Hacker News: scottfalconer

New comment by scottfalconer in "[dead]"

scottfalconer — Fri, 13 Mar 2026 02:39:14 +0000

For the last 20 years, most software process was built around the assumption that creating software is slow and expensive.

That has changed.

New comment by scottfalconer in "[dead]"

scottfalconer — Mon, 29 Dec 2025 21:20:01 +0000

I built self-learning-skills because I noticed my agents often spent time poking around and guessing at things I had already solved in previous runs. I used to manually copy-paste those fixes into future prompts or backport them into my skills.

This repo streamlines that workflow. It acts as a sidecar memory that: - Stops the guessing: Records “Aha moments” locally so the agent doesn’t start from zero next time. - Graduates knowledge: Includes a CLI workflow to Backport proven memories into permanent improvements in your actual skills or docs.

It works with Claude Code, GitHub Copilot, and Codex and any other system that implements the https://agentskills.io specification.

New comment by scottfalconer in "OpenAI codex can now generate best of N responses"

scottfalconer — Sat, 14 Jun 2025 15:01:03 +0000

At first pass this seems 1) incredibly useful for me 2) incredibly expensive for them, but after using it a bit I'm thinking it might be incredibly valuable for them because once I review and approve one of the options, they're essentially getting preference data on which of the approaches I felt was "best".

Thoughts from those who have used it?

OpenAI codex can now generate best of N responses

scottfalconer — Sat, 14 Jun 2025 15:01:03 +0000

Article URL: https://help.openai.com/en/articles/11428266-codex-changelog

Comments URL: https://news.ycombinator.com/item?id=44276813

Points: 2

# Comments: 2

Any good strategies to avoid merge conflicts when using Codex, Jules, etc.?

scottfalconer — Mon, 09 Jun 2025 15:00:39 +0000

I tend to start tasks one at a time, let them complete, and then start the next. I know I can manually resolve the conflicts, but in a flow that's otherwise generally painless that feels like a huge diversion.

I tried asking it to rebase, but that tends to error out due to resource limitations (and when I asked jules to do it, it flat out refused).

My plan is to explore structuring my tasks like I would with a human dev team - targeting specific areas / files in isolation, but was wondering if anyone else has any good tips here.

tldr: I'm lazy and would prefer to not deal with merge conflicts in an otherwise great workflow.

Comments URL: https://news.ycombinator.com/item?id=44225188

Points: 1

# Comments: 0

Completing four development tasks while on a trail run

scottfalconer — Sun, 08 Jun 2025 19:59:42 +0000

I tend to tend to get my best ideas when I'm not sitting in front of a computer.

My general workflow was:

- Be out. - Think of idea. - Make a note on my phone. - Hopefully remember to look at it later. (Rarely happened)

but now it's:

- Be out. - Think of idea. - Kick off coding / creative / research agent to do whatever I’m thinking of. - Review when I’m home.

Why make a note when you can just as easily start doing the thing?

So today I put it to the test and decided to see how much dev work I could get done while on a run.

My workflow: Kick off an initial task, head out on the trails, whenever I got to a shady spot, check the tasks, merge the ones with passing tests, and start new tasks as needed.

End results:

~5 miles through the Boise foothills. ~550ft elevation gain. - 7 development tasks kicked off. - 4 pull requests reviewed and merged.

Development tasks initiated, developed, and merged while on the run:

https://github.com/scottfalconer/compact-memory/pull/399

https://github.com/scottfalconer/compact-memory/pull/400

https://github.com/scottfalconer/compact-memory/pull/401

https://github.com/scottfalconer/compact-memory/pull/402

Strava map:

https://strava.app.link/e83SL3bz2Tb

Comments URL: https://news.ycombinator.com/item?id=44219172

Points: 1

# Comments: 0

New comment by scottfalconer in "A Research Preview of Codex"

scottfalconer — Fri, 16 May 2025 17:04:25 +0000

Next week: OpenAI rebrands Windsurf as Codex.

New comment by scottfalconer in "AI Is Like a Crappy Consultant"

scottfalconer — Tue, 13 May 2025 13:33:59 +0000

A good manager can make a less-than-ideal contributor highly effective with the right guidance and feedback. Applies to AI as well.

New comment by scottfalconer in "Ask HN: What are you working on? (April 2025)"

scottfalconer — Mon, 28 Apr 2025 17:08:46 +0000

A minimalist, text-based memory system designed to naturally store and recall important events. It emphasizes simplicity, portability, and human-friendly structure by using six optional fields: who, what, when, where, how, and thing. These fields capture factual context clearly, deferring interpretation for later use or analysis.

https://github.com/scottfalconer/vibedb

I still have no idea if it's a good idea or a bad idea but it's been fun to think through.

New comment by scottfalconer in "Not worried about AI taking our jobs; worried it won't take our current jobs"

scottfalconer — Sun, 27 Apr 2025 21:18:08 +0000

Happy to clarify. The parent comment tackles a macro-economic utopia I never proposed. My post was about individual level gains: using AI to automate routine work, offload mental load, and free time to think, create, or just live.

I’m not claiming to fix the global economy, nor denying real risks like job loss or scarcity. Labeling me a "summer child" assumes I am naive about those challenges...another projection.

In short, I described a practical benefit available today, not a perfect future. A thoughtful reply would engage with those points instead of refuting a position I never took.

New comment by scottfalconer in "Not worried about AI taking our jobs; worried it won't take our current jobs"

scottfalconer — Sun, 27 Apr 2025 20:02:21 +0000

I believe there's still plenty of margin to capture beyond merely overseeing AI. Could we reach a point where humans add no marginal utility? Maybe. I hope not, but we can't discount the possibility.

New comment by scottfalconer in "Not worried about AI taking our jobs; worried it won't take our current jobs"

scottfalconer — Sun, 27 Apr 2025 19:57:13 +0000

Once again you make an incorrect assumption and then build an argument against it. Good luck.

New comment by scottfalconer in "Not worried about AI taking our jobs; worried it won't take our current jobs"

scottfalconer — Sun, 27 Apr 2025 19:16:28 +0000

What are the false things that I believe in? Seems like you're making some pretty big assumptions on how I think of the world.

New comment by scottfalconer in "Not worried about AI taking our jobs; worried it won't take our current jobs"

scottfalconer — Sun, 27 Apr 2025 19:09:33 +0000

Totally hear you. Reinvesting saved time in higher-value / more interesting work doesn’t remove the structural-equity risk, which arguably might be the most challenging problem to solve.

New comment by scottfalconer in "Not worried about AI taking our jobs; worried it won't take our current jobs"

scottfalconer — Sun, 27 Apr 2025 19:01:57 +0000

100% agree. Workflow automation is the easy part...a system that leads to fair value distribution is a whole other issue.

Not worried about AI taking our jobs; worried it won't take our current jobs

scottfalconer — Sun, 27 Apr 2025 16:51:57 +0000

I want us to plan, strategize, review, and set AI tools to auto. While they work, we're free to be human - thinking, creating, living. Agree, disagree?

Comments URL: https://news.ycombinator.com/item?id=43813256

Points: 13

# Comments: 18

New comment by scottfalconer in "Lessons Learned Writing a Book Collaboratively with LLMs"

scottfalconer — Fri, 25 Apr 2025 11:39:15 +0000

In the end there are plenty of stories, but they're ones that are relevant. The story that the LLM gave feedback on was about flipping a raft on the Grand Canyon, the LLM's advice was that it felt unrelated to the point I was trying to make. That made me realize I had it in there more because I wanted to talk about the rafting Grand Canyon, vs. it being useful and entertaining to readers.

New comment by scottfalconer in "Lessons Learned Writing a Book Collaboratively with LLMs"

scottfalconer — Thu, 24 Apr 2025 15:25:37 +0000

I think it was faster in that I would have never written the book without the LLMs. Essentially they unlocked the swirl of thoughts and notes that lived somewhere between my head, TextEdit, emails to myself, and anywhere else I stashed things.

It's like it unblocked the "hard part" (getting the words into a coherent form for others), while letting me focus on the "value parts" (my unique perspective / ideas).

It might not be that overall it saved me time, but it made it a hell of a lot more fun, so in the end I completed it - and maybe AI helping us see things through to completion is where we'll see a big unblock in human potential.

New comment by scottfalconer in "Ask HN: Is politeness towards LLMs good training data, or just expensive noise?"

scottfalconer — Thu, 24 Apr 2025 15:06:57 +0000

Even in that it likely depends on what you're measuring for waste. Is it wasted electricity, or is wasted productivity/opportunity time waiting for your machine to boot up?

New comment by scottfalconer in "Ask HN: Is politeness towards LLMs good training data, or just expensive noise?"

scottfalconer — Thu, 24 Apr 2025 00:09:29 +0000

The email is a good callout, chat would feel the same. What's interesting is the nuance in those channels, i.e. someone saying "hi" by itself in a work chat seems rude to me... just get to the point. But if it was switched in a real conversation, it'd feel rude without.