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

Because it’s in a page accessible from its search tool presumably https://claude.dev/blog/getting-the-most-out-of-opus-5-5/

Isn’t this post comparing zero shot Jev to fine tunes of this model for each of the datasets it is tested on? If so seems like fairly impressive results for Jev

Most valuable comment here. You can fine tune BERT to perform really well on classification tasks. What's exciting about Jev is that it generalizes. Laya does not!

My own thoughts on this, with examples https://github.com/nfcampos/loop-dev/blob/main/README.md


Are those your own thoughts? Or Claude's? I tried to read but had to stop a few paragraphs in because of Claude's annoying authorial voice.


No, they really are my thoughts, I've been doing this stuff pretty much every day for the past 6 months


No offense, but this sentiment is diluted by commits like this:

https://github.com/nfcampos/loop-dev/commit/e28b1fce0078e605...

I assume that GP was just saying that they would prefer to read these thoughts written by a human author (preferably you). I agree.


That's a perfect use case for an LLM: grammar-aware find and replace (spicy find and replace.)


That commit happens to be a find replace because i usually write for my company’s blog (we)


I would be more willing to believe you only used Claude for minor editing tasks if you disclosed your usage of Claude upfront.


This commit seems to mostly be grammar fixes? If someone used a spell/grammar checker it might produce a diff similar to this. Why does the fact it was Claude and not Microsoft Word or other matter in this case?


Because Microsoft Word doesn't write blog posts for you

Edit: I just realized that Microsoft Word probably does do that now, and I hate it.


Copilot is the new clippy meme. Copilot is hiding in every MS product and is ready to write an email for you, anytime.


Yes but that commit doesn't support the fact that it has written it for the user.


I think the same will be true of the ‘popular science’ category of nonfiction


For what it’s worth, I personally discovered something similar with another category of nonfiction books - economics and business. I read a lot of these circa 10-15 years ago and the rate of new signal id get from each new one eventually became low enough that I stopped reading in that category altogether.


He does mention audiobooks, see quoted below

> But what about ebooks and audio? Looking at all formats (print + ebook + audio) for the catalog in 2025, the second half of the year was down ~45% versus the first half.

This compares to 46% on print only


The title of the submission is an almost comical example of hn navel-gazing - of the many interesting things in the article surely the job prospects of hn readers should not be near the top of the list


Anthropic marketing (and even supposedly technical write ups) sadly has become more hyperbole and less substance over time imo. This technology is so impressive on its own, really feels like shootings themselves in the foot in the long run, but what do I know

Case in point here where they conveniently fail to report the false positive rate, while also saying that if it wasn’t for Address Sanitizer discarding all the false positives this system would have been next to useless


Right now, we accept false positives as long as you can sort them out. I think it's pretty typical that >99% of fuzzer runs don't result in new coverage. Of course they're far from useless without feedback but it's better to have it if you can. I guess the question is does the llm approach have lower costs for validation and triaging vs just fuzzing alone, unclear to me. Anthropic would like people to believe automation is this scary new unknown


But on the other hand the claude app is garbage… https://github.com/anthropics/claude-code/issues/22543 obviously native apps can be garbage too, but I must say electron apps have a surprisingly high incidence of terrible performance issues, unsure if it’s a correlation or causation issue


LangGraph implements a variant of the Pregel/BSP algorithm for orchestrating workflows with cycles (ie. not DAGs) and parallelism without data races. You can design your graph as a state machine if you so desire


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

Search: