The LGTM (Page 32)

The LGTM

Sign in Subscribe

Qwen Code’s Latest Runtime Fixes Are About Making Agents Fail Less Stupidly

Qwen Code’s Latest Runtime Fixes Are About Making Agents Fail Less Stupidly

Qwen Code’s most useful work this week is not a model launch. It is plumbing. That sounds like faint praise until you remember that coding agents do not fail in production because the demo prompt was insufficiently cinematic; they fail because a pipe blocks, a context estimate lies, a

OpenAI's GPT-5.5 Rate Card Makes the New Model Hierarchy Obvious: Frontier for Hard Work, Mini for Subagents

OpenAI's GPT-5.5 Rate Card Makes the New Model Hierarchy Obvious: Frontier for Hard Work, Mini for Subagents

OpenAI’s pricing page is doing more product strategy than most launch posts. The current GPT-5-era API lineup makes the hierarchy hard to miss: GPT-5.5 for complex reasoning and professional coding work, GPT-5.4 for a cheaper middle tier, and GPT-5.4 mini for lower-latency coding, computer-use, and subagent

Agent Benchmarks Just Stopped Measuring Models and Started Measuring the Data Center

Agent Benchmarks Just Stopped Measuring Models and Started Measuring the Data Center

Agent benchmarks are growing up, which means they are getting less flattering and more useful. NVIDIA’s latest post around Artificial Analysis’ new AA-AgentPerf benchmark looks, at first glance, like the usual hardware victory lap: Blackwell GB300 NVL72 beats older systems by a lot, the chart goes up and to

Qwen Code’s Newest Main-Branch Work Is About Surviving Real Agent Operations

Qwen Code’s Newest Main-Branch Work Is About Surviving Real Agent Operations

Qwen Code’s most interesting work today is not a benchmark, a model card, or another “look, it can edit files” demo. It is a cluster of main-branch patches about how an agent behaves when the world gets annoying: rate limits, dropped streams, browser refreshes, memory pressure, native computer-use drivers,

MiniMax M3 on NVIDIA Is a Long-Context Infrastructure Test, Not a Prompt-Box Flex

MiniMax M3 on NVIDIA Is a Long-Context Infrastructure Test, Not a Prompt-Box Flex

The least interesting thing about MiniMax M3 is that it has a 1M-token context window. Giant context windows are now the AI industry’s favorite spec-sheet flex: impressive, expensive, and frequently misused. The more interesting story is that NVIDIA is treating MiniMax M3 as an infrastructure problem instead of a

Qwen Code 0.18 Turns the CLI Into an Agent Runtime With Desktop, Daemon, Teams, Workflows, and Cron

Qwen Code 0.18 Turns the CLI Into an Agent Runtime With Desktop, Daemon, Teams, Workflows, and Cron

Qwen Code 0.18 is what happens when a terminal coding assistant starts admitting it wants to be an agent runtime. The release is too large to read as a normal changelog. Desktop app, daemon mode, ACP bridge, Agent Team, workflow scripts, cron loops, tool-output truncation, telemetry, cross-session rewind, plan-mode