PinnedInTowards AIbyallglenn·Apr 11Becoming a top 1% Claude Code user: the complete playbook no one else is sharingMost developers use Claude Code like a fancy autocomplete. The top 1% treat it like a programmable engineering team. This guide shows you…A response icon47A response icon47
InTowards AIbyallglenn·2h agoOpenAI’s Decisions API vs Jev: which one should you use?A documented comparison of images, latency, pricing, data residency, limits, and the small tests that point in different directions.
InTowards AIbyallglenn·3h agoOpenai’s Dots Aren’t Just a Feature Launch. They’re a Lock-in PlayThe more a dot learns about how you work, the less of that you can take with you. Run this exit audit before you teach it anything…
InLevel Up Codingbyallglenn·3d agoThe Four Loops that Keep Coding-Agent Work ReliableBound the task, require a plan, delegate inspectable increments, and approve evidence before merge.A response icon1A response icon1
InTowards AIbyallglenn·6d agoThe memory problem OpenAI’s dots makes impossible to ignoreCompare dots, Muse, Team Bots, and Claude Managed Agents to see where memory lives, who can edit it, and how forgetting works.A response icon2A response icon2
InTowards AIbyallglenn·Sep 30The $200 OpenAI Pro Plan Has a Math ProblemA coding benchmark shows when API spending reaches $200, while the plan’s real usage ceiling remains unpublished.A response icon1A response icon1
InTowards AIbyallglenn·Sep 30Same Price, Different Habits: Sonnet 5.5 vs GPT-6.1 Solsol on a Real RepoAcross 132 graded agent runs on TinyDB, correctness stayed tied while cost, speed, tool use, and code-review tradeoffs split apart.A response icon2A response icon2
InTowards AIbyallglenn·Sep 29OpenAI’s Agent Escaped through DNS. The Kill Switch Failed for 2.5 hours.A practical checklist for blocking hidden egress, detecting boundary violations, and proving an agent run is actually dead.A response icon1A response icon1
InTowards AIbyallglenn·Sep 28What Xiaomi’s 7,780 MiMo Tasks Reveal About Training AgentsA hands-on tour of the code, cyber, knowledge-work, web, and music environments released under Apache 2.0.A response icon1A response icon1
InTowards AIbyallglenn·Sep 27Anthropic Called For pacing. Its Next Flagship Arrived 10 Days LaterA release-history and system-card audit shows what changed in Opus 5.5, what did not, and why Claude builders should care.A response icon1A response icon1
