cd /news/ai-agents/opus-4-8 · home topics ai-agents article
[ARTICLE · art-45131] src=ampcode.com ↗ pub= topic=ai-agents verified=true sentiment=↑ positive

Opus 4.8

Amp released Opus 4.8, a new AI coding agent that powers its 'smart' mode, replacing Opus 4.7. The model solves 62% of tasks in internal evaluations, up from 52% for its predecessor, by making more focused changes and verifying its own work more thoroughly. Opus 4.8 also offers a faster mode at 2.5× speed and 3× cheaper token costs.

read2 min views11 publishedJun 4, 2026

Opus 4.8 now powers Amp's smart

mode, replacing Opus 4.7.

It is a better coding agent than Opus 4.7: more faithful to the prompt, tighter in the changes it makes, and better at checking its own work. In our internal evals it solved 62% of tasks, up from 4.7's 52%.

Opus 4.7 was already strong on hard, multi-file work, and Opus 4.8 keeps that. What changes is how it gets there: with fewer wasted steps and more self-checking.

The clearest difference is restraint and verification.

Opus 4.7 can sometimes over-engineer, reaching for a more elaborate solution than the task needs. It also verifies its own work less, occasionally moving on even when a command's output is already warning that something is off.

Opus 4.8 makes a more focused change that solves the specific intended task, then checks itself. It leans on a tighter write→test loop, often spinning up a quick script, test, or skill to confirm the change works before proceeding. In our evals it ran tests and code 15% more per task than 4.7.

That restraint is easiest to see on hard tasks. On everyday work the two make a similar number of tool calls. The harder a task gets, the tighter 4.8 stays, just where 4.7 tends to run long and fail more often.

Opus 4.8 is noticeably better at using its tools and sub-agents without being told to.

When a task needs outside context, it actually calls librarian

instead of inferring a library's behavior from the local code. Across our eval it reached for it 14 times, versus once for Opus 4.7. It also reaches for a repo's skills more often to verify its work, for example by driving the browser or the CLI, rather than just assuming the change worked.

When it edits, it leans on edit_file

for surgical, in-place changes rather than rewriting whole files with create_file . In our evals 79% of its file edits go through edit_file

, up from 63% on Opus 4.7.

We dropped the Read

tool from smart

.

Opus 4.8 is good enough at reading files straight from the shell with cat

, rg

, sed

, and nl

. It parallelizes those reads when it needs several files at once.

Opus 4.8 has a fast mode at roughly 2.5× the speed. It now costs 2× base tokens, down from 6× on 4.7—3× cheaper.

Toggle fast mode for a thread from the CLI command palette (Ctrl+O) → speed: use fast

.

Opus 4.8 stays close to what you ask, changes less to get there, and checks its own work. A few habits make it shine:

── more in #ai-agents 4 stories · sorted by recency
── more on @amp 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/opus-4-8] indexed:0 read:2min 2026-06-04 ·