The  LGTM
  • Home
  • Agentic Coding
  • Claude Code
  • Codex
Sign in Subscribe
Gemini’s New Photo-Aware Image Generation Turns Google Photos Into a Context Moat
google-ai

Gemini’s New Photo-Aware Image Generation Turns Google Photos Into a Context Moat

Google’s latest Gemini image feature is being pitched as a friendlier way to make personalized pictures. That description is technically true and strategically incomplete. The bigger story is that Google is trying to turn one of the most annoying parts of generative AI, namely explaining yourself to a machine
16 Apr 2026 4 min read
Google’s Ads Safety Report Shows Where Gemini Is Actually Paying Off
google-ai

Google’s Ads Safety Report Shows Where Gemini Is Actually Paying Off

The most important Gemini story from Google this week is not a new assistant trick, not a shiny consumer demo, and not another benchmark designed to make investors feel warm. It is ad moderation. Specifically, it is Google saying Gemini-powered systems helped catch more than 99% of policy-violating ads before
16 Apr 2026 5 min read
Claude Opus 4.7 Looks Less Like a Model Refresh and More Like Anthropic Fixing Agent Reliability
ai-models

Claude Opus 4.7 Looks Less Like a Model Refresh and More Like Anthropic Fixing Agent Reliability

Anthropic did not price Claude Opus 4.7 like a moonshot. That is the point. The company shipped its new flagship generally available model at the same $5 per million input tokens and $25 per million output tokens as Opus 4.6, then spent most of the launch arguing not
16 Apr 2026 5 min read
Qwen Opens a Smaller 3.6 Model, and the Real Story Is Distribution
qwen

Qwen Opens a Smaller 3.6 Model, and the Real Story Is Distribution

Open models do not win because somebody posts a benchmark chart with a lot of green cells. They win when developers can actually deploy them without turning inference into a side quest. That is why Qwen’s latest release matters. Alibaba did not just announce another model with a slightly
16 Apr 2026 5 min read
OpenClaw Just Closed a Nasty Codex Resume Escape Hatch
openclaw

OpenClaw Just Closed a Nasty Codex Resume Escape Hatch

Security bugs in agent platforms rarely announce themselves with a dramatic exploit chain. More often they show up as one ugly flag in one quiet code path that nobody thought to treat as part of the trust model. OpenClaw’s Codex resume fix is that kind of bug. The patch
16 Apr 2026 4 min read
OpenClaw’s Config API Still Has a Secret-Leak Problem, Just in a New Place
openclaw

OpenClaw’s Config API Still Has a Secret-Leak Problem, Just in a New Place

Secret leaks in agent platforms rarely happen because nobody thought secrets mattered. They happen because one more subsystem got bolted on, one more config shape looked harmless, and one more redaction rule turned out to be a naming convention in a trench coat. OpenClaw’s newly filed browser.cdpUrl issue
16 Apr 2026 4 min read
OpenClaw Wants OpenRouter to Be More Than a Text Gateway
openclaw

OpenClaw Wants OpenRouter to Be More Than a Text Gateway

Most people still talk about OpenRouter as if it were a convenience layer for text completions. Pick a model, swap a provider, avoid rewriting the app. Fine. Useful, even. But OpenClaw’s new OpenRouter image-generation work suggests something more ambitious: model routing is turning into a full multimodal control plane,
16 Apr 2026 4 min read
Agent Status Pages Are Useless If They Lie About Context Pressure
openclaw

Agent Status Pages Are Useless If They Lie About Context Pressure

Every agent platform eventually learns the same unglamorous lesson: dashboards are part of the product. Not because they look nice, but because operators make real decisions off them. They decide whether a session is healthy, whether compaction worked, whether they can keep going on the current model, whether memory is
16 Apr 2026 4 min read
Microsoft Wants Azure Agent Hosting to Stop Looking Like Kubernetes with Extra AI Branding
azure-ai

Microsoft Wants Azure Agent Hosting to Stop Looking Like Kubernetes with Extra AI Branding

Microsoft keeps making the same argument about enterprise AI from three different angles, which is usually how you can tell the company actually means it. First it pushed Foundry as the control plane. Then it pushed MCP as the tool boundary. Now it is pushing Hosted Agents as the answer
16 Apr 2026 4 min read
Azure MCP in Visual Studio Is Microsoft Turning Agent Tooling into a Checkbox, Which Is Exactly the Point
azure-ai

Azure MCP in Visual Studio Is Microsoft Turning Agent Tooling into a Checkbox, Which Is Exactly the Point

Standards do not win when everyone agrees they are elegant. They win when they become annoying to avoid. That is why Microsoft’s newest Azure MCP move matters more than it first appears. The company has now baked Azure MCP tools directly into the Azure development workload for Visual Studio
16 Apr 2026 4 min read
LangChain Core 1.3.0a2 Fixes the Kind of Memory Leak That Quietly Breaks Real Agent Systems
ai-frameworks

LangChain Core 1.3.0a2 Fixes the Kind of Memory Leak That Quietly Breaks Real Agent Systems

Agent framework competition in 2026 is increasingly being decided by bugs nobody puts on a conference slide. Not “look, five agents talking to each other.” Not another benchmark with suspiciously convenient prompts. The real separator is whether the runtime behaves like production software when traces get nested, state piles up,
16 Apr 2026 4 min read
Anthropic’s Latest Claude Code Positioning Is Barely About Developers Anymore
agentic-coding

Anthropic’s Latest Claude Code Positioning Is Barely About Developers Anymore

Anthropic’s latest Claude Code product positioning is interesting not because it says coding agents are useful. Everyone in this market says that now. It is interesting because Anthropic is barely selling Claude Code as a developer tool anymore. The product page frames it as an agentic system that can
16 Apr 2026 4 min read
← Newer Posts Page 110 of 120 Older Posts →
The LGTM © 2026
  • Sign up
Powered by Ghost