As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/v/yt-tonbi-s-ai-garage-first-look-at-claude-opus-4-8/

# First Look at Claude Opus 4.8

Tonbi's AI Garage, 1 June 2026, YouTube. 3,286 views as of 8 October 2026.
Kind: Community.
Watch: https://www.youtube.com/watch?v=Sz-nvGuSdp8

## Why it is here

Found 2026-09-29 by YouTube search "introducing claude opus 4.8" (sorted by upload date). Listed as: 3,286 views, length 16:50, published "4mo ago" (so the date above is approximate).

## Description (written by Gemini from the video)

**Summary**  
In this video, creator Tonbi from the YouTube channel *Tonbi's AI Garage* reviews Anthropic's release of Claude Opus 4.8. He breaks down the model's official release slides, system card benchmarks, and new features before testing Opus 4.8 hands-on within the Claude Code terminal interface on frontend web design and technical experiment analysis tasks.

**What is shown**  
* **Release Announcement & System Card Overview [00:00–07:58]:** Presentation slides showing Anthropic's official announcement, benchmark tables, and core improvements: coding reliability, effort controls, pricing changes, dynamic multi-agent workflows, and safety/honesty metrics.
* **Claude Code Setup [07:59–08:18]:** Claude Code CLI (`v2.1.154`) running Claude Opus 4.8 configured with high effort reasoning.
* **Frontend Design Task [08:18–12:56]:** 
  * The presenter prompts Opus 4.8 to build a single HTML file without a build step for a *One Piece* meets *Star Wars* game webpage, featuring a rotating 3D Three.js sphere with a custom GLSL fragment shader (rim lighting), GSAP scroll animations, and staggered entrance headline text [08:18].
  * Displays the rendered browser result ("Void + Pirates") and compares it to Opus 4.7's previous attempt [09:47].
  * When the headline text initially fails to render due to CSS background clipping, the presenter inputs a follow-up prompt, and Opus 4.8 diagnoses and updates the code to display the text "Where Legends Set Sail Beyond the Stars" [11:16–12:22].
* **Research Plan Critique Task [12:57–15:40]:** 
  * Opus 4.8 reads and analyzes a local `plan.md` outlining a machine learning experiment involving LeJEPA representations, 6-DoF camera trajectories, and latent distribution alignment [12:57].
  * Opus 4.8 produces a structured critique classifying potential failures into Tier 1 ("Will halt you or fail a gate"), Tier 2 ("Will silently corrupt results"), and Tier 3 ("Will annoy you / polish"), successfully flagging experimental confounding factors and hardware bottlenecks [14:07–15:33].

**Claims & numbers**  
* **SWE-bench Scores:** The presenter states Opus 4.8 scores 88.6% on SWE-bench Verified (versus 84.3% on Opus 4.7, 78.2% on GPT-5.5, and 70.3% on Gemini 3.1 Pro) and 69.2% on SWE-bench Pro (versus 64.3% on Opus 4.7 and 58.0% on GPT-5.5) [01:34, 02:41, 03:26].
* **Terminal-Bench & OSWorld:** The presenter reports GPT-5.5 leads on Terminal-Bench 2.1 at 78.2% compared to Opus 4.8's 74.6%, while Opus 4.8 leads OSWorld-Verified (computer use) at 83.4% (ahead of GPT-5.5's 78.7% and Gemini 3.1 Pro's 71.8%) [01:40, 02:03].
* **Math Benchmark:** The presenter claims Opus 4.8 achieved 96.7% on USAMO 2026 math, up from 69.3% on Opus 4.7 [02:22].
* **Code Reliability:** The presenter notes Anthropic claims Opus 4.8 is ~4x less likely than Opus 4.7 to let a code flaw slip past unmarked [02:59].
* **ProgramBench:** The presenter cites scores jumping from 71–84% on Opus 4.7 to 79–88% on Opus 4.8 [03:57].
* **Effort Control & Efficiency:** The presenter explains Opus 4.8 at minimum effort matches Opus 4.7 at maximum effort on SWE-bench Pro [04:27].
* **Pricing:** Standard tier pricing remains unchanged at $15 input / $75 output per million tokens, while "Fast mode" low-latency pricing runs at $10 input / $50 output per million tokens (three times cheaper than previous fast mode) [04:47].
* **Multi-Agent Workflows:** The presenter notes BrowseComp multi-agent score reached 88.5% (versus 84.3% single agent), and a 5-agent team completes hard tasks >3x faster at ~20% latency [05:43].
* **Other Benchmarks:** Harvey AI strict Legal Agent Benchmark reached 86.82% pass rate; GraphWalks BFS at 1M tokens scored 68.1% (compared to 40.3% on Opus 4.7 and 45.4% on GPT-5.5) [06:37].
* **Security Caveat:** The presenter highlights system card findings that Opus 4.8 is slightly less robust than Opus 4.7 on some agentic prompt-injection tests [06:58].

**Notable quotes**  
* "The honest headline is that it's a real step up, but not a clean sweep." [01:27]
* "It catches its own bad code more often, which if you used Opus 4.7 a lot, like I did, you'll notice that there was a lot of bad code that slipped through." [03:10]
* "On SWE-bench Pro, Opus 4.8 at minimum effort matched Opus 4.7 at maximum effort." [04:26]

**Assessment**  
This is an independent user review and hands-on demonstration from an AI creator, combining a walkthrough of Anthropic's official release deck with unedited, real-time testing in Claude Code. The creator transparently displays flaws during testing—such as a CSS background clipping bug requiring a follow-up prompt—rather than cherry-picking a flawless output.

_Described by gemini-3.8-flash on 2026-09-29 from the video's audio and frames._

## How AI was used to make it

AI made a substantial part of this video (Subject built by AI).
- Claude Opus 4.8 generated a single-file HTML webpage featuring a rotating 3D Three.js sphere with a custom GLSL fragment shader and GSAP animations
- Claude Opus 4.8 generated a structured critique analyzing failure tiers for a machine learning experiment plan
Tools: Claude Opus 4.8, Claude Code
(Classified by gemini-3.8-flash from our description; high confidence. Overview: https://postcutoff.com/ai-video/)

## Related

- 2026-05-28: [Anthropic releases Claude Opus 4.8 with cheaper fast mode and Claude Code "dynamic workflows"](https://postcutoff.com/e/2026-05-28-claude-opus-4-8/)

## More videos on this

- 2026-05-28: [Embrace long-running tasks with Opus 4.8 and Claude Code](https://postcutoff.com/v/claude-opus-4-8-long-running-tasks/), Claude, YouTube, official, 136,862 views as of 9 October 2026.
- 2026-06-01: [Claude Opus 4.8 actually blew my mind...](https://postcutoff.com/v/yt-alex-finn-claude-opus-4-8-actually-blew-my-mind/), Alex Finn, YouTube, community, 86,747 views as of 9 October 2026.
- 2026-06-01: [Anthropic Just Dropped Claude Opus 4.8 (Full Breakdown)](https://postcutoff.com/v/yt-brock-mesarich-ai-fo-anthropic-just-dropped-claude-opus-4-8-f/), Brock Mesarich | AI for Non Techies, YouTube, review, 66,277 views as of 8 October 2026.
- 2026-07-31: [NEW Claude Sonnet 5 vs Opus 4.8! (Full Review)](https://postcutoff.com/v/yt-ai-foundations-new-claude-sonnet-5-vs-opus-4-8-full-rev/), AI Foundations, YouTube, review, 48,839 views as of 8 October 2026.

What else happened that month, day by day: https://postcutoff.com/timeline/2026/05/