Skip to main content
Search

Together

2 related articles

Subscribe to updates
  1. Ollama

    Long-running agents stop rereading the whole transcript: Ollama and Together AI split prefix-cache upkeep across harness and engine

    Coding agents resend the entire session on every step, so long inputs and short outputs make prefix caching decide whether long sessions slow down. Ollama and Together AI describe the problem from the request-construction and inference-engine sides: a cache matches only up to the first differing token, so one per-turn field in the system prompt forces the whole session to be reprocessed. In an idealized estimate where each turn adds the same amount, ten turns cost 55 prompt units uncached versus 10 cached; a hit also depends on routing the request back to the node holding that cache.

  2. arXiv

    Can agents build agents? On Singularity-Bench's six end-to-end tasks, Opus 5.5 with Claude Code matches or beats the human baseline on all six

    Singularity-Bench splits AI development into six end-to-end tasks: pre-training, mid-training, post-training, inference, the agent harness and cluster orchestration, each starting from a minimal codebase with a fixed time budget and compared against a human-engineered baseline on identical hardware. Across 11 agents built from 7 frontier models and 2 harnesses, Opus 5.5 with Claude Code matches or outperforms the baseline on all six for a Singularity-Index of 1.25, while the other 10 average 0.58. The index averages each agent's ratio to the human baselines across the six tasks, scoring failed tasks as zero, so it measures consistency across the stack rather than a single best result.

You’re all caught up