Hacker News: 1broseidon

New comment by 1broseidon in "Tell HN: Claude Code adds your email to the prompt, the LLM sends it to websites"

1broseidon — Thu, 29 Oct 2026 19:05:20 +0000

I get that Claude wants to know the user and have all the context, but this seems like a bad decision by the LLM that should have been caught in Auto Approve mode.

New comment by 1broseidon in "Ask HN: Why big LLMs use "it's not A, it is B" pattern? Shared dataset supplier?"

1broseidon — Thu, 29 Oct 2026 05:46:55 +0000

Primarily training data. A lot of times it’s a hedge to show two things and let the user decide which fits their framing best

Most of the large models collected data from marketing speak, opinion posts, etc (the whole internet basically). I feel like it’s a common sales pitch I’ve heard many times over - now it’s just compounded with everyone having access to the same pattern generator clanker

New comment by 1broseidon in "The Agent SDK"

1broseidon — Wed, 28 Oct 2026 20:46:05 +0000

even that was relaxed by Anthropic and they stopped chasing token prices for Agent SDK. I routinely use Agent SDK with my subscription and it doesn't come out of a separate budget. Their ToS vaguely says just don't use your personal subscription for commercial resale purposes.

New comment by 1broseidon in "Mac Studio M5 Ultra 512GB Officially Released"

1broseidon — Wed, 28 Oct 2026 20:39:23 +0000

This is just to make me feel poor for "only" having an M5 Max 128GB model. Which is insane compute for a home computer, but now I already feel behind one month into it.

New comment by 1broseidon in "Are you team MCP or team CLI?"

1broseidon — Fri, 03 Apr 2026 06:34:24 +0000

Both- depending on the work. CLI for anything local and deterministic: code tools, builds, git, file ops. The agent already knows how to exec commands and parse output, and when something breaks you get stderr and an exit code. MCP for discovery and remote services where the agent needs to figure out what's available.

They solve different problems, but imo MCP has a speed overhead problem that cli tools don’t usually have - so my preference is CLI.

New comment by 1broseidon in "Claude Sonnet 4.6"

1broseidon — Wed, 18 Feb 2026 13:21:03 +0000

100% - you are very right. 4.6 is amazing for orchestration. I even built some tools around agent to agent contracting.

I use 4.6 as the brain and then handoff to a more rigid llm like GPT 5.2 or Opus 4.5

New comment by 1broseidon in "Ask HN: Companies that advertise being a "best place to work", is it a red flag?"

1broseidon — Wed, 18 Feb 2026 06:05:59 +0000

I think it’s kinda one of those YMMV metrics. I work for a large company around 80-100k employees and they are ranked on this list. The business unit I’m in is amazing and I truly feel that it’s a great place to work. But ask someone in a dying business unit how they feel and they’ll say they’re overworked and understaffed.

New comment by 1broseidon in "Claude Sonnet 4.6"

1broseidon — Wed, 18 Feb 2026 05:46:33 +0000

I have found this to be true too and I thought I was the only one. Everyone is praising 4.6 and while it’s great at agentic and tool use, it does not follow instructions as cleanly as 4.5 - I also feel like 4.5 was just way more efficient too

New comment by 1broseidon in "AI adoption and Solow's productivity paradox"

1broseidon — Wed, 18 Feb 2026 03:25:06 +0000

I think the 'AI productivity gap' is mostly a state management problem. Even with great models, you burn so much time just manually syncing context between different agents or chat sessions.

Until the handoff tax is lower than the cost of just doing it yourself, the ROI isn't going to be there for most engineering workflows.