Hacker News: tobyhinloopen

New comment by tobyhinloopen in "If your product is Great, it doesn't need to be Good (2010)"

tobyhinloopen — Fri, 19 Jun 2026 15:14:33 +0000

Gotta love the LP4 mode. So much music on a single disk! Remember the cool rectangular batteries? Why aren't these gumstick batteries more used in modern devices!?

New comment by tobyhinloopen in "DuckDB Internals: Why Is DuckDB Fast? (Part 1)"

tobyhinloopen — Fri, 19 Jun 2026 10:01:31 +0000

I'll 100% try DuckDB in more serious projects where I would normally use Sqlite.

New comment by tobyhinloopen in "DuckDB Internals: Why Is DuckDB Fast? (Part 1)"

tobyhinloopen — Fri, 19 Jun 2026 08:23:55 +0000

The only reason I know and use DuckDB is because my (internal, private-use-only, experimental) vibe coded projects use it a ton. I didn't pick it - LLMs did. Until this article, I wasn't aware of what it actually is capable of.

Most of these projects use JSON(L) files for storage, and duckdb to process them.

New comment by tobyhinloopen in "SpaceX to buy Cursor for $60B"

tobyhinloopen — Wed, 17 Jun 2026 05:54:40 +0000

Try the superpowers plugin, let it write a spec (what do you want?) and a plan (how is it implemented). Then let it implement the plan.

Review each step as much as you care. These things take time so you can just do other stuff while it’s cooking.

With proper isolation of projects you can easily have multiple sessions in parallel. I frequently have 4 to 8 parallel Claude Code sessions, each with whole trees of agents reproducing, speccing, planning, implementing and reviewing things.

For common mistakes, you can make it remember things or rely on reviews.

New comment by tobyhinloopen in "Leaked OpenAI financials show $38.5B loss and compute burn"

tobyhinloopen — Wed, 17 Jun 2026 05:36:48 +0000

You know what’s worse (less efficient) at parsing and writing code than LLMs?

Humans.

New comment by tobyhinloopen in "Reviews have become expensive, rewrites have become cheap"

tobyhinloopen — Tue, 16 Jun 2026 06:03:46 +0000

“This is a significant rewrite that will take weeks”

Done after my potty break

New comment by tobyhinloopen in "Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?"

tobyhinloopen — Mon, 15 Jun 2026 17:41:48 +0000

Try it on RAM and CPU.

It’s slower but you can run them.

New comment by tobyhinloopen in "Arch Linux Now Believes Malware Incident Under Control: More Than 1,500 Packages"

tobyhinloopen — Mon, 15 Jun 2026 09:36:37 +0000

That’s a great idea. Maybe use Claude Code with some owasp knowledge to sweep through them and see if there’s anything obvious?

New comment by tobyhinloopen in "Why does paper fold so well?"

tobyhinloopen — Mon, 15 Jun 2026 08:31:02 +0000

Because the air is squished out I suppose

New comment by tobyhinloopen in "Arch Linux Now Believes Malware Incident Under Control: More Than 1,500 Packages"

tobyhinloopen — Sat, 13 Jun 2026 14:08:55 +0000

Min Release Age of 7-30 days covers the majority of potential issues with 0 effort.

All major Node package managers should support it by now.

Prom was the best IIRC, yarn second, but even npm is catching up

New comment by tobyhinloopen in "Statement on US government directive to suspend access to Fable 5 and Mythos 5"

tobyhinloopen — Sat, 13 Jun 2026 05:29:19 +0000

I agree with this, It feels like a small upgrade like Opus 4.9 or something.

It’s still pretty good though

New comment by tobyhinloopen in "Statement on US government directive to suspend access to Fable 5 and Mythos 5"

tobyhinloopen — Sat, 13 Jun 2026 05:25:18 +0000

I’ve been doing pentesting with LLMs for a while and only hit a few “nope I won’t do that” and one “this conversation is flagged for being against the TOS”. No idea what the guardrails are but they are trivially abused

New comment by tobyhinloopen in "How to setup a local coding agent on macOS"

tobyhinloopen — Fri, 12 Jun 2026 19:51:50 +0000

Claude “respond in a friendly way that I agree with this comment”

New comment by tobyhinloopen in "If you are asking for human attention, demonstrate human effort"

tobyhinloopen — Fri, 12 Jun 2026 05:57:18 +0000

I actively support “my boss” to run Claude Code. I offered them to help and made jokes it’s so easy these days they might as well just call Claude Code themselves. I’ve shown I could plop in their documents of feedback and Claude fixed the issues.

I have worked with non-tech employees to set up Claude to help them do small tasks. I’ve helped to review and improve completely vibe-coded projects by such employees.

I’m not sure what my role will be, but I fully embrace that my traditional role of writing code is gone.

New comment by tobyhinloopen in "If you are asking for human attention, demonstrate human effort"

tobyhinloopen — Fri, 12 Jun 2026 05:47:35 +0000

I told something like “your value lies in reviewing the output yourself before sharing it, not in calling Claude. I can also use Claude.”

New comment by tobyhinloopen in "Building an HTML-first site doubled our users overnight"

tobyhinloopen — Thu, 11 Jun 2026 06:25:51 +0000

You can order LLMs to use other patterns. I had an LLM recreate an app in a different stack with reasonable success

New comment by tobyhinloopen in "Anthropic requires 30 day data retention for Fable and Mythos"

tobyhinloopen — Thu, 11 Jun 2026 05:01:00 +0000

You mean these tools you can now rebuild at the cost of a night and one Claude code subscription?

You have to have an ordinarily unique startup if your software can’t be recreated quickly.

New comment by tobyhinloopen in "Upcoming breaking changes for npm v12"

tobyhinloopen — Wed, 10 Jun 2026 09:36:55 +0000

That’s a bold claim to randomly write without any supporting sources

New comment by tobyhinloopen in "Apple reveals new AI architecture built around Google Gemini models"

tobyhinloopen — Mon, 08 Jun 2026 21:18:06 +0000

Just as long as you speak a major language

New comment by tobyhinloopen in "LLMs are eroding my software engineering career and I don't know what to do"

tobyhinloopen — Sun, 07 Jun 2026 21:19:31 +0000

(A) I spent day and night using and making tools with and for LLMs. (B) As much as I humanly can.