Live data from Hacker News

I used o3 to profile myself from my saved Pocket links

noperator.dev

191–200 of 217 posts

Re: I used o3 to profile myself from my saved Pocket links

#191
post #76

When moving my links from Pocket to Wallabag I passed them through Claude for tagging. Worked very well

Did you come up with a defined list of tags or just ask it to zero-shot give you a tag?

I considered trying to curate a list but decided the tags for me were really to get an idea of the contents of the article and not for management so I didn't really care if tags were reused or one offs.

This was the prompt:

  You are a helpful assistant that tags articles in my read it later list.
        You will be given an article with content, title, and url, and you will need to tag it with the most relevant tags.

        Rule: Try to keep high level tags to a minimum.
        Rule: Max 5 tags per article (3–4 is ideal)
        Rule: Tags should represent core themes, not every passing mention.
        Rule: All tags should be lowercase, be singular nouns unless a compound concept, avoid special characters
        Rule: Avoid Redundant or duplicate Tags
        Rule: 1–3 high-level tag + optional granular

        Remember already used tags and prioritize them.

        Return a dictionary with the following structure:
        {{
            "id": {article.id},
            "title": "{article.title}",
            "tags": ["tag1", "tag2", "tag3", ect]
        }}

Re: I used o3 to profile myself from my saved Pocket links

#192
post #152

Earlier quoted context omitted.

How do you trust the recipe without context? People say they want one thing but then their actions and money go to another. I do agree there's unnecessary fluff. But "just give me the recipe" isn't really what people want. And I don't think your represent some outlier take because really have you ever gotten a recipe exactly as you outlined — zero context – and gave a damn to make it?

> How do you trust the recipe without context? Well, I just read it. The stakes are not that high! > have you ever gotten a recipe exactly as you outlined — zero context – and gave a damn to make it? Of course: there are a great many useful cookbooks written exactly this way.

The book is the context! It was published, it has a presumably influential vetted author.

Maybe I am coming off too flippant. I'm just trying to say there's a spectrum between fluff and context. If the AI's literally just gave us answers and list of recipes, it wouldn't be as useful as with the context backing up where it came from, why this list, and so on.

Re: I used o3 to profile myself from my saved Pocket links

#193
post #163
post #152

Earlier quoted context omitted.

How do you trust the recipe without context? People say they want one thing but then their actions and money go to another. I do agree there's unnecessary fluff. But "just give me the recipe" isn't really what people want. And I don't think your represent some outlier take because really have you ever gotten a recipe exactly as you outlined — zero context – and gave a damn to make it?

> How do you trust the recipe without context? Ratings or poster reputation. I often use recipes from a particular chef's website, which are formulated with specific ingredients, steps, and, optionally, a video. I trust the chef since I've yet to try a bad recipe from him. I also often use baking recipes from King Arthur based on ratings. They're also pretty consistently good and don't have much fluff.

Those are good examples. A trusted chef's website can list purely the recipe because it's held within a pre-vetted context. I do this as well.

I'm advocating for the need for those kinds of trust signals. If AI literally just listed ingredients, I wouldn't trust it. How could I?

Re: I used o3 to profile myself from my saved Pocket links

#194

Earlier quoted context omitted.

I believed this, which is what made me avoid computer science in college; I wanted to avoid ruining my favorite hobby. After a few years post graduation, where I wasn't sure what I wanted to do and I floundered to find a career, I decided to give software development a try, and risk ruining my favorite hobby. Definitely the best decision I could have made. Now people pay me a lot of money to do the thing I love to do…

I think it heavily depends on who you're working for. If they get out of the way and let you do the thing you love how you want to do it you'll get good results for you and them. If they treat you like a cog in a machine and assume they need to carrot and stick you into doing things because you might not really want to be there, you'll be miserable.

I have worked a few places at many different positions over an 18 year career so far.

I have enjoyed the programming part of all the jobs. I don’t really care the problem, I just like using computers to solve problems.

Re: I used o3 to profile myself from my saved Pocket links

#195
post #192

Earlier quoted context omitted.

> How do you trust the recipe without context? Well, I just read it. The stakes are not that high! > have you ever gotten a recipe exactly as you outlined — zero context – and gave a damn to make it? Of course: there are a great many useful cookbooks written exactly this way.

The book is the context! It was published, it has a presumably influential vetted author. Maybe I am coming off too flippant. I'm just trying to say there's a spectrum between fluff and context. If the AI's literally just gave us answers and list of recipes, it wouldn't be as useful as with the context backing up where it came from, why this list, and so on.

Well, that's a reasonable point!

Perhaps it also depends on one's approach to cooking. I often read recipes not because I intend to follow them, but to understand the range of variation in the dish before I make my own version. "Somebody liked this enough to bother writing it up" is enough context for that use.

Re: I used o3 to profile myself from my saved Pocket links

#196

Earlier quoted context omitted.

> Are they, or instead they will help keeping you in your comfort cage? I’ve been paying close attention to what YouTube shorts/tiktok do. They don’t just show you the same genre or topic or even set of topics. They are constantly in an explore-exploit pattern. Constantly trying to figure out the next thing that’ll keep your attention, show you a bunch of that content, then on to the next thing. Each interest cluster…

But you're describing the engagement cage, while I'm just pointing that you need to be careful not to escape from it just to get trapped inside the comfort cage.

Is there a rigorous definition of "engagement cage" or is the term just HN-tuned engagement bait? (:

Fundamentally content discovery is always an explore-exploit loop. What you tune the loop with is what makes it useful for any given purpose.

Re: I used o3 to profile myself from my saved Pocket links

#197

Earlier quoted context omitted.

This can give a false sense of what Google (Alphabet) actually knows about you. That above is Google playing the game of 'ok, here is what we know of your activities on youtube when logged in!' But Google and the rest of the "advertising" (euphemism for surveillance) industry track and create "profiles" based on a basket of data points, from ip/MAC address to the rest of their bag of tricks.

Internally at Google a toy tool to peek into your own personal advertisement profile was released and taken down within a week or two because it was creepy knowledgeable about you.

when?

Re: I used o3 to profile myself from my saved Pocket links

#198

oh shit! didn't know they were shutting down i hope i can still export my data wtfff. i do not understand why companies stop offering products that people use and love.

hurry! It's gone in October: https://pocket.archivebox.io

Re: I used o3 to profile myself from my saved Pocket links

#199
post #41

I recently migrated to Linkwarden [0] from Pocket, and have been fairly happy with the decision. I haven't tried Wallabag, which is mentioned in the article. Linkwarden is open source and self-hostable. I wrote a python package [1] to ease the migration of Pocket exports to Linkwarden. [0] https://linkwarden.app/ [1] https://github.com/fmhall/pocket2linkwarden

+1 for this one, Linkwarden is great!

Re: I used o3 to profile myself from my saved Pocket links

#200
If you're trying to get your data out of Pocket be aware their export doesn't include your tags, highlights, or the actual saved article content.

If you want everything including the text archives from sites that have gone down, you need to use an external tool like this one I built: https://pocket.archivebox.io

Post reply on HN