dbbk

To boil it down I think it's basically one 'orchestrator' chat, so you don't manage multiple chats, and it proactively reaches out to you to update you on how your other chats are going. In the presentation they mentioned a "Chief of Staff".

It's not intended for coding.

No, they are right. This is basically just GOV.uk for America, and GOV.uk by all accounts is an incredible success.

It could have been worse, the Dots name was originally "o" and the introduction videos they have put out have been clearly dubbed over

Using advisors doesn't break anything

Hence why it is no longer dangerous, yes

Alternatively you could just use plan mode

There is a point, plan mode has harness level behaviour - it's restricted to readonly tools, and it re-reads its plan into context after compaction

I use Claude's Plan mode daily and it's great. I almost always have feedback to refine the plan and I want a clean separation of planning time before writing code. I don't get what the problem is.

I also find this "kill Plan mode" push on Twitter odd, because developers have been complaining about AI supposedly killing their jobs, yet they want to take away the main feature that lets them be an active collaborator and participator in the process. Weird.

Yes

Now this just makes me sad that Apple gave up on the lighter Vision Pro. I might actually use this... if it had a real OS

Not many people know this but OpenAI even has a FREE separate moderation model and API endpoint that can classify user generated content.

If you're happy with letting Meta train on you, Muse Spark 1.3 Contributor pricing is a much better deal than Luna

This makes Fable not really make any sense?

Sounds like you want a product manager

How is it not relevant? It's not like they randomly picked the place, it's their office

You... know they work there right?

Slop

No I do other things. Oftentimes I'll just do it from my phone when I'm out and about and just work with it asynchronously.

It's almost as if there is a blog post that explains what's different

Perhaps I'm just "stuck in the past" but I do not understand the appeal of working like this. Your app is being built on architectural quicksand.

I just work on one thing at a time, always with Plan mode upfront, and I'd say most of the time I have some feedback to refine the plan. Working good so far.

It's Postgres search any coding agent can switch you to something else in 5 minutes

Why would you need super fast search for local testing?

So?

I am a technical user and I literally last week was trying to work out what the difference between ChatGPT Chat and Work was and couldn't figure it out (other than they bill you differently)

I have a question about project memory. Last time I tried using Claude to organise my chats into Projects, it turned them into isolated silos. I asked a different chat to refer to what we'd discussed in the other chat, and it said it wasn't allowed to access it.

This was pretty frustrating. By trying to organise my chats, I actively made them worse. ChatGPT at least gives you the option to have either open or closed memory. Is this being considered?

When they say "can't hallucinate" they mean they produce a confidence value for every result, so you could see for example it has 0.1 confidence, and you can disregard the result - that'd be different from hallucinating where it believes it's correct

At least AA have a dedicated speech model index, of which this is now the leader: https://artificialanalysis.ai/speech-to-speech

Uh, what? This is SOTA for a live model. What are you talking about?

The year is 2026 and "Siri mark my medication as taken" returns "I'm sorry I can't do that"

"A simple app" well there's your first mistake, it's not a simple app is it