The LGTM (Page 39)

The LGTM

Sign in Subscribe

Anthropic’s SDK Update Makes Streaming Thinking Less of a Black Box

Anthropic’s SDK Update Makes Streaming Thinking Less of a Black Box

Anthropic's latest Python and TypeScript SDK releases are easy to file under plumbing. That would be a mistake. The new thinking-token-count beta is not a shiny app feature, but it gives developers a live signal they badly need: how much reasoning work Claude appears to be spending while

Claude Code 2.1.147 Turns Multi-Agent Workflows Into Something You Can Actually Govern

Claude Code 2.1.147 Turns Multi-Agent Workflows Into Something You Can Actually Govern

Claude Code 2.1.147 is the kind of release that tells you where the product is really going. Not toward another magic prompt. Toward a runtime where agents are pinned, orchestrated, policy-bound, inspected, updated, and occasionally told not to escape their sandbox through JavaScript weirdness. Glamorous, no. Necessary, absolutely.

NVIDIA AI-Q Turns Deep Research Into an Agent Skill — Which Is the Right Kind of Laziness

NVIDIA AI-Q Turns Deep Research Into an Agent Skill — Which Is the Right Kind of Laziness

NVIDIA’s AI-Q deep-research skill is easy to undersell if you read it as another “now your coding agent can research things” announcement. That is the boring interpretation, and probably the wrong one. The more interesting move is architectural: NVIDIA is turning deep research into a delegated backend capability. Claude

NVIDIA’s Agent Customization Playbook Is Really a Maturity Model for When Prompts Stop Being Enough

NVIDIA’s Agent Customization Playbook Is Really a Maturity Model for When Prompts Stop Being Enough

NVIDIA’s latest agent-customization post looks, at first pass, like another taxonomy of techniques: prompts, RAG, tools, skills, supervised fine-tuning, LoRA, preference tuning, reinforcement learning, distillation. Fine. Everyone building agents already has that pile of acronyms in a notebook somewhere. The useful part is the sequencing. NVIDIA is effectively saying

LangChain Fireworks 1.4 Moves Off Protobuf Landmines and Makes Provider Integrations More Agent-Ready

LangChain Fireworks 1.4 is a provider-integration release, which is exactly why it matters. The easy take is that LangChain updated its Fireworks wrapper to the rewritten fireworks-ai 1.x SDK, then shipped 1.4.1 to fix retry behavior. The more useful take is that AI frameworks are becoming

Deep Agents 0.6.3 Turns Memory, Search, and Message Identity Bugs Into Agent-Runtime Lessons

Deep Agents 0.6.3 is a patch release with exactly the kind of changelog most teams skim past and later rediscover through a production incident. There is no new model benchmark, no glossy orchestration primitive, no “now with agents” flourish. Instead LangChain fixed four runtime seams: search globs pointed