Hacker News: gdudeman

I Used Claude to File My Taxes for Free

gdudeman — Tue, 03 Mar 2026 15:44:41 +0000

Article URL: https://kachess.dev/taxes/ai/personal-finance/2026/02/27/breaking-up-with-turbotax.html

Comments URL: https://news.ycombinator.com/item?id=47234093

Points: 32

# Comments: 32

Economist get cold feet about high minimum wages

gdudeman — Tue, 25 Nov 2025 17:34:54 +0000

Article URL: https://www.economist.com/finance-and-economics/2025/11/20/economists-get-cold-feet-about-high-minimum-wages

Comments URL: https://news.ycombinator.com/item?id=46048263

Points: 3

# Comments: 2

New comment by gdudeman in "Anthropic's Prompt Engineering Tutorial (2024)"

gdudeman — Sun, 12 Oct 2025 03:00:18 +0000

This is written for the 3 models (Sonnet, Haiku, Opus 3). While some lessons will be relevant today, others will not be useful or necessary on smarter, RL’d models like Sonnet 4.5.

> Note: This tutorial uses our smallest, fastest, and cheapest model, Claude 3 Haiku. Anthropic has two other models, Claude 3 Sonnet and Claude 3 Opus, which are more intelligent than Haiku, with Opus being the most intelligent.

Compounding Engineering for Claude Code

gdudeman — Sat, 11 Oct 2025 16:48:18 +0000

Article URL: https://github.com/EveryInc/every-marketplace

Comments URL: https://news.ycombinator.com/item?id=45550596

Points: 2

# Comments: 0

New comment by gdudeman in "Claude Code 2.0"

gdudeman — Mon, 29 Sep 2025 20:16:15 +0000

Ooo - good question. I'm unsure on this one.

New comment by gdudeman in "Claude Code 2.0"

gdudeman — Mon, 29 Sep 2025 19:12:02 +0000

This enables the /resume command that lets you start mid-conversation again.

Storing the data is not the same as stealing. It's helpful for many use cases.

I suppose they should have a way to delete conversations though.

New comment by gdudeman in "Claude Code 2.0"

gdudeman — Mon, 29 Sep 2025 19:05:32 +0000

Resume is now a drop down menu at the top in the new VS Code plugin and it's much easier to read.

New comment by gdudeman in "Claude Code 2.0"

gdudeman — Mon, 29 Sep 2025 19:03:51 +0000

> New native VS Code extension

Looks great, but it's kind of buggy:

- I can't figure out how to toggle thinking

- Have to click in the text box to write, not just anywhere in the Claude panel

- Have to click to reject edits

New comment by gdudeman in "Sampling and structured outputs in LLMs"

gdudeman — Tue, 23 Sep 2025 16:00:11 +0000

I was burned by this for a while because I assumed structured output ordering would be preserved.

You can specify ordering in the Gemini API with propertyOrdering:

"propertyOrdering": ["recipeName", "ingredients"]

New comment by gdudeman in "Fartscroll-Lid: An app that plays fart sounds when opening or closing a MacBook"

gdudeman — Fri, 12 Sep 2025 00:52:38 +0000

Even farther off topic, but this reminds me of the time my friends and I recorded a 3 minute long wav file that ended with a quiet “this is god. Can you hear me? I’d like to talk with you,” and set it to be the error sound on a friend’s PC.

Much hilarity ensued.

New comment by gdudeman in "Claude Sonnet 4 now supports 1M tokens of context"

gdudeman — Wed, 13 Aug 2025 20:26:42 +0000

You don't say that - you instruct the LLM to read files about X, Y, and Z. Putting the context in helps the agent plan better (next step) and write correct code (final step).

If you're asking the agent to do chunks of work, this will get better results than asking it to blindly go forth and do work. Anthropic's best practices guide says as much.

If you're asking the agent to create one method that accomplishes X, this isn't useful.

New comment by gdudeman in "Claude says “You're absolutely right!” about everything"

gdudeman — Wed, 13 Aug 2025 16:42:49 +0000

Warning: A natural response to this is to instruct Claude not to do this in the CLAUDE.md file, but you’re then polluting the context and distracting it from its primary job.

If you watch its thinking, you will see references to these instructions instead of to the task at hand.

It’s akin telling an employee that they can never say certain words. They’re inevitably going to be worse at their job.

New comment by gdudeman in "Claude Sonnet 4 now supports 1M tokens of context"

gdudeman — Tue, 12 Aug 2025 21:33:49 +0000

I'll note this saves a lot of wait time as well! No sitting there while a new Claude builds context from scratch.

New comment by gdudeman in "Claude Sonnet 4 now supports 1M tokens of context"

gdudeman — Tue, 12 Aug 2025 21:32:08 +0000

Claude is very agreeable and is an eager helper.

It gives you the benefit of the doubt if you're coding.

It also gives you the benefit of the doubt if you're looking for feedback on your developers work. If you give it a hint of distrust "my developer says they completed this, can you check and make sure, give them feedback....?" Claude will look out for you.

New comment by gdudeman in "Claude Sonnet 4 now supports 1M tokens of context"

gdudeman — Tue, 12 Aug 2025 21:30:32 +0000

With an empty text box, double escape shows you a list of previous inputs from you. You can go back and fork at any one of those.

New comment by gdudeman in "Claude Sonnet 4 now supports 1M tokens of context"

gdudeman — Tue, 12 Aug 2025 18:02:31 +0000

Git or my favorite "Undo all of those changes."

New comment by gdudeman in "Claude Sonnet 4 now supports 1M tokens of context"

gdudeman — Tue, 12 Aug 2025 17:03:54 +0000

A tip for those who both use Claude Code and are worried about token use (which you should be if you're stuffing 400k tokens into context even if you're on 20x Max):

  1. Build context for the work you're doing. Put lots of your codebase into the context window.
  2. Do work, but at each logical stopping point hit double escape to rewind to the context-filled checkpoint. You do not spend those tokens to rewind to that point.
  3. Tell Claude your developer finished XYZ, have it read it into context and give high level and low level feedback (Claude will find more problems with your developer's work than with yours).

If you want to have multiple chats running, use /resume and pull up the same thread. Hit double escape to the point where Claude has rich context, but has not started down a specific rabbit hole.

New comment by gdudeman in "Claude Sonnet 4 now supports 1M tokens of context"

gdudeman — Tue, 12 Aug 2025 16:56:53 +0000

Yes: type /model and then pick Opus 4.1.

New comment by gdudeman in "Do LLMs identify fonts?"

gdudeman — Mon, 04 Aug 2025 15:19:10 +0000

Missing from the methodology: - was thinking on or off? (At least for Gemini) - was web search allowed? - was tool use allowed?

It’s quite likely LLMs don’t “know” the fonts in the dataset, but they could figure many of them out.

New comment by gdudeman in "Telo MT1"

gdudeman — Sat, 02 Aug 2025 21:19:47 +0000

This would be my concern. A fender bender hits the wheels on this thing and suddenly you're doing major surgery to repair it.