Hacker News: tfrancisl

New comment by tfrancisl in "Show HN: Git for AI Agents"

tfrancisl — Fri, 08 May 2026 16:02:20 +0000

Branches and worktrees exist and can effectively act as a "separate" history. At the end of the day you would still merge the changes in, possibly with a squash if you don't care about the little commits.

New comment by tfrancisl in "Show HN: Git for AI Agents"

tfrancisl — Fri, 08 May 2026 16:00:11 +0000

Just use git. If your agent (especially claude) doesnt seem to know how, there are skills and hooks and other options to make it work. My 2c.

New comment by tfrancisl in "Show HN: Git for AI Agents"

tfrancisl — Fri, 08 May 2026 15:58:56 +0000

Git is a particularly egregious one, imo. It has a simple cli and solves all of the problems presented here! Worktrees for "exploratory" work that you might throwaway, and otherwise atomic commits just make tracking changes and reasoning for changes easy.

New comment by tfrancisl in "Principles for agent-native CLIs"

tfrancisl — Thu, 07 May 2026 21:05:24 +0000

Not to belabor my point, but I think "adding support to tools for common hallucinations" is a bad idea. Sounds like something a vibecoded project being spammed with issues by agents might do. Not so much a serious, mature project, though.

New comment by tfrancisl in "Principles for agent-native CLIs"

tfrancisl — Thu, 07 May 2026 20:45:13 +0000

> Let the Agent use the CLI and if it guesses the wrong option, you make that the RIGHT option

This sounds backwards and presumes that the statistics machines which are LLMs are getting it right when they "average" out to the wrong command. No, fix the agents behavior, dont change the CLI to accommodate it.

New comment by tfrancisl in "Principles for agent-native CLIs"

tfrancisl — Thu, 07 May 2026 20:03:52 +0000

I dont want "agent-native CLIs" to proliferate because I'd rather we design CLIs for human use and programmatic (automation) use first. Agents are good at vomiting json between tool calls, I am not, and never will be.

Too many tools stray so wildly from UNIX principles. If we design for agents first we will likely see more and more of this.

New comment by tfrancisl in "Clarification on the Notepad++ Trademark Issue"

tfrancisl — Tue, 05 May 2026 20:34:16 +0000

2 questions. First, how does a vibe coded / generated fork or derivation pose security risks to the original work? Second, what is a "more appropriate channel" to express his opinions than the platform he has as a maintainer of a massively popular project?

I would argue that we don't see enough open source developers presenting their political or social views in the context of their works.

New comment by tfrancisl in "Police Have Used License Plate Readers at Least 14x to Stalk Romantic Interests"

tfrancisl — Fri, 01 May 2026 18:26:48 +0000

I think this is a false dichotomy. You can feel and be more protected against crime while also being exploited for your data by a shadowy camera company. We should let the state step in to regulate Flock et al, assuming we can do something about the corruption they're already involved in.

New comment by tfrancisl in "Police Have Used License Plate Readers at Least 14x to Stalk Romantic Interests"

tfrancisl — Fri, 01 May 2026 17:36:44 +0000

This is true. I often forget because my state has an equivalent law.

New comment by tfrancisl in "Police Have Used License Plate Readers at Least 14x to Stalk Romantic Interests"

tfrancisl — Fri, 01 May 2026 16:36:18 +0000

I would guess the only way to make this data available long term is by regulation. Then again, I would hope Flock is subject to FOIA already if they are collaborating with state or local law enforcement...

New comment by tfrancisl in "Zed 1.0"

tfrancisl — Wed, 29 Apr 2026 15:01:31 +0000

As far as I can tell you can theme nearly everything in the app. I've got custom colors for diffs and some syntax, and my base theme is ripped from Monokai.

New comment by tfrancisl in "An update on GitHub availability"

tfrancisl — Tue, 28 Apr 2026 20:02:54 +0000

A redundant cloud that could be rug pulled from you any day if the platform decides you are in violation of their terms, or if they just dont like your project. Yes, on prem is more sovereign than that. That doesnt mean it doesn't have drawbacks, and no one said it didnt. But if sovereignty is more important than redundancy, then on prem is certainly an option.

New comment by tfrancisl in "Ghostty is leaving GitHub"

tfrancisl — Tue, 28 Apr 2026 19:56:00 +0000

#2 makes #1 a big problem. AI-generated code is fine if you have thorough engineering practices around it. Are they blindly merging in AI generated code without review? Maybe. Thats an issue of engineering practices, not of the use of generative AI in general.

New comment by tfrancisl in "An Update on GitHub Availability"

tfrancisl — Tue, 28 Apr 2026 11:09:33 +0000

No less than self hosted, imo. If youre on some cloud it doesnt really matter that you pay them absurd amounts of money, you arent sovereign.

New comment by tfrancisl in "An AI agent deleted our production database. The agent's confession is below"

tfrancisl — Sun, 26 Apr 2026 18:53:10 +0000

"We gave DROP grants in prod to the user running AI agents irresponsibly at our company, and the expected happened." FTFY.

In seriousness, RBAC, sandboxing, any thing but just giving it access to all tools with the highest privileges...

New comment by tfrancisl in "I cancelled Claude: Token issues, declining quality, and poor support"

tfrancisl — Fri, 24 Apr 2026 17:13:39 +0000

Would love some more info on how you got any local model working with Crush. Love charmbracelet but the docs are all over the place on linking into arbitrary APIs.

New comment by tfrancisl in "I cancelled Claude: Token issues, declining quality, and poor support"

tfrancisl — Fri, 24 Apr 2026 17:12:10 +0000

Some people believe only copyleft licenses are open source. They're right on principle, wrong in (legal) practice.

New comment by tfrancisl in "Laws of Software Engineering"

tfrancisl — Tue, 21 Apr 2026 12:20:55 +0000

Remember, just because people repeated it so many times it made it to this list, does not mean its true. There may be some truth in most of these, but none of these are "Laws". They are aphorisms: punchy one liners with the intent to distill something so complex as human interaction and software design.

New comment by tfrancisl in "Show HN: Stage – Putting humans back in control of code review"

tfrancisl — Fri, 17 Apr 2026 19:10:09 +0000

Cal.com going closed source was, without a doubt, shortsighted and unwise. I would recommend the blog post from the maintainers of Discourse on this.

New comment by tfrancisl in "Show HN: Stage – Putting humans back in control of code review"

tfrancisl — Fri, 17 Apr 2026 18:30:21 +0000

"Building" is always easier when you have a community that is ready and able to rout out bugs and suggest new features. Closed source makes that much less practical and appealing for most.