[overbytecode]

That’s a bit ridiculous, no one is forcing you to interact with his work. I find his articles to be informative source on the practical aspects of LLMs. And clearly other people agree. This is a very meaningless resentment to harbor.

[rvz]

I would like to see other takes for once in a while on HN instead of one source always reaching the top repeatedly almost every week.

With that being said, it tells you that the HN algorithm is either broken, gamed or both.

[Philpax]

I wouldn't mind diversity, but in this particular case, Simon has been consistently documenting, exploring, and commenting upon AI advancements. As far as I can tell, nobody has attempted to keep up with his pace, aside from maybe Zvi, whose writings are much less compatible with the HN audience at large.

That is to say, I don't think this is a consumption issue - it's a production issue.

[minimaxir]

Personally I've been wanting to blog more about new AI trends but at the rate AI trends are evolving it's unexpectedly hard to keep up while also having a full-time job while still maintaining good writing quality. The few blog posts I've written about this year have only because there has been significant overlap with my work for my full-time job.

Also, with social media becoming increasingly broken, the distribution of non-hype AI blog posts is entirely dead outside of the coin flip of getting the post to the top of Hacker News, which is less rewarding. It's a chicken-and-egg problem.

[scarface_74]

Well do you have something more interesting to say on a blog somewhere?

[rvz]

Well you’re really going to love this expert blog post series on the flaws of MCPs and how they are exactly exploited. (I’m not the author) [0]

But as always in times of lots of hype, this get no attention and no-one cares.

[0] https://www.tramlines.io/blog

[simonw]

Those all appear to be thinly disguised sales pitches for their Tramlines product.

They also look to be selling the kind of filtering/guardrails solution that I argue in my talk doesn't actually work. (Update: that's a little unfair, I had a look and a bunch of their rules are at least deterministic, like making sure DELETE isn't present in a call made to a database MCP.)

If you're looking for credible sources on MCP and prompt security that aren't my blog, I strongly recommend https://embracethered.com/blog/

[seanhunter]

That’s just blogvertising. The fact that you think that’s an expert take harms your credibility.