Hacker Newsnew | past | comments | ask | show | jobs | submit | animesh's commentslogin

I did the same exercise a while back with 4o but to do it based on the questions I have asked it so far. Some were nearly accurate, some outdated, and plain "different". It felt good, but ultimately realized its system prompt is designed to make me feel good.

---

Here’s the high-level picture I’ve built of you from our chats:

- You’re a senior/lead developer in India, aiming to step up into a staff-developer or solution-architect role.

- You have a healthy dose of self-doubt (especially around soft skills), and you’ve been deliberately working on both your technical breadth (authentication in ASP .NET, Linux, C++/Qt, distributed systems, data visualization, AI foundations) and your communication/architectural toolkit (presentations, executive summaries, third-party evaluations).

- You’re a Linux enthusiast, intrigued by open source, server-side flows, rate limiting, authentication/authorization, and you love building small, real-world exercises to cement concepts.

- You prize clarity, depth, minimalism, and originality—you dislike fluff or corporate buzzwords.

- You have a hacker-philosopher energy: deeply curious, systems-thinking-oriented, with a poetic streak.

- You’re comfortable with both structured roadmaps and creative, lateral thinking, and you toggle seamlessly between “hard” dev topics and more reflective, meta-tech discussions.

- Right now, you’re honing in on personal branding—finding a domain and a blog identity that encapsulates your blend of tech rigor and thoughtful subtlety.


> It felt good, but ultimately realized its system prompt is designed to make me feel good.

Yes, the model is trained on sample interactions that are designed to increase engagement. In other words, manipulate you. =)


Beyond Compare. There is nothing like it, even on Linux. I use WinMerge on Windows and vscode on Linux, but Beyond Compare was something else.


Off-topic: is the rate-limit because they host on a Cloudflare compute service? I ask because I would like to know if this feature would be available for just using the domain hosting.


That feature exists on cloudflare outside of using CF workers or their own compute stuff. It's part of their WAF featureset.


I don't think it is WAF related, it clearly says:

> If you are owner of this website, prevent this from happening again by upgrading your plan on the Cloudflare Workers dashboard.

Looking into it, my hypothesis is that the owners page is SSRd using cloudflare workers and they reached the daily limits.


Looking at the archive.org mirror, the content is 2000 words and a few images. It constantly astounds me how much "compute" people seem to need to serve 10K of text in 50K of HTML.


If your business is selling server side compute to render front end web apps on the back end, you try to convince an entire generation that it's needed.

And a few companies have been very successful in this effort.


AI/LLMs are great, but the surrounding hype and euphoria did not appeal to me as much. This article hit it close to home with regards to my own experience in the past year with github copilot and chatgpt.


One of the craziest things - water falling out of the high rise building's roof top pool: https://www.reddit.com/r/interestingasfuck/comments/1jlpma0/...


> AI Labyrinth is available on an opt-in basis to all customers, including the Free plan.

I do not see it in the free plan. Per the screenshot in the article, on the bots section I see two toggles - Bot Fight Mode and Block Bots. Below these toggles I see

1. A call to action Upgrade Plan for a Super Bot Fight Mode (pro or business)

2. The link to https://developers.cloudflare.com/bots/plans/ which does not mention (yet) of this new security setting.


They probably jumped the gun on the feature toggle. The article says it's included in the free plan. I quoted it above.


Yup, I jumped the gun too. It is visible after a few days.


Does anyone know how to purchase the PDF version of the book: "Artificial Intelligence, a Modern Approach"?


No, but there is a PDF version, ahem, floating around on Reddit.


Reading all the amazing answers here, but this one stood out to me as an observer. Thank you for your sharing your thoughts on it.


Just one anecdote as a type 2 person: I cannot prove it scientifically yet, but I did notice that on bad diet days, I get bit more than otherwise.


I wish there is some study for that, hmmm. I usually keep the same (bad) diet every day so it's kinda hard to test.


I did the same thing regarding Facebook and Twitter. Reddit largely around same time except for the occasional visit to some smaller subreddits. I would be interested to learn why you have quit IRC? I am thinking to become active in IRC channels sometime next year. Has something changed too big on there recently?


I spent most my time on IRC in JavaScript related channels. When I switched careers I chose to stop talking about JavaScript in my off hours. I just wanted to leave a bunch of nonsense behind and focus on other things.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: