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

Thank you for writing this.

This is gold

> Rule Number One: You may not use a single word an LLM suggests to you.

Over the last week-ish I turned around 2 product announcement blogposts within ~24hrs. Both written manually by someone who doesn't do product marketing for a living. It actually felt incredibly satisfying to focus and smash something out that was 100% human (despite praising the benefits of agentic systems, oh the irony).

My flow has been: Go for a walk, record all of the thoughts on the topic with speech to text, and have LLM organise my thoughts into what I call "facts" - simple sentences of fact, and point out open questions and inconsistencies ("you are a product marketing expert helping me organise the content for an upcoming feature announcement" ...).

After some back and forth of inconsistency bashing I have a large pile of short sentences in the vein of "Feature X is for Y because Z", that I use to manually build a narrative with headings, and then write the actual copy covering a subset of them.

I also agree that light style LLM edits are fine, and that I don't let LLM do anything other than ordering and filler words removal and provide structural comments.


> Go for a walk, record all of the thoughts on the topic with speech to text I have been doing this. I think better when I walk (so much so, even within the confines of my home, I walk when I have to think).

> organise my thoughts into what I call "facts" - simple sentences of fact, and point out open questions and inconsistencies Would appreciate little more details of how you do this.


I spent way too much time on this yesterday! Love it but it's super tricky. I'd love a (realistic) "cheat" that lets me see the departure boards without being at the station - that way you can plan the journey at least a little upfront. I'd do that on my phone anyway


I'm a solo dev founder working on Potniq (https://potniq.com) - a business travel tool that tells you exactly when to leave based on your entire itinerary.

I used to work in devrel, and traveled a lot for events, and I always struggled skipping things like workouts, looking at the time on the last day of a conference trying to check whether it's time to leave yet - so this gives me the opportunity to build a tool I would have loved to use.

Currently I'm working on a LLM-powered booking email parser, that ingests forwarded booking confirmations and adds flights, hotels, etc. to your itinerary.


https://potniq.com

It's a travel tool for business travelers that figures out your suggested departure times for your entire itinerary based on predicted traffic patterns. Think Flighty but for all the non-flight parts of your trip.

You first build a travel itinerary with your legs - flights, activities, hotels (and hotel returns) and it tells you things like "leave your hotel at 7:40am" before your 8:30 meeting - in a single itinerary, no need to do the google maps acrobatics for every two items in your itinerary. While it's aimed at frequent business travellers I personally use it for all family leisure travel and daily itineraries around town as well - "do I have time for lunch at home after my son's class or should we bring packed lunch". I built it as during my time working in developer relations I traveled a lot, and always built unnecessary buffers and kept nervously glancing at my watch or phone to see if my planned time to leave still holds.

Tech-wise, currently it's Remix web app with a NodeJS/Fastify backend and Supabase for storage, and relying on google maps for route duration calculations. I want to expand it to native mobile clients in the future as well.

I am using it as playground on product thinking, ruthless prioritisation based on user benefit, figuring out unit pricing and economics, sensible architectural design, and exploring how including AI-enhanced features here and there can help make the product better, not just include them for their own sake.


The TL;DR; is in the next few days, 1 hour session, going through the docs & guides, and giving your experience. Conducted over Zoom and recorded.

We can offer a $50 Amazon gift card as a thank you.

Happy to also answer any questions.


This is great, thank you for sharing.

I recently created this one to help with my particular GitHub workflow - instantly diff any commit with the current master branch: https://gist.github.com/zmarkan/503789d31acf385e44f13b0b3c3c...


Just the level of airplane nerdery one needs right now. Also probably the best explanation of EDIFACT artifacts I've seen.

I just have one remark - how on earth does a 737 fly from SFO to LHR without stopping as in the example?


Ha, great question. We didn't have access a SABRE system so the lookups are fake. I was just about to go in and change it in to a 388 (my favorite plane!), which I think flies daily between LHR and SFO as BA286.

~Unfortunately, the output is in png format which was generated by carbon.now.sh, so I'll have to type everything out. I'll change it once I have a few minutes...~

Edit: just changed it into BA286, which is an 388. (For fun, I also added in first class fare buckets, which United no longer offers.) For additional accuracy, I also updated the UA equipment to 772s, which IIRC is what they actually fly (as opposed to 77Ws).

(If we did this more often, we'd probably actually design it in HTML instead of using Carbon, but an image was much faster, haha.)


It doesn't. Or it has a technical stop.

The MAX has a range of 3850 nm, LHR-SFO is 4664 nm

So unless it's an empty ferry flight and you've got very favorable winds, you're not doing that without stopping.

Hawaiian needed extra tanks to ferry their 717 (or was it MD something) over there (there's a picture around IIRC)



That was around the time of the merger with McDonnell-Douglas. The 717 was actually the MD-95, so, you're basically correct either way. :)


I love the ASCII arty Clippy for tool tips!


Hey everyone, I'm Zan - the person being interviewed. Any questions about the survey, let me know :)


There are more ways to resolve this.

- Netflix shouldn't charge cards without verifying email addresses. Security should be an integral part of UX, and not subservient to it.

- Individual email address canonicalisation/resolve _could_ actually be a standard. I'm not sure whether it is or not, but if we can agree on emoji we could also maybe agree on something that binds the internet together. Email is infrastructure, Netflix is not.

- There is still a potential issue by having configured catch-all email addresses on some domains, but we should in that case optimise for the hundreds of millions of gmail.


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

Search: