08:25 CETWednesday · May 13, 2026

shipfeed

⌘K SEARCHJK NAVO OPEN
on the wire
arXiv — cs.AIMedHopQA benchmark tests LLM reasoning in biomedical Q&A◆arXiv — cs.CLRouters learn geometry of sparse mixture-of-experts◆arXiv — cs.AIStudy audits how LLMs generate political discourse during crises◆arXiv — cs.AIClassifier Context Rot: Monitor Performance Degrades with Context◆arXiv — cs.AIExecutable Agentic Memory for GUI Agent◆arXiv — cs.CLLongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced◆arXiv — cs.AISparse-to-dense rewards improve language model post-training◆arXiv — cs.AIAI-native mobility dataset advances 6G handover and beam management◆arXiv — cs.AIMedHopQA benchmark tests LLM reasoning in biomedical Q&A◆arXiv — cs.CLRouters learn geometry of sparse mixture-of-experts◆arXiv — cs.AIStudy audits how LLMs generate political discourse during crises◆arXiv — cs.AIClassifier Context Rot: Monitor Performance Degrades with Context◆arXiv — cs.AIExecutable Agentic Memory for GUI Agent◆arXiv — cs.CLLongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced◆arXiv — cs.AISparse-to-dense rewards improve language model post-training◆arXiv — cs.AIAI-native mobility dataset advances 6G handover and beam management◆
home/§ tools/cluster
ad slot opena single understated line lives here — sponsor wordmark + a short line.advertise on shipfeed →
§ tools · cluster

Vercel AI SDK — deepseek v2.0.35

today · · primary fetch1 sourcecluster 6873be00updated today ·

Patch Changes c70e921: Accept `thinking.type: 'adaptive'` and the full `reasoningEffort` enum (`low`, `medium`, `high`, `xhigh`, `max`) for the DeepSeek provider.

read full article on github.com ↗
§ sources2 publications · timeline below
  1. github.comVercel AI SDK — deepseek v2.0.35primary
  2. github.comVercel AI SDK — deepseek v3.0.0-canary.43

§ how this story moved

  1. primary — Vercel AI SDK — Releases publishes the launch post.
  2. Vercel AI SDK — Releases picks up coverage.