PulseAugur
EN
LIVE 23:37:10

DeepSeek V4 struggles with tool calls in early tests

DeepSeek V4, a new iteration of the DeepSeek language model, has been released. Early testing indicates that the model struggles with generating proper tool calls, often taking a significant amount of time to process before failing. AI

IMPACT Early performance issues with tool calls may indicate areas for improvement in future iterations of DeepSeek models.

RANK_REASON New model release from a frontier lab. [lever_c_demoted from frontier_release: ic=1 ai=1.0]

Read on Mastodon — mastodon.social →

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

DeepSeek V4 struggles with tool calls in early tests

How we ranked this

Signal score
12 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
New model release from a frontier lab. [lever_c_demoted from frontier_release: ic=1 ai=1.0]
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, product
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] ·

    First prompt for Deepseek v4 flash and after a long time of "thinking" it fails to generate proper tool calls :/ # LLM # Deepseek # Deepseek4 # AI

    First prompt for Deepseek v4 flash and after a long time of "thinking" it fails to generate proper tool calls :/ # LLM # Deepseek # Deepseek4 # AI