xur17 · HackerLangs

Which limit? Weekly or 5 hour?

I've been using it with hermes and some coding (with opencode), and I am getting a LOT more than one feature out of it, but the work is spread throughout the week.

xur17

昨日議論

Looks like I have access to gpt-5.6-terra and luna. How does one decide between gpt-5.5 and gpt-5.6-terra? Pricing is similar, but it's hard to tell if it's better..

xur17

昨日議論

I personally use opencode so I can swap between models and try different options. I'd say I prefer claude (fable and opus 4.8) so far, but curious to see where gpt 5.6 lands.

For personal stuff, I've been pretty happy with chatgpt's $20 plan. I believe it has considerably higher limits than claude's $20 plan, and it's enough for the personal stuff I play with (hermes, and some small coding stuff). Also allows me to keep up to date on openai models.

xur17

3 日前議論

[dead]

xur17

9 日前議論

And debit / credit cards are horrible for privacy (name and address info is sent along with payments).

xur17

9 日前議論

Agreed. To me this feels like the perfect solution for websites and ai crawlers. Instead of having crawlers paying proxy services and captcha solvers, they can pay the website itself. As a web scraper, I'd happily pay the website provider to get access if it meant easy access to the content. Heck, as a human, I'd pay to avoid the dumb captchas.

xur17

23 日前議論

Android does this fairly well for me - it will list out the options as they are spoken, and you can click on them directly to type the number. I believe (but haven't seen this recently) it will pre-render the options before they are read if it has knowledge of that phone tree.

xur17

24 日前議論

Speed and scriptability

xur17

2 か月前議論

I feel like the general consensus on most of the recent layoffs were that they severance was pretty generous. If it seems to be working okay, why do we need to introduce additional inefficiencies to get something we already have?

xur17

2 か月前議論

Maybe, but I have heard the exact same experience from my Dad and others that have worked with unions. It unfortunately seems to attract people trying to take advantage of the system. Personally if I were offered similar jobs, one with a union, one without, I'd take the one without.

xur17

2 か月前議論

Gemini thinks my name is my brother in law's name, and despite explicitly telling it that's not my name + digging through the settings, it still amusingly calls me the wrong name.

xur17

3 か月前議論

Even in those cases I'd prefer to just be able to natively search the content that has been lazy loaded. I've run into more than one website where the search functionality they bound to control-f is horrible.

xur17

3 か月前議論

Any idea way "5x or 20x more usage" means?

xur17

3 か月前議論

Don't you still have to worry about big bills since bunny bills based on usage?

xur17

3 か月前議論

Thank you! Just realized someone else recommended this a hour ago as well, oops.

xur17

3 か月前議論

Thanks for building this!

Feature request: I'd love to be able to share a search results page with a friend. If you update the url to include the location or zip code I am searching for (ex: https://www.govauctions.app/feed/12345) this would be possible.

xur17

5 か月前議論

I am hunting for houses - I've used it as an assistant that catalogs them (but it has this stored in multiple places and will give me the wrong list a lot). I also had it read through my emails and create a doc with my upcoming trips.

I'd say it's right on the edge of being useful, but given the number of bugs, it's not really that practically useful. It's moreso a glimpse into the future.

xur17

5 か月前議論

I have it installed in a VM, and overall it's fairly useful, but very buggy. Right now I can send it a message asking it something, and it won't answer. I typically have to follow up 2 or 3 times before I get an actual response. This weirdly used to work fine.

xur17

6 か月前議論

More broadly, I'd say if you don't have something to retire to (kids or otherwise), don't.

xur17

6 か月前議論

I've found this to be the case as well. My typical workflow is:

1. Have the ai come up with an implementation plan based on my requirements

2. Iterate on the implementation plan / tweak as needed, and write it to a markdown file

3. Have it implement the above plan based on the markdown file.

On projects where we split up the task into well defined, smaller tickets, this works pretty well. For larger stuff that is less well defined, I do feel like it's less efficient, but to be fair, I am also less efficient when building this stuff myself. For both humans and robots, smaller, well defined tickets are better for both development and code review.

コメント