AI Wiki — Knowledge Base

New release of LLM adds support for reasoning traces, OpenAI Responses, server-side tools, and smarter logging

I released LLM 0.32 this morning, the most significant new version of LLM since the initial launch of the project. The new version includes support for visible reasoning traces, server-side provider t

model-releasessimon-willison

4 Aug 2026

Search: “llm”

New release of LLM adds support for reasoning traces, OpenAI Responses, server-side tools, and smarter logging

LLM 0.32a0 is a major backwards-compatible refactor

llm-typesafe 0.1a0

llm-chat-completions-server 0.1a0

llm-openai-decisions 0.1a0

llm 0.33

llm 0.32rc2

Ray Data LLM enables 2x throughput over vLLM’s synchronous LLM engine at production-scale

llm 0.36

llm 0.32.1

llm-gemini 0.33

llm 0.32rc1

llm-echo 0.5a0

llm-coding-agent 0.1a0

llm-anthropic 0.26

datasette-llm-accountant 0.1a4

datasette-llm-limits 0.1a0

llm-anthropic 0.27

llm-gemini 0.34

Minimize idle accelerators: Native RL job interleaving with co-operative time-slicing in llm-d

Using LLM in the shebang line of a script

llm-keys-ui 0.1

llm 0.35

Comprehensive observability for Amazon SageMaker AI LLM inference: From GPU utilization to LLM quality

llm-gemini 0.35

llm-anthropic 0.29

How To Write With An LLM

llm-gemini 0.32

llm-openrouter 0.6

Stealing Reasoning Traces from Proprietary LLM APIs

How to measure human-LLM judge alignment

datasette-llm 0.1a8

llm 0.32a2

llm 0.31

My Workflow for Understanding LLM Architectures

What agent traces can tell you without an LLM judge

What Jev’s probabilities reveal that repeated LLM judgments miss

Real-time LLM guardrails with Jev: comparing latency and cost

Reduce LLM latency with prefix-aware routing on Amazon SageMaker Inference

How to build LLM-as-a-Judge evaluators that hold up in production

llm 0.32a0

llm-meta-ai 0.2

Cost Agent: find where your LLM and agent spend goes with your traces

NarrateAI: production-ready LLM quality assurance on Amazon Bedrock

Benchmarking LLM Inference at Scale with AIPerf

How to reduce LLM costs without sacrificing quality

llm 0.31.1

llm-gemini 0.32a0