HackerTrans
TopNewTrendsCommentsPastAskShowJobs

scottfalconer

no profile record

Submissions

[untitled]

1 points·by scottfalconer·2 mesi fa·0 comments

[untitled]

1 points·by scottfalconer·2 mesi fa·0 comments

[untitled]

1 points·by scottfalconer·2 mesi fa·0 comments

[untitled]

1 points·by scottfalconer·2 mesi fa·0 comments

[untitled]

1 points·by scottfalconer·3 mesi fa·0 comments

[untitled]

1 points·by scottfalconer·4 mesi fa·0 comments

[untitled]

1 points·by scottfalconer·5 mesi fa·0 comments

[untitled]

1 points·by scottfalconer·5 mesi fa·0 comments

[untitled]

1 points·by scottfalconer·6 mesi fa·0 comments

[untitled]

1 points·by scottfalconer·7 mesi fa·0 comments

[untitled]

1 points·by scottfalconer·anno scorso·0 comments

OpenAI codex can now generate best of N responses

help.openai.com
2 points·by scottfalconer·anno scorso·2 comments

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

1 points·by scottfalconer·anno scorso·0 comments

Completing four development tasks while on a trail run

1 points·by scottfalconer·anno scorso·0 comments

[untitled]

1 points·by scottfalconer·anno scorso·0 comments

[untitled]

1 points·by scottfalconer·anno scorso·0 comments

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

13 points·by scottfalconer·anno scorso·18 comments

[untitled]

1 points·by scottfalconer·anno scorso·0 comments

Ask HN: Is politeness towards LLMs good training data, or just expensive noise?

8 points·by scottfalconer·anno scorso·13 comments

Every Interaction Is a Turing Test

2 points·by scottfalconer·anno scorso·1 comments

comments

scottfalconer
·mese scorso·discuss
Getting the right answers is just half of it, you need to know the right questions to ask. I haven't yet seen AI crack that one.
scottfalconer
·4 mesi fa·discuss
For the last 20 years, most software process was built around the assumption that creating software is slow and expensive.

That has changed.
scottfalconer
·7 mesi fa·discuss
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.
scottfalconer
·anno scorso·discuss
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?
scottfalconer
·anno scorso·discuss
Next week: OpenAI rebrands Windsurf as Codex.
scottfalconer
·anno scorso·discuss
A good manager can make a less-than-ideal contributor highly effective with the right guidance and feedback. Applies to AI as well.
scottfalconer
·anno scorso·discuss
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.
scottfalconer
·anno scorso·discuss
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.
scottfalconer
·anno scorso·discuss
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.
scottfalconer
·anno scorso·discuss
Once again you make an incorrect assumption and then build an argument against it. Good luck.
scottfalconer
·anno scorso·discuss
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.
scottfalconer
·anno scorso·discuss
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.
scottfalconer
·anno scorso·discuss
100% agree. Workflow automation is the easy part...a system that leads to fair value distribution is a whole other issue.
scottfalconer
·anno scorso·discuss
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.
scottfalconer
·anno scorso·discuss
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.
scottfalconer
·anno scorso·discuss
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?
scottfalconer
·anno scorso·discuss
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.
scottfalconer
·anno scorso·discuss
That was my gut too, but in general it's a question I've wondered about. i.e. what are the signals we send in our usage that will be beneficial to improving the models.
scottfalconer
·anno scorso·discuss
One of the things I found helpful about getting out of the specific / formulaic feedback was asking the LLM to ask me questions. At one point I asked a fresh LLM to read the book and then ask me questions. It showed me where there were narrative gaps / confusing elements that a reader would run into, but didn't realy on the specific "answer" from the LLM itself.

I also had a bunch of personal stories interwoven in and it told me I was being "indulgent" which was harsh but ultimately accurate.
scottfalconer
·anno scorso·discuss
Anthropic analyzed 700k real-world Claude chats to figure out what values it expresses naturally.

One particularly interesting finding was that nearly half of Claude's real-world conversations involve subjective content...not just factual Q&A. From over 700,000 analyzed chats, ~44% include interactions where Claude had to express judgments or preferences.