[darepublic]

These days it feels like there is a ton of pro anthropic astroturfing on this site. Probably it is mostly genuine enthusiasm from sincere people. But nevertheless there are a ton of articles from or about anthropic and within the comments of these you are sure to find, often at the top, someone staunchly defending the superiority of engineering everything via agentic use of the in fashion Claude model. If they are truly right than I don't see the need for proselytizing like they do. The proof is in the pudding. That is, if your choices are truly the best and fastest way to produce software inevitably the market and industry will reflect this. But it feels like they don't want to let results speak for themselves they need to hype up their claims continually and forcibly shove this down people's throats

[codexon]

I think some of it might be genuine. For people that don't code (like management), going from 0 to being able to create a landing page that looks like it came from a big corporation is a miracle.

They are not able to comprehend that for anything more complicated than that, the code might compile, but the logical errors and failure to implement the specs start piling up.

[chamomeal]

I’ve also been a little suspicious of the vote counts these days. Pro AI stuff regular hitting like 800 votes. The codex announcement hit like 1500? Like what’s goin on here

[andai]

If you check the OpenClaw discord, a common sentiment there is "it works but only if you use Opus." That seems to be the actual situation now.

Grok 4 Fast told me its own internal system prompt has rules against autonomous operation, so that might have something to do with it. I am having decent results with it though.

[andai]

Edit: My bad. I investigated and... while I do think Grok does have a hidden system prompt on the API, in this case, the part about self-replication and autonomy was on OpenClaw's side!

I've noticed Claude shutting down conversations on the same subject. It says "you may continue this conversation with an older model." ChatGPT also got extremely uncomfortable talking about it, and refuses to build anything in that direction, which I find amusing since its ancestor GPT-4 built a self-modifying Python programmer in 2023.

(Also, OpenClaw meets GPT-5's definition for "extremely dangerous AI software" due to the self-modification factor. But I think that applies trivially to any agent, so...)