Hacker News: bear3r

New comment by bear3r in "A case for Go as the best language for AI agents"

bear3r — Mon, 02 Mar 2026 23:17:40 +0000

the article conflates two different things: what's easy for an LLM to write vs. what's safe to run. python wins on the first axis (smaller context, more training data, faster iteration). go wins on the second (compile errors caught early, explicit error handling). for a long-running autonomous agent that can't be supervised, you probably want the second. for a human-in-the-loop workflow where you can just rerun, the first.

New comment by bear3r in "Microgpt"

bear3r — Mon, 02 Mar 2026 05:13:02 +0000

tradeoff worth naming: you avoid the autodiff graph overhead (hence the speedup), but any architecture change means rewriting every gradient by hand. fine for a pedagogical project, but that's exactly why autodiff exists.

New comment by bear3r in "If AI writes code, should the session be part of the commit?"

bear3r — Mon, 02 Mar 2026 03:12:11 +0000

reproducibility isn't really the goal imo. more like a decision audit trail -- same reason code comments have value even though you can't regenerate the code from them. six months later when you're debugging you want to know 'why did we choose this approach' not 'replay the exact conversation.'

New comment by bear3r in "WebMCP is available for early preview"

bear3r — Mon, 02 Mar 2026 01:11:37 +0000

different threat model. cloudflare blocks automation that pretends to be human -- scraping, fake clicks, account stuffing. webmcp is a site explicitly publishing 'here are the actions i sanction.' you can block selenium on login and expose a webmcp flight search endpoint at the same time. one's unauthorized access, the other's a published api.

New comment by bear3r in "Why XML tags are so fundamental to Claude"

bear3r — Sun, 01 Mar 2026 23:11:00 +0000

the antml: namespace prefix is doing extra work here too -- even if user input contains invoke tags, they won't collide with tool calls because the namespace differs. not just xml for structure but namespaced xml for isolation.

New comment by bear3r in "When does MCP make sense vs CLI?"

bear3r — Sun, 01 Mar 2026 21:11:27 +0000

fair point on token efficiency -- dsls are usually tighter than json. where i see mcp still winning is tool discovery: the client learns what tools exist and what args they take without having to try calling them first or knowing the commands upfront. with cli you have to already know the tool exists.

New comment by bear3r in "When does MCP make sense vs CLI?"

bear3r — Sun, 01 Mar 2026 19:01:04 +0000

the output format (ascii/json/markdown) is one piece, but the other side is input schema. mcp declares what args are valid and their types upfront, so the model can't hallucinate a flag that doesn't exist. cli tools don't expose that contract unless you parse --help output, which is fragile.

New comment by bear3r in "MCP server that reduces Claude Code context consumption by 98%"

bear3r — Sun, 01 Mar 2026 17:02:23 +0000

yeah gh cli in particular is lean. though `gh pr view --json body,comments` can still flood context fast. the real win here is gatekeeping what hits context at all, regardless of source.