Comments URL: https://news.ycombinator.com/item?id=47542112

Points: 3

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=46993637

Points: 2

# Comments: 1

https://anupamchugh.github.io/placematch/

Comments URL: https://news.ycombinator.com/item?id=46980668

Points: 1

# Comments: 0

  10 MCP servers as device drivers (exchange APIs, browser automation, Apple docs, issue tracking).
  200+ skills as prose runbooks that compose system calls. Agent-mail for IPC between parallel
  agents. A drift detector called "wobble" that scores skill stability using bias/variance analysis.

Good code isn't dying. The cost of bad code just went up.

Waymo's fleet is ~700 cars. The internet has millions of hours of driving footage. This technique turns the entire internet into a sensor suite. That's a bigger deal than the simulation itself.

One session's scaffold assumes one pattern. Second session scaffold contradicts it. You reviewed both in isolation. Both looked fine. Neither knows about the other.

Reviewing AI code per-session is like proofreading individual chapters of a novel nobody's reading front to back. Each chapter is fine. The plot makes no sense.

The lock file approach (current_tasks/parse_if_statement.txt) prevents two agents from claiming the same task, but it can't prevent convergent wasted work. When all 16 agents hit the same Linux kernel bug, the lock files didn't help — the problem wasn't task collision, it was that the agents couldn't see they were all solving the same downstream failure. The GCC oracle workaround was clever, but it was a human inventing a new harness mid-flight because the coordination primitive wasn't enough.

Similarly, "Claude frequently broke existing functionality implementing new features" isn't a model capability problem — it's an input stability problem. Agent N builds against an interface that agent M just changed. Without gating on whether your inputs have changed since you started, you get phantom regressions

  Agent teams in this release is mcp-agent-mail [1] built into
  the runtime. Mailbox, task list, file locking — zero config,
  just works. I forked agent-mail [2], added heartbeat/presence
  tracking, had a PR upstream [3] when agent teams dropped. For
  coordinating Claude Code instances within a session, the
  built-in version wins on friction alone.

  Where it stops: agent teams is session-scoped. I run Claude
  Code during the day, hand off to Codex overnight, pick up in
  the morning. Different runtimes, async, persistent. Agent
  teams dies when you close the terminal — no cross-tool
  messaging, no file leases, no audit trail that outlives the
  session.

  What survives sherlocking is whatever crosses the runtime
  boundary. The built-in version will always win inside its own
  walls — less friction, zero setup. The cross-tool layer is
  where community tooling still has room. Until that gets
  absorbed too.

  [1] https://github.com/Dicklesworthstone/mcp_agent_mail
  [2] https://github.com/anupamchugh/mcp_agent_mail
  [3]
  https://github.com/Dicklesworthstone/mcp_agent_mail/pull/77

Comments URL: https://news.ycombinator.com/item?id=46883680

Points: 2

# Comments: 0

I haven't opened Xcode in months. My terminal: Claude writes code. build_sim. launch_app_sim. screenshot describe_ui.

What still requires Xcode: Instruments profiling, Signing/provisioning

For UI iteration, describe_ui returning the accessibility tree might actually be more useful to an agent than a preview screenshot.

Ran it on my sessions. Result: none of skills scored STABLE. The structural predictors of high variance: Numbered steps without clear default, Options without (default) marker, Content >4k chars (overthinking zone), Missing constraint language

[1] https://github.com/anupamchugh/shadowbook (bd wobble)

I ran into this building a spec/skill sync system [1] - the "sync once" model breaks down when you need to track whether downstream consumers are aware of upstream changes.

  [1] https://github.com/anupamchugh/shadowbook

Whether Bitcoin is good at this is debatable. Whether it's a real use case isn't.

Comments URL: https://news.ycombinator.com/item?id=46826990

Points: 2

# Comments: 0