Loading video...

Video Failed to Load

Go Home

Claude Haiku 5.5 really cooked hard

TechyAizen's profile picture

Aizen

1,393 subscribers

26,419 views • 18 days ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Claude Haiku 5.5 vs GPT-6 Luna
0:19

Claude Haiku 5.5 vs GPT-6 Luna

Da7em

45,204 views • 19 days ago

Gemini 4 Argon vs Claude Haiku 5.5 Haiku looks better, nails the lighting, and somehow costs 40x less.
0:13

Gemini 4 Argon vs Claude Haiku 5.5 Haiku looks better, nails the lighting, and somehow costs 40x less.

Da7em

30,516 views • 13 days ago

Claude Coders: Pair Haiku 5.5 with an Opus advisor *NOW*. Opus 5.5 checks Haiku's work. Take advantage of the speed and cost-efficiency of Haiku with the intelligence of Opus. Copy this into settings.json (or ask Claude to): {"model":"haiku","advisorModel":"opus"}
0:13

Claude Coders: Pair Haiku 5.5 with an Opus advisor *NOW*. Opus 5.5 checks Haiku's work. Take advantage of the speed and cost-efficiency of Haiku with the intelligence of Opus. Copy this into settings.json (or ask Claude to): {"model":"haiku","advisorModel":"opus"}

Dan McAteer

113,517 views • 19 days ago

Introducing Claude Haiku 5.5: the cheapest, fastest, and most capable small model we’ve ever released. On average, it costs around 75% less to run than Claude Haiku 4.5.
0:11

Introducing Claude Haiku 5.5: the cheapest, fastest, and most capable small model we’ve ever released. On average, it costs around 75% less to run than Claude Haiku 4.5.

Claude

6,760,319 views • 19 days ago

holo 3D card effect made by Claude Haiku 5.5 it's cheap yet works like a champ, impressivee
0:19

holo 3D card effect made by Claude Haiku 5.5 it's cheap yet works like a champ, impressivee

Ann Nguyen

61,314 views • 19 days ago

Anthropic just introduced Claude Haiku 5.5! 🔥 A new small model designed to deliver speed, capability, and affordability. The best part? It costs around 75% less to run than Haiku 4.5.
0:11

Anthropic just introduced Claude Haiku 5.5! 🔥 A new small model designed to deliver speed, capability, and affordability. The best part? It costs around 75% less to run than Haiku 4.5.

NOOR TECH

31,677 views • 17 days ago

it's f*cking insane.. Anthropic just dropped a Claude Code setup that makes tokens up to 97% cheaper Opus brains, Sonnet bill: > Sonnet runs your session and writes the code > Haiku subagents grab the small tasks > Opus steps in only when Sonnet gets stuck > it checks the work, digs into the problem and puts Sonnet back on track $19.50 saved on every 1M tokens a Haiku 5.5 subagent writes, compared with Opus 5.5 one command sets it up: npx claude-code-templates@latest --setting model/sonnet-opus-advisor-haiku-subagents the easiest money you'll save on Claude Code this year
0:18

it's f*cking insane.. Anthropic just dropped a Claude Code setup that makes tokens up to 97% cheaper Opus brains, Sonnet bill: > Sonnet runs your session and writes the code > Haiku subagents grab the small tasks > Opus steps in only when Sonnet gets stuck > it checks the work, digs into the problem and puts Sonnet back on track $19.50 saved on every 1M tokens a Haiku 5.5 subagent writes, compared with Opus 5.5 one command sets it up: npx claude-code-templates@latest --setting model/sonnet-opus-advisor-haiku-subagents the easiest money you'll save on Claude Code this year

Mnimiy

55,980 views • 17 days ago

haiku 5.5 vs deepseek v4.1 flash tested both models with same prompt at highest reasoning available > haiku took 90 mins and cost $3.4 via claude code > v4.1 flash took 50 mins and cost $0.67 via aihubmix api haiku failed to make the game on the first try cuz of claude code bug, then spent over 30 mins just thinking on second try which one did better here?
0:15

haiku 5.5 vs deepseek v4.1 flash tested both models with same prompt at highest reasoning available > haiku took 90 mins and cost $3.4 via claude code > v4.1 flash took 50 mins and cost $0.67 via aihubmix api haiku failed to make the game on the first try cuz of claude code bug, then spent over 30 mins just thinking on second try which one did better here?

J A Z I I

22,890 views • 19 days ago

Opus 5.5, Sonnet 5.5, Haiku 5.5 ve GPT-6 Luna'ya Türkiye haritasını ezberden, kodla çizdirdim. İnternet yok, referans yok, 81 il sınırıyla. Gerçek sınırlarla örtüşme: Opus %79,3 · $14,96 Sonnet %74,0 · $8,30 Haiku %53,8 · $0,87 Luna %47,7 · $0,036 Luna, Opus'tan 418 kat ucuz.
0:12

Opus 5.5, Sonnet 5.5, Haiku 5.5 ve GPT-6 Luna'ya Türkiye haritasını ezberden, kodla çizdirdim. İnternet yok, referans yok, 81 il sınırıyla. Gerçek sınırlarla örtüşme: Opus %79,3 · $14,96 Sonnet %74,0 · $8,30 Haiku %53,8 · $0,87 Luna %47,7 · $0,036 Luna, Opus'tan 418 kat ucuz.

Avenox

21,040 views • 19 days ago

Claude Haiku 4.5, rolling out to Visual Studio Code today Learn more:
0:17

Claude Haiku 4.5, rolling out to Visual Studio Code today Learn more:

Visual Studio Code

64,317 views • 1 year ago

THIS IS PURE F*CKING PLATINUM Anthropic just shared a Claude Code setup that stops you from wasting expensive models on work cheaper ones can handle idea: let Sonnet write the code, Haiku handle the exploration, and Opus review the decisions that actually matter 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 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
0:15

THIS IS PURE F*CKING PLATINUM Anthropic just shared a Claude Code setup that stops you from wasting expensive models on work cheaper ones can handle idea: let Sonnet write the code, Haiku handle the exploration, and Opus review the decisions that actually matter 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 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

Livsun

12,272 views • 15 days ago

You can use Haiku 5.5 for free btw tbh it’s totally over for OpenAI Try it here:
0:19

You can use Haiku 5.5 for free btw tbh it’s totally over for OpenAI Try it here:

Sakata

21,942 views • 19 days ago

I used Opus 5.5 to make a motion design video about Haiku This is 100% motion graphics and code Short story about Opus delegating small tasks to Haiku Prompt in the comments
0:20

I used Opus 5.5 to make a motion design video about Haiku This is 100% motion graphics and code Short story about Opus delegating small tasks to Haiku Prompt in the comments

Baptiste (Kelano)

25,148 views • 19 days ago

Claude Opus 5.5 is FREE 😳 - Claude Opus 5.5 - Claude Fable 5.1 - Kimi K3 - Qwen3.8 Max - GLM-5.3 get access: > 5M free tokens > lots of top models available worth testing 👀
0:15

Claude Opus 5.5 is FREE 😳 - Claude Opus 5.5 - Claude Fable 5.1 - Kimi K3 - Qwen3.8 Max - GLM-5.3 get access: > 5M free tokens > lots of top models available worth testing 👀

K2S

89,426 views • 27 days ago

THIS IS AN ABSOLUTE GOLDMINE The team at Anthropic just revealed one of the most effective techniques for Claude Code The core concept: run Sonnet, Haiku 5.5, and Opus 5.5 simultaneously, letting each model focus strictly on what it does best You get higher quality output while dramatically reducing token consumption, since every specific job gets routed to the optimal model To spin up Claude Code with this setup, simply execute: ⁠claude --model sonnet --advisor opus⁠ Here is how the workload is split: > Sonnet 5.5 handles the primary session, writes code, and applies bug fixes > Haiku 5.5 scans the codebase in parallel: performing searches, running grep queries, exploring docs, and auditing diffs > Opus 5.5 acts as an on-demand advisor for critical decisions and approves final code diffs > You stop burning expensive Opus context on routine tasks that don't require high-level reasoning Opus intervenes exclusively during three specific scenarios: > Right before locking in an execution plan > Whenever the exact same error triggers twice in a row > Prior to marking a task as complete Sonnet builds. Haiku scans and explores. Opus reviews JEV engineering applies the exact same principle one layer deeper: routine execution forks that don't need high-level reasoning (determining which file to inspect, which tool to trigger, or whether to retry or stop) are processed by JEV in sub-milliseconds, leaving big models to handle only complex decision splits The full architectural tree: Sonnet 5.5 manages the primary session and modifies code Search maps out the repository structure via Haiku 5.5 Grep locates call references using Haiku 5.5 Docs fetches API specifications through Haiku 5.5 Opus 5.5 serves as an advisor, reading the complete conversation history whenever consulted JEV routes lightning-fast micro-forks in milliseconds Feed this tree structure alongside the prompt below into Claude Code Reconfigure my Claude Code workspace based on this architecture: 1. Run the primary session utilizing Sonnet 5.5, with Opus 5.5 designated as the advisor 2. Set up three read-only Haiku 5.5 subagents: search (maps out the repo), grep (locates call sites), and docs (retrieves API documentation) 3. Insert a single rule into CLAUDE.md: consult the advisor prior to committing to a plan, after encountering an identical error twice, and before marking a task as done 4. Direct rapid, deterministic decisions (tool selections, file paths, retries) through JEV. Show all modifications as a diff first. Do not execute any edits until I grant permission Bookmark this setup: it will become a daily driver in your workflow
0:19

THIS IS AN ABSOLUTE GOLDMINE The team at Anthropic just revealed one of the most effective techniques for Claude Code The core concept: run Sonnet, Haiku 5.5, and Opus 5.5 simultaneously, letting each model focus strictly on what it does best You get higher quality output while dramatically reducing token consumption, since every specific job gets routed to the optimal model To spin up Claude Code with this setup, simply execute: ⁠claude --model sonnet --advisor opus⁠ Here is how the workload is split: > Sonnet 5.5 handles the primary session, writes code, and applies bug fixes > Haiku 5.5 scans the codebase in parallel: performing searches, running grep queries, exploring docs, and auditing diffs > Opus 5.5 acts as an on-demand advisor for critical decisions and approves final code diffs > You stop burning expensive Opus context on routine tasks that don't require high-level reasoning Opus intervenes exclusively during three specific scenarios: > Right before locking in an execution plan > Whenever the exact same error triggers twice in a row > Prior to marking a task as complete Sonnet builds. Haiku scans and explores. Opus reviews JEV engineering applies the exact same principle one layer deeper: routine execution forks that don't need high-level reasoning (determining which file to inspect, which tool to trigger, or whether to retry or stop) are processed by JEV in sub-milliseconds, leaving big models to handle only complex decision splits The full architectural tree: Sonnet 5.5 manages the primary session and modifies code Search maps out the repository structure via Haiku 5.5 Grep locates call references using Haiku 5.5 Docs fetches API specifications through Haiku 5.5 Opus 5.5 serves as an advisor, reading the complete conversation history whenever consulted JEV routes lightning-fast micro-forks in milliseconds Feed this tree structure alongside the prompt below into Claude Code Reconfigure my Claude Code workspace based on this architecture: 1. Run the primary session utilizing Sonnet 5.5, with Opus 5.5 designated as the advisor 2. Set up three read-only Haiku 5.5 subagents: search (maps out the repo), grep (locates call sites), and docs (retrieves API documentation) 3. Insert a single rule into CLAUDE.md: consult the advisor prior to committing to a plan, after encountering an identical error twice, and before marking a task as done 4. Direct rapid, deterministic decisions (tool selections, file paths, retries) through JEV. Show all modifications as a diff first. Do not execute any edits until I grant permission Bookmark this setup: it will become a daily driver in your workflow

Bober_smart

23,219 views • 1 day ago

check out at: (made with claude opus 5.5)
0:15

check out at: (made with claude opus 5.5)

xevrion

20,718 views • 1 month ago

OPUS 5.5 SHOULDN'T BE DOING THE WORK. It should be writing the PLAN. Claude Code workflows let Opus write a script that runs a whole swarm of agents in the background. Opus plans. Haiku 5.5 scans every file in parallel. Sonnet 5.5 makes the fixes. A verifier checks every finding. Opus only sees what survives. Your expensive model never reads 100 agent transcripts again. Setup prompt below 👇
0:15

OPUS 5.5 SHOULDN'T BE DOING THE WORK. It should be writing the PLAN. Claude Code workflows let Opus write a script that runs a whole swarm of agents in the background. Opus plans. Haiku 5.5 scans every file in parallel. Sonnet 5.5 makes the fixes. A verifier checks every finding. Opus only sees what survives. Your expensive model never reads 100 agent transcripts again. Setup prompt below 👇

CyrilXBT

21,334 views • 9 days ago

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.
0:20

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

29,321,229 views • 1 month ago

Every frame drawn in code by Claude Opus 5.5
0:15

Every frame drawn in code by Claude Opus 5.5

DreW

18,510 views • 1 month ago