The LGTM (Page 9)

The LGTM

Sign in Subscribe

Task Guard’s NO_REPLY Bug Shows Why Agent Safety Instructions Need Exit Conditions

Task Guard’s NO_REPLY Bug Shows Why Agent Safety Instructions Need Exit Conditions

The uncomfortable thing about prompt-based safety is that the model keeps reading the prompt after the moment you meant it to apply. OpenClaw issue #95773 is a clean example: Task Guard tells the model that the final reply for the turn “must be and can only be NO_REPLY,” then

OpenClaw’s Model-Call Telemetry PR Makes Prompt Cost Debuggable at the Span Where It Happens

OpenClaw’s Model-Call Telemetry PR Makes Prompt Cost Debuggable at the Span Where It Happens

Every agent cost investigation eventually starts with the same miserable question: which part of the prompt got expensive? The invoice says tokens. The trace says a model call happened. The runtime says the agent was “working.” None of that tells you whether the bill came from duplicated system instructions, a

ACP Background Tasks Need to Wake the Parent Agent, Not Just Announce That They Finished

ACP Background Tasks Need to Wake the Parent Agent, Not Just Announce That They Finished

Background tasks are supposed to buy back attention. If an agent can delegate work to an ACP harness, wait for completion, and then leave the parent conversation sitting there like a CI job with no status check, the platform has not built orchestration. It has built a very expensive notification

Rubin’s 45°C Liquid Loop Is NVIDIA Turning Cooling Into Token Economics

Rubin’s 45°C Liquid Loop Is NVIDIA Turning Cooling Into Token Economics

NVIDIA’s new Rubin cooling story looks, at first glance, like facilities plumbing: warmer coolant, fewer chillers, less water, cleaner racks. That undersells it. The real announcement is that NVIDIA is trying to make the physical data center part of the AI runtime, because at agent scale the cost of

Microsoft’s 2GW Pecos Datacenter Is the AI Capacity Story Builders Cannot Ignore

Microsoft’s 2GW Pecos Datacenter Is the AI Capacity Story Builders Cannot Ignore

Microsoft’s newest Azure AI announcement is not a model, a benchmark, or another Copilot button in a product that already had three. It is a 2-gigawatt datacenter campus in Pecos, Texas — and that makes it one of the more honest AI stories of the month. The AI stack has

Langfuse 3.194.1 Shows the Hidden Cost of Agent Observability

Langfuse 3.194.1 Shows the Hidden Cost of Agent Observability

The most revealing line in Langfuse 3.194.1 is not about a shiny new dashboard. It is about gzip. More specifically, it is about measuring how much active CPU time gzip consumes while exporting observability data. That may sound painfully internal, but it is exactly the kind of internal

Codex Exposes Safety Buffering and Context Compaction as Runtime State

Codex Exposes Safety Buffering and Context Compaction as Runtime State

The most important Codex updates this morning are not new buttons, model names, or demo-friendly tricks. They are the kind of runtime plumbing users only notice when it fails: a safety review state that used to look like a hung agent, and a context-management escape hatch that admits automatic compaction

Grok Build’s Enterprise Docs Say the Quiet Part Out Loud: Coding Agents Are Endpoint Software Now

Grok Build’s refreshed enterprise documentation is not the sort of launch that wins a hype cycle. Good. It is more important than that. The page reads like xAI has accepted the thing every serious engineering org eventually learns about coding agents: once an agent can read a repo, run

xAI’s Deferred Chat Completions Add the Missing Middle Between Wait on the Request and Batch It Overnight

xAI’s Deferred Chat Completions Add the Missing Middle Between Wait on the Request and Batch It Overnight

xAI’s Deferred Chat Completions are the kind of API feature that looks minor until you have to build around the absence of it. Most AI platform diagrams pretend model calls come in two shapes: synchronous requests where the user waits, and batch jobs where nobody cares until tomorrow. Production