For context, for an agent we're working on, we're using 5-mini, which is $2/1m tokens. This is $0.30/1m tokens. And it's Opus 4.6 level - this can't be real.

I am uncomfortable about sending user data which may contain PII to their servers in China so I won't be using this as appealing as it sounds. I need this to come to a US-hosted environment at an equivalent price.

Hosting this on my own + renting GPUs is much more expensive than DeepSeek's quoted price, so not an option.

I love the landing page - ugh just so perfect for the HN audience. I am pretty happy with the dock but after reading your landing, I felt like I need it.

Also, don't listen to people about pricing. $10/year as you have it is already cheap considering I'll end up using it every day (if I like it). People will never be satisfied.

This new tool I made works pretty well and I wanted to share it. Just give it your LinkedIn username. It pulls your career history and in about 2 seconds, it'll notice patterns in your career story and tell you things about yourself that are weirdly specific — your blind spots, what's driving your decisions, stuff you've probably felt but never had anyone put into words.

A big unlock I had (and why I built this) was that your career trajectory says SO MUCH about you as a person. Not your job titles, but the pattern of decisions. When you moved, when you stayed, what you kept going back to. That trail is basically a personality fingerprint.

The AI is pulling threads together across a full career history in a way that would take a coach hours to piece together. I think there's something genuinely powerful about having enough context (a full career arc) combined with enough research (our trait model) to say things that are helpful -- like you sat down with a real career strategist who gave you some cold, hard career therapy.

You can also check out our trait model through our main personality test - it's grounded in occupational psychology and psychometric research - it's kinda like the Big Five, Myers-Briggs, etc.

This tool only works on public LinkedIn profiles, and sometimes it infers too much and gets things wrong — especially when someone's LinkedIn is really sparse or outdated. But it'll give you goosebumps if it gets you right.

No LinkedIn sign up/permissions required (just your profile username), free for now (AI costs are not trivial but will cover costs up unless in the unlikely event a lot of people do it and my limits are hit).

Would love feedback on what you think :-)

Comments URL: https://news.ycombinator.com/item?id=47491774

Points: 3

# Comments: 0

This tool is pretty insane. Just give it your LinkedIn username. It pulls your career history and in about 2 seconds, it'll notice patterns in your career story and tell you things about yourself that are weirdly specific — your blind spots, what's driving your decisions, stuff you've probably felt but never had anyone put into words.

A big unlock I had (and why I built this) was that your career trajectory says SO MUCH about you as a person. Not your job titles, but the pattern of decisions. When you moved, when you stayed, what you kept going back to. That trail is basically a personality fingerprint.

The AI is pulling threads together across a full career history in a way that would take a coach hours to piece together. I think there's something genuinely powerful about having enough context (a full career arc) combined with enough research (our trait model) to say things that feel almost too specific. You can check out our trait model through our main personality test - it's grounded in occupational psychology and psychometric research - it's kinda like the Big Five, Myers-Briggs, etc.

This tool only works on public LinkedIn profiles, and sometimes it infers too much and gets things wrong — especially when someone's LinkedIn is really sparse or outdated. But it'll give you goosebumps if it gets you right.

Would love feedback on when it misses and why.

No LinkedIn sign up/permissions required (just your profile username), free for now (AI costs are not trivial but will cover costs up unless in the unlikely event a lot of people do it and my limits are hit).

Check it out at: coached.com/deep-read

Comments URL: https://news.ycombinator.com/item?id=47488699

Points: 2

# Comments: 1

But I am still surprised it's at $100mm ARR. I had thought the company had died after their initial hyped launch and didn't see anyone talking about or using the company at all since then...and we play around with a lot of AI tools. I wonder who their customers are.

Totally agree - the mobile experience need a ton of work, I'll try to figure out a better UX.

When AI came along, I started asking it to explain what I was looking at - and I learned a ton. I couldn't stop using this combo.

So I built Streetwhip. It's kinda like reverse Geoguessr - instead of guessing where you are, you get educated about places as if you had a smart local guide with you.

What used to be just "some random street in Buenos Aires" becomes a rich learning adventure about Argentine architecture, why things look the way you are, and stuff about the history and way of life.

I've been having so much fun with it. I LOVE when I'm on an ordinary looking street and suddenly I find out there's a WILD historic story behind why the architecture is a certain way.

A couple of tips: - make sure you log in! If you don't, things aren't really real-time (I had to do this because Street View's API costs can get expensive and this is just a fun hobby project for me). - play around with the categories - they're fun. I'm curating in more places over time. - the search is not perfect - when it works its magical (totally llm-driven). But sometimes it isn't. - don't use this on mobile, it kinda sucks

Would love to get your thoughts on the concept and what you could see it turn into! :)

P.S. Oh and one of my favorite features: radio! You get a live radio from a stream in the country (please mute it if you get annoyed - but I promise you it makes things a whole lot more immersive)

Comments URL: https://news.ycombinator.com/item?id=43849266

Points: 8

# Comments: 8

Comments URL: https://news.ycombinator.com/item?id=43136488

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=42469657

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=42145802

Points: 3

# Comments: 0

"I can only ask my employee 20 smart things this week for $20?! And they get dumber (gpt-4o) after that? Not worth it!"

1. No-one’s going to go out of their way to guide you. Esp at smaller companies, the fact that you’ve been hired means you’re joining a time-poor company, and there likely won’t be a formal onboarding process. So...you’ve got to onboard yourself.

2. Adopt a mindset of personal responsibility. This isn’t going to be a passive process, but an active one.

3. Don't meet everyone for the sake of it. The goal isn't to set-up endless meetings and become a burden. Limit yourself to a few, and make the most out of them. Make your ask clear when you ask someone for their time — e.g. 'I'd like context on X and what's been done so far'

4. Get some small wins on the scoreboard. Although your priority is to learn the key skills of the job, you also want to make a great impression during your first 60 days by showing you’ve made an impact. To do that, identify some smaller projects you can knock out to get a few small wins under your belt.

5. Be ‘seen’. Make your presence known. And communicate upwards so people know you’re busy. How? Tell your manager, “Can I send you a list of 5 things I think I need to hit the ground running? I’ll then set up a 1-1 and we could go through that.”

the full essay's here [2] (and plug: the newsletter I write is called Coached. If occasional career strategy is your thing, feel free to check it out)

[1] https://coached.com

[2] https://careersupplement.beehiiv.com/p/cs233-onboarding-hard...

I’m also a user of your other Chrome app you developed (Intention) [1] - I’d recommend people try that out too (simple free app for productivity), it’s also so good.

Good luck with the launch!

[1] https://chrome.google.com/webstore/detail/intention-stop-min...

I'd also really love your feedback on what this could evolve into (if anything!). This is just an initial version. Right now I curated links and distilled the core ideas on this page. But going forward, I'd love to have some more original content (e.g. interviewing people and sharing their advice in small nuggets).