I shut my openclaw down this week. It was a fun run but too brittle. Cursor automations covered most of my openclaw use cases.
@randal_olson
-
Fake TechCrunch Imposters Using Calendly for Social Engineering
By
–
Sounds similar to the fake TechCrunch people trying to schedule calendly meetings to discuss writing an article too.
-
AI Agents: Need for External Verifier to Assess Work
By
–
Anthropic and OpenAI both published posts on agent harness design last month and arrived at the same conclusion. Agents need an external checker that gives concrete feedback. Without it, the agent praises its own mediocre work and moves on. https://goodeyelabs.com/insights/evaluation-is-the-load-bearing-part [Translated from EN to English]
→ View original post on X — @randal_olson, 2026-04-02 13:00 UTC
-
Claude Code Leak Reveals Unexpected Gacha Game Mechanics and Species System
By
–
You expect JWT bridges & task orchestration in a leaked agent CLI. You don’t expect 18 species, 5 rarity tiers, and odds that read like a gacha spec sitting under compile-time flags. That is what fell out of a community mirror of the Claude Code leak. randalolson.com/2026/04/02/c…
→ View original post on X — @randal_olson, 2026-04-01 20:02 UTC
-
Analysis of Claude Code Agent Tools Revealed in Leak
By
–
A breakdown of the Claude Code agent tools from yesterday's leak. Source: randalolson.com/2026/04/02/c… [Translated from EN to English]
→ View original post on X — @randal_olson, 2026-04-01 19:24 UTC
-
npm Error Exposes Anthropic’s Complete Claude Code Architecture
By
–
One npm packaging mistake exposed @AnthropicAI's entire Claude Code tree. The treemap is worth staring at. You can see the silhouette of a real desktop agent, not a thin chat wrapper: terminal UI, session hooks, IDE bridge glue, CLI wiring, etc. Source: randalolson.com/2026/04/02/c… [Translated from EN to English]
→ View original post on X — @randal_olson, 2026-04-01 19:09 UTC
-
Claude Code Leak: Source Code Rewritten in Rust to Evade Takedown
By
–
If you, like me, just woke up, let me catch you up on the Claude Code Leak (I know nothing, all conjecture): > Someone inside Anthropic, got switched to Adaptive reasoning mode > Their Claude Code switched to Sonnet > Committed the .map file of Claude Code > Effectively leaking the ENTIRE CC Source Code > @realsigridjin was tired after running 2 south korean hackathons in SF, saw the leak > Rules in Korea are different, he cloned the repo, went to sleep > Wakes up to 25K stars, and his GF begging him to take it down (she's a copyright lawyer) > Their team decided – how about we have agents rewrite this in Python!? Surely… this is more legal > Rewrite in Py > Board a plane to SK🇰🇷 > One of the guys decides python is slow, is now rewriting ALL OF CLAUDE CODE into Rust. > Anthropic cannot take down, cannot sue > Is this "fair use?" > TL;DR – we're about to have open source Claude Code in Rust
→ View original post on X — @randal_olson, 2026-03-31 15:44 UTC
-
AI Agents Creating Publication-Ready Charts Using Tufte Principles
By
–
AI agents make charts fast. The output is almost always fine. Correct data, readable axes, nothing you'd actually want to publish. We encoded Tufte's principles as an AI quality bar in Truesight and told an agent to keep revising until it passed. goodeyelabs.com/insights/the…
→ View original post on X — @randal_olson, 2026-03-31 13:00 UTC
-
Claude Close But With Locking and Reliability Issues
By
–
Claude is very close on this one, but they have model lock-in and massive reliability issues. Codex is still playing catch-up, but it's just a matter of time. [Translated from EN to English]
→ View original post on X — @randal_olson, 2026-03-29 16:53 UTC
-
Cursor Cloud Agents Replaces OpenClaw with Better Features
By
–
.@cursor_ai has gone in the exact direction I hoped they would with their Cloud Agents. Automations + reliable cloud environments + wide and permissive connectors (MCP) + broad model selection (no lock-in) = OpenClaw killer. Finally able to replace my high maintenance OpenClaw.
→ View original post on X — @randal_olson, 2026-03-29 16:51 UTC