The LGTM (Page 4)

The LGTM

Home
Agentic Coding
Claude Code
Codex

Sign in Subscribe

OpenAI’s Cyber-Safety Update Confirms Coding Agents Have Crossed Into a Different Risk Class

OpenAI’s Cyber-Safety Update Confirms Coding Agents Have Crossed Into a Different Risk Class

The coding-agent market has spent a year talking as if safety were a downstream issue. Ship faster, wire in review later, add a scanner if compliance starts sending tense emails. OpenAI’s new cyber-safety documentation for Codex is a useful correction because it admits the problem now starts earlier than

16 Apr 2026 4 min read

OpenAI Wants Codex Security to Be More Than a Scanner, and That’s the Interesting Part

OpenAI Wants Codex Security to Be More Than a Scanner, and That’s the Interesting Part

Every AI coding vendor eventually runs into the same business reality: if you help teams write more code, you also create a larger market for helping them distrust that code more efficiently. OpenAI’s new Codex Security product page is interesting because it makes that move explicit. This is not

16 Apr 2026 4 min read

GitHub Just Gave Copilot Cloud Agent a Rollout Lever Enterprises Actually Needed

GitHub Just Gave Copilot Cloud Agent a Rollout Lever Enterprises Actually Needed

Enterprise software adoption usually dies in one of two places: procurement or policy. The model can be great, the demo can be slick, the benchmark chart can glow in neon, and none of it matters if the platform team cannot roll the thing out without flipping a giant switch for

16 Apr 2026 4 min read

Muse Spark Cracks Arena Top 3 in One Week — and Llama 4 Is Already Gone

One week ago, Meta launched Muse Spark — the first model from its Superintelligence Labs division. Today it sits at #3 on the Arena AI text leaderboard with 1495 Elo, displacing Llama 4, which was Meta's own previous flagship. The Llama brand didn't lose to a competitor.

16 Apr 2026 5 min read

GitHub Copilot CLI’s April 16 Release Shows the Agent War Is Now About Control Surfaces

GitHub Copilot CLI’s April 16 Release Shows the Agent War Is Now About Control Surfaces

AI coding tools spent the last year competing on the fun part: benchmark screenshots, model names, and demos where an agent heroically writes a feature from scratch. The real market is now being decided by much duller questions. Can you resume a session without spelunking for a UUID? Can you

16 Apr 2026 5 min read

OpenClaw’s Cron Layer Is Learning the Hard Way That "Delivered" and "Healthy" Are Not the Same Signal

OpenClaw’s Cron Layer Is Learning the Hard Way That "Delivered" and "Healthy" Are Not the Same Signal

OpenClaw's cron bugs are getting more interesting, which is another way of saying the product is becoming a real operations surface. Issue #67441 reports a particularly ugly observability failure: a cron-triggered agent can successfully deliver a message to Discord and still have the run recorded as an error.

15 Apr 2026 4 min read

OpenClaw Just Fixed a Hidden Token Tax on Every Multi-Turn Session

Some of the most important OpenClaw fixes are the ones that barely look like product news. PR #67447, merged early on April 16, changes the platform's default context-injection mode from always to continuation-skip. In plain English, follow-up turns stop re-injecting the same bootstrap files into every turn by

15 Apr 2026 4 min read

OpenClaw’s Exec Approvals Are Starting to Look Too Trusting for the Kind of Software It Has Become

OpenClaw’s Exec Approvals Are Starting to Look Too Trusting for the Kind of Software It Has Become

The most revealing OpenClaw security story this week is not a CVE. It is a feature request. Issue #67440 asks for optional TOTP-backed exec approvals, and the reason it lands so hard is simple: it forces everyone to say out loud what kind of software OpenClaw has become. This is

15 Apr 2026 4 min read

OpenClaw’s Dreaming Pipeline Has a Memory Poisoning Problem, Not Just a Cleanup Problem

OpenClaw’s Dreaming Pipeline Has a Memory Poisoning Problem, Not Just a Cleanup Problem

OpenClaw's memory stack has crossed the line where “quality bug” is no longer an adequate label. If issue #67442 holds up, the problem is not that Dreaming occasionally writes goofy summaries. The problem is that the system can take transport noise, promote it through multiple memory stages, and

15 Apr 2026 4 min read

Gemini’s Mac App Arrives Late, but It Finally Makes Google Serious on the Desktop

Gemini’s Mac App Arrives Late, but It Finally Makes Google Serious on the Desktop

Google finally shipped a native Gemini app for macOS, and the timing tells you almost as much as the feature list. For the last year, Google has had solid AI models, a growing app ecosystem, and a chronic packaging problem. Too often the experience felt like a collection of capabilities

15 Apr 2026 4 min read

Prepaid Gemini API Credits Fix a Very Real Developer Pain: Billing Anxiety

Prepaid Gemini API Credits Fix a Very Real Developer Pain: Billing Anxiety

The most revealing Google AI announcement of the day might be the least glamorous one. Not a frontier benchmark, not a new agent demo, not another lifestyle video about how AI will transform everything. Just billing. Specifically, prepaid Gemini API credits in Google AI Studio. That sounds like bookkeeping. It

15 Apr 2026 4 min read

Google’s New TTS Model Is Really a Promptable Voice Engine, Not Just Another Speech API

Google’s New TTS Model Is Really a Promptable Voice Engine, Not Just Another Speech API

Text-to-speech has spent the last few years stuck in an awkward middle state. The demos kept getting smoother, the voices kept getting less robotic, and the APIs kept pretending that the remaining problem was mostly cosmetic. Pick a voice, maybe tweak the speed slider, ship a narrator, call it innovation.

15 Apr 2026 5 min read

← Newer Posts Page 4 of 13 Older Posts →

The LGTM © 2026

Sign up

Powered by Ghost