PulseAugur
EN
LIVE 18:06:58

Anthropic's Opus 5 criticized for poor instruction following

By PulseAugur Editorial · [1 sources] ·

A user on Mastodon expressed significant concern regarding the instruction-following capabilities of Anthropic's Opus 5 model. The user reported that the model repeatedly ignored explicit instructions, such as being told not to perform a certain action, which they found to be a critical failure in its performance. AI

IMPACT Highlights potential limitations in current large language model instruction adherence, impacting user trust and practical application.

RANK_REASON User commentary on a specific model's performance, not a primary release or research finding.

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Anthropic's Opus 5 criticized for poor instruction following

How we ranked this

Signal score
4 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Commentary
User commentary on a specific model's performance, not a primary release or research finding.
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    🤖 Opus 5 Instruction Following is Genuinely Concerning I think that Anthropic has dropped the ball, instruction following is actually non-existent. You tell it

    🤖 Opus 5 Instruction Following is Genuinely Concerning I think that Anthropic has dropped the ball, instruction following is actually non-existent. You tell it to not do something, ignores you and does it anyway. I’ve said at least ten times to no open... 📰 Source: Artificial Int…

RELATED ENTITIES

RELATED TOPICS