best setups for Claude Code The rule: orchestrate Sonnet, Haiku and Opus 5.5 simultaneously, locking every model into the exact lane it dominates Opus-grade intelligence on critical architectural calls, zero Opus burn on routine terminal iterations Launch Claude Code with this flag pair: claude --model sonnet --advisor opus how the workload divides: → Sonnet 5.5 leads the main session and cuts the actual code → Haiku 5.5 swarms repos, greps call sites, and parses docs concurrently → Opus 5.5 remains on standby as advisor for high-leverage checkpoints → you eliminate token waste on work that never required frontier reasoning Opus only gets triggered on three specific events: → right before locking an architectural plan → the second an identical error hits twice → right before marking a complex task complete Sonnet builds · Haiku explores · Opus reviews JEV engineering applies the exact same logic one layer deeper: deterministic branches (file selection, tool dispatch, fast retry vs abort) clear in sub-milliseconds, so the frontier models only handle genuine forks the architecture tree: > Sonnet 5.5 drives the primary terminal session and edits code > search crawls repo structure on Haiku 5.5 > grep locates call signatures on Haiku 5.5 > docs fetches API specs and schemas on Haiku 5.5 > Opus 5.5 stands on call as advisor, ingesting full context when pinged > JEV resolves instant deterministic routing feed this tree and prompt directly into Claude Code ↓ "Configure my Claude Code environment around this multi-model tree: 1. Run the primary session on Sonnet 5.5 with Opus 5.5 as advisor 2. Spawn three read-only Haiku 5.5 subagents: search (repo mapping), grep (call sites), docs (API references) 3. Enforce one rule in CLAUDE.md: ping advisor before locking any plan, upon repeating any error twice, and before final task handoff 4. Route instantaneous deterministic forks (tool choice, path check, retries) through JEV Show every file update as a diff first, make zero changes without confirmation" ↳ bookmark this, you'll run it every single day

mirku

80,072 Aufrufe • vor 4 Tagen