ryanschaefer

Are you the author of this page?

The market *hates* this one weird trick to juice earnings

This was a satirical comment about this:

https://x.com/trq212/status/2014051501786931427

Guess I have to throw it in here… “/s” on my original comment

Please be respectful. I find it incredibly dismissive that you would use such language to describe such amazing individuals. They revolutionized the industry. They built a game engine to render text for cripes sake! So please get it right.

Huff. They huff their own farts.

I had written a whole pull request by hand, and then Adam rejected it. But he said, “Actually, you should use clide for this.”

Interesting

Had a similar comment but what’s even weirder and I seemed to have missed entirely at first glance is that this is an AI news aggregator agent?

The article is “by MLQ Agent.”

I mean… should you be able to? It looks like this is just an AI summarizing a bunch of other paywalled sources. It’s “by MLQ Agent”

What makes you assert that?

It’s funny how many times the same thing happens at each large company. I think people’s thought process is this:

Oh wow! If I paid for this myself I would have spent a lot of money! Are other people spending as much as me? I’m going to create a leaderboard!

Oh no, my misinformed manager is using the leaderboard as a slight of hand for work. I need to game this now.

Then the leaderboard is banned… I can’t see how this ever really goes up the chain beyond director.

Wasn’t this already reported on? FWIW this article links to primary sources from early last month https://www.theinformation.com/articles/tokenminimizing-meta...

If Michael Lewis is to be believed making Gemini whole was his largest mistake.

According to a Wall Street Journal (WSJ) report, the technique in question was tested by researchers at Amazon,

Why not link that? Is this a dupe?

Found the primary source:

https://www.wsj.com/tech/ai/amazon-ceos-talks-with-u-s-offic...

Members can request a division of the assembly (a rising vote, where each sides rise in turn to be counted)

Isn’t this the important bit? IIRC this can be demanded by anyone. If it passes by a voice vote, assume your representative voted yay or abstain.

“First time”

The graph seems like it only goes back to April 27 and on that day it was 57% bot…

A strange issue I’ve found is careless use of AI at my job has lead to many people rolling their own incomplete mini parsers. Think YAML parsers of a frontmatter that expects either `key: value` exactly or treats `item1, item2, …` as a list.

It’s a litmus test I use to see if someone actually glanced over what the AI generated.

The problem is using AI to “push” the answer to an asker. Unless the company has hidden docs they use for support (which why would that ever benefit them), I could get just as good of an answer if I point my LLM at your docs (“pull” an answer). In fact, the response might be better because I have context set up to tune it to my understanding.

Instead, you (company / support agent) have decided that I should instead have a conversation with an LLM through a worse, more opaque harness to the detriment of all of us.

It’s the fat introduced by the process that annoys me the most. The user of the LLM had an idea, but it got greased up and packaged into something that the average person would create, not a specialist in the domain. It dumbs down everything into a single perspective / way of presenting a topic.

The oversized emdashes are chefs kiss

Entirely accurate, but what an absolute waste of resources across the board.

In really large codebases grep and find timeout. If you operate at that scale you quickly come to realize Claude will not use the tools you built to make searching feasible.

It’s a watershed moment. Basically one of the most controlled applications of an LLM into a robust codebase without regard for the implications of doing so.

Anthropic needed something like this and it must proceed flawlessly. My guess is that nothing will explicitly break. But that’s the difficulty of LLM generated code: nothing breaks. You sit with a codebase that swallows all errors and appears to be working. Silently failing makes debugging performance and behavior much harder.

Is this your post? We don't fall asleep as easily for Write.as subscribers.

I think one of the things I had forgotten about but sheds some more light in my mind about how this was done is that anthropic bought bun.

The change of tone with the author in the capabilities of Claude. The strategy of merging everything at once instead of a more slow, careful cutover. The “single” author story that every company loves to put forth.

many devs would prefer convenience and tradition

This is too reductive of the situation.

If it ain’t broke don’t fix it. Except, in this case, unless you have someone tell you it’s broken you won’t even know you need to fix it.

And this is where asymmetry comes in to play. Attackers are free to test and break as much as they want as long as they are silent. Whereas maintainers don’t know if the fix an LLM proposes will actually address the issue or cause some regression elsewhere.

IMO, if Microsoft wants actually good PR around GitHub for once they would offer free LLM security audits on all actions for at least the X most popular repos…

https://noyaml.com

But that afternoon, fueled by curiosity and frustration, I felt a switch flip in my brain, and I dived head-first into a rabbit hole with no turning back.

https://xkcd.com/356/

It happens to all of us. However, I think it’s much easier nowadays with LLMs for something productive like this to come out of it. I can notice something wrong and triage or even fix it before the point where I’d normally start to feel the subconscious pull of opportunity cost telling me to stop.

We’ve taken it *outside* the environment

Are we even at the stage where we can encode any best practices into such a certification…?

What?