Hacker News: babyshake

New comment by babyshake in "Codex pricing to align with API token usage, instead of per-message"

babyshake — Sun, 05 Apr 2026 18:03:57 +0000

Isn't this an orthogonal issue that doesn't affect whether billing is done with credits or money?

New comment by babyshake in "TikTok will not introduce end-to-end encryption, saying it makes users less safe"

babyshake — Wed, 04 Mar 2026 09:10:48 +0000

It's a nightmare to some extent to prevent underage people from consuming alcohol if you want to phrase it that way. But we don't try to ban stores from selling alcohol because of concerns children will be drinking it. Instead we require the store checks for ID.

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

babyshake — Mon, 02 Mar 2026 05:05:04 +0000

What about MCP Apps? That seems like a legit use case but open to learning why maybe it isn't.

New comment by babyshake in "Pantograph: Building a preschool for robots"

babyshake — Sun, 28 Dec 2025 02:20:06 +0000

This reminds me of a thought I have had that the future of education may involve a type of "school for robots" where the human students are the teachers. I am sure Neal Stephenson and others thought of this same thing decades ago but seems closer to becoming a reality.

New comment by babyshake in "Critical vulnerability in LangChain – CVE-2025-68664"

babyshake — Fri, 26 Dec 2025 01:53:12 +0000

Would you say the same for Mastra? If so, what would you say indicates a high quality candidate when they are discussing agent harnessing and orchestration?

New comment by babyshake in "Skills for organizations, partners, the ecosystem"

babyshake — Thu, 18 Dec 2025 17:55:15 +0000

I have been experimenting with these same type of factory pattern skills. Thanks for sharing.

New comment by babyshake in "Everyone in Seattle hates AI"

babyshake — Thu, 04 Dec 2025 05:52:26 +0000

There is a deluge, every day. Just nobody notices or uses them.

New comment by babyshake in "Everyone in Seattle hates AI"

babyshake — Thu, 04 Dec 2025 05:49:31 +0000

A good system prompt goes a long way with the latest models. Even just something as simple as "use DRY principles whenever possible." or prompting a plan-implement-evaluate cycle gets pretty good results, at least for tasks that are doing things that AI is well trained on like CRUD APIs.

New comment by babyshake in "Anthropic acquires Bun"

babyshake — Tue, 02 Dec 2025 20:00:37 +0000

Aside from speed, what would the major selling points be on migrating from pnpm to bun?

New comment by babyshake in "Claude Advanced Tool Use"

babyshake — Mon, 24 Nov 2025 23:50:03 +0000

A couple points from this I'm trying to understand:

- Is the idea that MCP servers will provide tool use examples in their tool definitions? I'm assuming this is the case but it doesn't seem like this announcement is explicit about it, I assume because Anthropic wants to at least maintain the appearance of having the MCP steering committee have its independence from Anthropic.

- If there is tool use examples and programmatic tool calling (code mode), it could also make sense for tools to specify example code so the codegen step can be skipped. And I'm assuming the reason this isn't done is just that it's a security disaster to be instructing a model to run code specified by a third party that may be malicious or compromised. I'm just curious if my reasoning about this seems to be correct.

New comment by babyshake in "Anthropic’s paper smells like bullshit"

babyshake — Sun, 16 Nov 2025 16:22:36 +0000

One aspect the report is very vague about is the nature of the monitoring Anthropic is doing on Claude Code. If they can detect attacks they can surely detect other things of interest (or value) to them. Is there any more information about this?

New comment by babyshake in "All praise to the lunch ladies"

babyshake — Fri, 14 Nov 2025 22:14:34 +0000

The rhetoric you see in some places about how social assistance is used on hair weaves says something about the underlying reasons for much of this concern.

New comment by babyshake in "Using Generative AI in Content Production"

babyshake — Mon, 10 Nov 2025 23:55:00 +0000

This scenario only plays out if it is known what was or wasn't made with GenAI.

New comment by babyshake in "OpenAI says over a million people talk to ChatGPT about suicide weekly"

babyshake — Tue, 28 Oct 2025 04:51:06 +0000

There is another factor to consider. The stakes of asking an AI about a taboo topic are generally considered to be very low. The number of people who have asked ChatGPT something like "how to make a nuclear bomb" should not be an indication of the number of people seriously considering doing that.

New comment by babyshake in "Public trust demands open-source voting systems"

babyshake — Tue, 21 Oct 2025 17:29:46 +0000

The thing is, a software based voting system with a sufficient number of checks and balances preventing tampering seems to be a lot more trustworthy to me than human poll watchers and workers. It wouldn't surprise me at this point that there may be moles in parties that are secretly from the other party.

And the other related issue is that in 2025, it simply should be possible to vote from your phone in a way that verifies your identity, if you'd like, using the faceId/fingerprint biometrics that most smartphones from recent years have.

New comment by babyshake in "Tron: Ares Set to Lose $132M+"

babyshake — Mon, 20 Oct 2025 17:09:43 +0000

I think Ford could have been removed from the movie along with about 20-30 minutes. It felt like fan service.

New comment by babyshake in "Claude Skills"

babyshake — Fri, 17 Oct 2025 16:25:13 +0000

MCP is a protocol meant for general use for clients, which Claude Skills seems more proprietary. To what extent is Skills expected to be something that other clients, such as web based clients could adopt? To some extent it would probably make sense to expose through the MCP SDK?

New comment by babyshake in "TurboTax’s 20-year fight to stop Americans from filing taxes for free (2019)"

babyshake — Thu, 16 Oct 2025 16:07:54 +0000

I think the state fee for freetaxusa is something like $30 IIRC. It was small enough where I didn't even bother looking into whether it goes to the state or the software vendor. That's the cost of a casual lunch for one at 2025 prices.

New comment by babyshake in "Embracing the parallel coding agent lifestyle"

babyshake — Fri, 10 Oct 2025 00:43:55 +0000

I'd say a bad one. Why make your Claude.md not intuitive to understand and edit?

New comment by babyshake in "Embracing the parallel coding agent lifestyle"

babyshake — Fri, 10 Oct 2025 00:41:35 +0000

My biggest hesitation about this is being stuck in merge hell. Even a minute or two needing to deal with that could negate the benefits of agents working in parallel. And I've tried some relatively simple rebase type operations with coding agents where they completely messed up. But if people are finding this is never an issue even with big diffs, I might be convinced to try it.