80hd

Was about to complain about the pricing (more expensive than newly released 5.3 Codex?) but then I noticed that Auto/Composer mode appears to be billed separately now -- so I can use $400 of API in _addition_ to Auto/Composer?

Am I right in thinking that's a separate allowance? That's pretty cool if so

I mostly agree, almost everything is possible for almost everyone, but some people have hurdles to overcome that would probably take their entire life to overcome.

Having said that, some people choose that path anyway, and sometimes they actually end up mastering the field from the bottom up in a completely new way that no one else would ever think to do.

I say this on the off-chance someone reading this is one of those people. But yeah, I'm not gonna try grow from 5'7 to 6'4 or sprint faster than Usain Bolt. But more power to anyone who tries!

There's nothing wrong with being unhappy, IMO - you can still channel those emotions into something meaningful.

But if you do want to be happy, you can find stories, if you look hard and long enough, of "outliers". People who, against all odds, defied "statistics" and broke out of whatever expectations society and "facts" projected onto them.

I tried "everything" until age ~27 when I finally found one dial (very specific elimination diet) that made the rest of my body act mostly normally. Other changes were easier to make from that point onwards, altho there's a lot of damage to undo still. Diet is just one factor, for others it could be completely different.

My point is - I thought I would never be healthy. This stuff runs in my family too. But I just kept trying things. There's no other option.

You are a unique human being and soul who has something valuable to contribute to this world. Even if that's being unhappy.

Hope that doesn't sound condescending, it's something I tell myself too.

Insane velocity from the Cursor team. I wonder how they move so fast?

I wasn't expecting to, but I got chills listening to some Suno creations from artists who are clearly very talented at using this new medium.

Much like those of us hammering away at LLMs who eventually get incredible results through persistence, people are doing the same with these other AI tools, creating in an entirely new way.

I'm sure Suno are working hard on this and these AI tools can only come together as fast as we can figure out the UX for all this stuff, but I'm holding out for when I can guide the music with specific melodies using voice or midi.

For "conventional" musicians, we (or at least I) would love to have that level of control. Often we know exactly what it should sound like, but might not have session musicians or expensive VSTs (or patience) on hand to get exactly the sound we want. Currently we make do with what we have - but this tech could allow many to take their existing productions to the next level.

After using Ableton for years and previously Logic, I've never used music software that evolves as fast as Bitwig. The rate at which they improve it is pretty mind-blowing in comparison.

Not OP but my two cents - probably laziness and propensity towards daydreaming.

I have extreme intolerance to boredom. I can't do the same job twice. Some people don't care.

This pain has caused me to become incredibly effective with LLMs because I'm always looking for an easier way to do anything.

If you keep hammering away at a problem - i.e. how to code with LLMs - you tend to become dramatically better at other people who don't do that.

Character consistency is great without any upfront fine tuning, nice!

Seconding this. My work has had the same problem - by the time I've got things all hooked up, figured out the complicated stuff - my brain (and body) clock out and I have to drag myself through hell to get to 100%. Even with ADHD stimulant medication. It didn't make it emotionally easier, just _possible_ lol.

LLMs, particularly Claude 4 and now GPT-5 are fantastic at working through these todo lists of tiny details. Perfectionism + ADHD not a fun combo, but it's way more bearable. It will only get better.

We have a huge moat in front of us of ever-more interesting tasks as LLMs race to pick up the pieces. I've never been more excited about the future of tech

I've been asking myself this since AI started to become useful.

Most people would guess it threatens their identity. Sensitive intellectuals who found a way to feel safe by acquiring deep domain-specific expertise suddenly feel vulnerable.

In addition, a programmer's job, on the whole, has always been something like modelling the world in a predictable way so as to minimise surprise.

When things change at this rate/scale, it also goes against deep rooted feelings about the way things should work (they shouldn't change!)

Change forces all of us to continually adapt and to not rest on our laurels. Laziness is totally understandable, as is the resulting anger, but there's no running away from entropy :}

Story in the sense that we understand everything (perhaps even our most fundamental perceptions) through stories - events described over time with meaning/significance ascribed to particular things. There's a beginning, middle and end - in its most basic form.

If we model "situations" in AI in a similar way, my intuition tells me it would be similarly useful.

Putting this idea out there, haven't seen anyone implement it:

Use vector embeddings to represent each task as a story, an abstraction of 1. the past, 2. the present, 3. the future - on a kind of global "story map".

Each embedding would be generated by all available sense inputs at a point in time. The most useful embeddings alg will be able to combine sight, hearing, internal monologue, visual imagination etc into one point on a high-dimensional map.

At each time step, find the closest successful "memory" (based on embedding of 1+2+3) and do some LLM exploration to adapt the memory to the new, novel situation.

Attempt the new "story", and do something like A* to get closer to the desired "future", tweaking the story each time and plotting failed attempts on the embedding map.

Theory being that over time, the map will become populated with successful attempts and embedding will be able to abstract between similar situations based on 1+2+3.

I'm not the guy to implement it, and I imagine new models training with a "reasoning step" are doing a similar thing at training-time.