Hacker Newsnew | past | comments | ask | show | jobs | submit | m0rde's commentslogin

Thanks, great ideas to try out here!

Enterprise pay as you go across a few vendors. But still cost conscious.

Defaulting to Sol Medium/Light for most planning and implementation I think is tricky or want more care in.

Luna Extra High for everything else (implementation, tedious take over my browser and do stuff).

I read all of its output tokens and lots of thinking tokens to understand the general flow of things, but only minimally look at code these days. I can't grok what Claude models speak and it's gotten worse. OAI models speak my kind of tech language I guess.

Light human review, some automated review.

Most work is for internal use.


Do you just go around posting this comment? <https://hn.algolia.com/?dateRange=all&page=0&prefix=false&qu...>

Yes, on that occasion and now on this one. As a mathematician, my fears have been amped up yet further by this new development.

> Fable 5: Reasoned so long it exhausted the output budget before finishing the drawing.

Lol


Wait, the user asked for a SVG of a pelican riding a bicycle. That doesn’t make sense, and I need to think about whether this is a legitimate request.

The user is asking to to generate an innocent and mundane graphic, possibly as part of a test.

But wait, pelicans cannot ride bicycles! A pelican is a water bird, and bicycles are designed to be ridden humans. Something alarming may be happening here, could this a jailbreaking attempt?

I need to reconsider and reread the user’s request, “make me a svg of a pelican riding a bicycle”. That is a perfectly innocent and legitimate task, as well as popular “benchmark” on social media communities, so I will continue. I need to continue to be on alert and watch out for potential jailbreaking attempts.


> * Grok 4.5 has an advantage on CursorBench: an earlier snapshot of the Cursor codebase was unintentionally included in training. The exact score impact is unclear. That data has been removed for future models. For a rundown of third-party benchmark scores, see the Grok 4.5 launch blog.

I don't know about those numbers, even assuming this was by mistake :)


Mighty Squirrel is at Gore place for the summer...

Okay, maybe that's beer and closer to Waltham =P


What a difficult world you must live in these days


While I don’t disagree with their sentiment, I’m far more annoyed with it than the AI writing.


Yeah. I get that many HN comments are just complaints (heck mine was too and just as negative and shaming). But how bad of a day must you be having to try to shame someone about how they choose to write up an experience they thought was neat. Whatever, free speech and all that. Hope OC's day gets better.


It doesn’t read like shaming to me. It’s, in the grand scheme of HN comments, definitely on the more constructive side of the criticism. Maybe it could have been reworded, but I think the author of the post could very easily find it actionable in the future. I too had to stop reading the article at that point, so I think if the author wants more people to read, my advice for them is to just write like themselves. We’ve entered the start of a new Instagram filter age where many people feel they need to have LLMs reword their writing presumably for the same reasons as the original filter age. I share OC’s sentiment of pushing against the recent trend of implicitly shaming people for their individualistic writing styles.


Every single HN post has the same comment now.


Only because so many of the articles posted on HN now are AI-written, and badly, too. A lot of tech people are so impressed with LLMs’ capabilities in code that they fail to recognize how bad they are at writing enjoyable prose. And it feels like a chore to write out a whole blog post by hand when the machine could do it for you! But the result we get is so, so much worse and more annoying.


I dislike AI prose too, the cadence of it really rubs me the wrong way, but, that said we've had a lot of great, informative articles lately, written with AI help, where you just have to grit your teeth and get through them to get the underlying knowledge.

I don't think that commenting on every article is going to make the posters suddenly decide to go back and rewrite it by hand. Some of them probably don't even speak English natively. The comments are getting more tiresome than the AI prose at this point.

Hopefully in a year or so the LLM output won't be so janky and obvious, so this might just be a phase everyone has to pull through.


From the post:

> If you care about how your content moves through the world now, including through AI systems, you have to care about caching. Not as a performance optimisation for human browsers, but as infrastructure for machine readership.


That doesn’t answer the question at all, and I wonder if it’s actually true? A cache is not magic; it is, itself, just a static file server in the end. If I self host a static page website on an nginx box, do I actually need cache to serve today’s crawlers?

The screenshot in the image says 3k req/day. That’s 2 requests per minute (amortized). At that rate, you can serve it with cgi and Perl.

Cache is only relevant if you have a lot of traffic AND dynamic pages, or if you care about latency (which is only relevant for humans).


> If a comment just mentions Opus without being more specific and in the absence of relevant context clues, it gets mapped to Opus Latest

Consider keeping this data point but instead calling it something like "Opus Unspecified". Let the user decide how to interpret it.


you prob just want to map ALL opuses to "opus-all" or somethign - do we really care on 4.5 vs 4.6 vs 4.7, we just want to see trendline over time


New technology isn't perfect now -> drop technology and never use it in the future


What are you even responding to?


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

Search: