fakwandi_priv

Then that check accounts history and tell me if you see a pattern or not, this one is really obvious.

Because both are bots, to prevent other people from wasting their precious mental energy on reading text which may or may not contain useful information but certainly are verbose.

Edit: downvoting them now can also help prevent future astroturfing which these accounts are made for, at least I hope.

I tried to integrate conductor in a project I’m working on but when starting a workflow the idempotency key was ignored, so sending the same key twice started two workflows with different id’s. I found that pretty strange but after prodding claude and linking it the github project it decided to look through the code and apparently that request param disappears somewhere in the plumbing. Somewhat surprised the article doesn’t mention it. This was the self-hosted version, the cloud version might be fine.

I switched over to Temporal, and so far pretty happy about it.

I recently started playing Expedition 33 and was impressed right away by the quality just in the first 10 minutes, hours later and the game just gets better.

I count 32 people on their team photo + the dog, and even this seems like a somewhat sizable number of people to manage. When I see news of these lay-offs it’s terrible for those people but at the end of the day I feel like those companies never should have reached those numbers. I fear for Larian

Most of this thread seems neutral/skeptical with just that post being obvious. On the other hand the volume of jev threads we have been seeing these past 2 weeks..

I’m a bit saddened this thread has so little activity, 55 comments as of posting, here even though there are half a million people watching the spacex stream. Just watching the launch, the amount of technology and people involved is incredible.

Prompting claude 5.5 has more appeal it seems.

> There is no additional fee for using prompt caching. Input tokens, whether served from the cache or processed fresh, are billed at the standard input token rate for the respective model.

So what he’s saying is correct, there is no separate cache pricing, which by normal standards should be 10% of the cost, which can become exceedingly expensive for anything other than single turn. The way they are stating this is of course strange..

I’ve also noticed this twice now in the autogenerated chat title, recent example: “Explore book locking liveewer”.

Googling it returns no matches but I think it was supposed to be “live viewer”?

What’s wrong with wiki.gg?

I have noticed the same thing starting with 5.6 when editing my last prompt inside the vscode codex plugin, I’ve seen the model’s thinking respond to the edit with a remark.

Slightly bummed out about it because in the past you could try different situations during a planning session and it wouldn’t pollute the cache but now it does. I’m not sure if forking the conversation has the same problem.

> According to Windows Latest, the high memory consumption is due to the fact that Weather is not a fully native Windows application. Instead, it is essentially an MSN Weather web app built on Microsoft's WebView2 framework.

I wonder how this approach is having such an high reduction in memory usage compared to what’s stated in the article. I would assume both use the exact same WebView here.

The only explanation here that I can think of would be that the “Add an application” starts it under an existing Edge process which shares it’s memory instead of completely isolated.

> - Math completely fails in longer contexts

Not sure what longer contexts we're talking about but didn't we have an old math problem optimized, which even the LLM itself was surprised about, just a week ago? Something which wasn't possible 6 months ago.

When I'm reading reviews of plans created by an agent especially on security boundaries it's suggesting huge matrixes to test even the very obscure situations, but then I'm also reading things like this and I just don't understand. Are we even using the same tools?

You're guesses are getting somewhat closer each time, almost there.