Have been giving GPT 6 Astra a genuinely good two days(mostly because I maxed out my ant sub)
first of all I don't remember Astra being this good to work with but on the other hand Astra was always hugely expensive so I guess I never gave it a real shot
now with banked resets and such working with it on High effort yeah this is awesome
secondly been working on how to display in-transcript images better and also how to have them show in a sidepane when in-transcript doesn't suffice but also on a canvas based on tldraw with all that gives
after 1 hour of ideation or such it produced a very nice concept off the bat
65
Replying to @mattzcarey @poteto
yeah was in the same camp and built it myself not even a week ago
nice!
25
Replying to @itssotsot
the way the ink behaves on the paper in fables case is a bit weird, the drop had to be huge for it to pool like that but given ratios it's volume doesn't make sense
also a rorshach is meant to be less specific in shape so they both failed. these shapes allow for no freedom of interpretation so the test doesn't even work :D
99
Replying to @TJeparskis
yeah It seems to do fine but I think in time it's oddities will show
I gave it a task to review a big chunk of work done by fable 5.2 and it found genuinely good things
also I've been using it on extra high and fast and it doesn't burn rates.
Don't think I need to continue using extra high but good ot know
76
well fable 5.2 with haiku 5.5 and sonnet 5.5 agents and if they fail as task it escalates it to the fable 5.2 orchestrator, I should have added
7
suuuuper rough and basically a first draft after brainstorming and ideation with Fable 5.2 high
after about 10 hours of work by fable 5.2 on medium this is the result. It captures almost everything we agreed on and I never really gave much in terms of the design but rather what I wanted and needed from this
Didn't know what to expect but this is actually usable, it's not pretty and it's buggy but it works. I could make an iphone app with this and test it on my phone, from my custom tooling.
this is every day things now but still this is nuts
1
1
20
Replying to @Gegam245074
this is a whole only you can get yourself out of
1 these are somewhat redundant but also not. You need to be more selective because a lot of this is now redundant but some things are not. At work we had to look at new features in a major release and turns out a new feature for how to parse json brought a major improvement to our etl process but most others did not. Saved us a good 30+ minutes
2 for me this is not the case, it remains about the same but has shifted to other areas. Without it I could not push back at agents but with it I can and it leads to avoiding stupid stuff but also saving on tokens.
3 this is the most difficult one, was for me anyways. I needed to build custom tooling to solve this. Now that it has come a long way it has increased my ability to handle multiple tasks much better. This is also very subjective though so not a one-size fit all thing. Unfortunately.
4 I see this as simply shifting from code and such to agents. Not only agents though, so maybe it is your version of ai psychosis
5 I used to be here, for a while, but all the other things I've brought up took me out of it. It's dangerous though and easy to get into. Gotta bring yourself out of it.
6 complete opposite for me. My creativity has exploded since all the above alleviated a lot of cognitive load and most of all time. I can now think of new things instead of having to think of current things. Goes back to point 4 and how it's now easier to keep track of many things.
I honestly don't know if any of this will help you but maybe it will, maybe it won't
good luck
humanity won't get stuck in a rut and stop developing though, just gotta get through this phase.
1
696
been meaning for the longest time to build support for creating iphone apps in my custom tooling but always had more important or fun things in line
now though I have a project for someone close to me that I wanna get going so it's time to put this feature at the top of the pile
one caveat, I don't have a mac I'm on windows but me and them use iphones.
once the phone actually got recognized on windows 10 it was very quick from there for fable 5.2 to actually get something going.
this is for it's internal use, just to see the fundamentals are in place before building anything or before even brainstorming what this should be and such but it took like 20 minutes from "it's recognized" to this showing up in the transcript
impressive actually
1
1
31
Replying to @emanueledpt
this is an improvement no doubt but when I tried this in my own tooling it ultimately just meant I still had no real idea what the agent wanted from me or it's current state.
I even tried wider and taller so it could fit more text but it just felt kind of forced into something that should be somewhere else
76
I'm starting a new project today - a multi-year quest to save my hand from being completely immobilised.
In 2019 i broke my left wrist 2 times within a month. First time happened after i crashed on a bicycle - which ended up in a surgery, metal plate and multiple bolts in my bones. A month later another accident made this bolts work as weak points, completely destroying the bones from the inside.
After my second surgery, the surgeon told me I bought around 15 years - after which the pain will become so unbearable I'll need to replace the bones with metal rods, removing all the mobility in my wrist.
So, my goal is to solve this problem within the next 7 years. The first phase of this project is to gather the data: i'm trying to get high quality 3d scans of every possible layer - soft and hard tissues in my wrist.
I've started with the 3D CT scan to map the bone structure. The website compares both of my wrists to make it easier to understand the current situation.
What I'm looking to do next:
• get more high quality scans (help me by recommending clinics/hospitals with good equipment)
• get more opinions and ideas (help me by sending this to orthopedic surgeons you know)
• get more knowledge on the topic (help me by pointing what exactly should i read/learn/watch on bioengineering).
not sure if this thing is even solvable, but we gotta try huh
wrist.kyzo.io
Replying to @ky__zo
good luck bro
unfortunately I can't help with the recommendations
subbed for your exposure
1
10
Replying to @pradeepXkapoor
hell yeah bro! I've got some juicy features and projects coming up so it would be awesome
1
1
17
Replying to @everolivares @tryAlanAI
yeah I figured this could be done and yeah it's much better
this still doesn't work for me personally but I have a very different workflow and needs for being able to focus compared to most, from what I've been able to gather on X at least
here is my custom tooling and it's still very much wip, there is too much going on that isn't necessary most of the time, but to give an idea of what is optimal for me
85
Replying to @JuliaScript
yep a lot of working with ai at work have been trying to figure out what can be done in advance and what is better left for later. Thankfully at work they've come around more now so there is less bureaucracy but it remains(and kind of the same) but everything else is different.
65
Replying to @SimonasLTU1
meanwhile I've been on medium since launch and have never had a day where it was stupid. Some back and forth at times sure but not stupid
1
1
11






