LLM Digest
Subscribe

AI Storyline

3 items · 3 sources · 3 days

View as JSON

Operational story trace

Web Search

Current stateDevelopingstatus changed Oct 27

Latest change

A GitHub benchmark compares 4 web search APIs for AI agents on 30 live queries, the first head-to-head comparison in this thread.

Earlier contextThe story so far

DeepSeek priced web search for agents at /bin/bash.75 per 1,000 calls on Oct 17, making search a metered line item. A long-horizon eval paper followed on Oct 26.

editor-curated · source-linked

Arc

Oct 17Oct 27 · now
PRICING · Oct 17
DeepSeek prices agent web search at $0.75 per 1,000 calls
1 source · show source ▾
EVALUATION · Oct 26
LongSearchEval targets long-horizon search failures
1 source · show source ▾
NOW · Oct 27
Community benchmark pits 4 search APIs against 30 live queries
1 source · show source ▾

What to watch — open questions

  • Do the benchmark's API rankings hold on a larger or different query set?
  • Do other search API vendors respond to DeepSeek's per-call price?
  • Is LongSearchEval adopted to compare search-agent systems?
How this thread was built
editor wrote the arc · 3 beatswatcher 1 status change

Storylines are threaded mechanically from the feed: stories that share a distinctive anchor across multiple days and sources. Each item links to its original source. The evidence trace, current state, and open questions are written by the editor routine and refreshed whenever a new beat lands.