You'll also go orange [0]
0: https://drink4good.com/can-drinking-too-much-carrot-juice-tu...
1,410 karma · joined September 8, 2011
CTO at Duel
https://www.duel.tech
https://www.linkedin.com/in/abovethewater
Author of Context Capsules
https://contextcapsules.com
https://contextcapsules.com/v2/CONTEXT_CAPSULES.md
0: https://drink4good.com/can-drinking-too-much-carrot-juice-tu...
So many launches don't show what they are. This on the other hand - got it straight away from the animation.
Great job
You building something else and this scratches an itch?
That aside. I actually love this. Anything that helps with the "wtf did you just do?".
If I can still learn I will. If an agent can't reason about the changes made, then they are not good changes.
Or use it through Vercel [0] with per call zdr.
https://vercel.com/changelog/typesafe-ai-jev-now-available-o...
The model isn't limited to concepts that can be expressed in natural language.
It's only once the AI gets to the output layers that natural language comes back into play.
After all, they're all made out of weights[0].
You price it at what you think works. There is no push back, so you make room to push the price higher.
You were happy to do it at the original price.
A twee handwritten sign for free range eggs at the roadside is likely to do well.
A handwritten sign for flying lessons on the other hand..
Couple that with mass unemployment in an incredibly vast, diverse population of individuals with individual moral boundaries willing to do whatever for money.
And then.. figured that you must be aware because it's been explored constantly in sci-fi for many, many years.
Let's hope for the culture at least.
1080p, but the picture far outstrips most other TVs I've owned to this day.
I have zero plans to change it, and it's usefulness has outlasted the Chromecast that's connected to it.
Yes, I put the first ads on Smart TVs. Apologies.
If there's more than enough grapes for everyone and one person takes more than their fair share, then, on the whole, it's fine. There's enough to go round.
If everyone tries to take more than their fair share, then the whole system falls apart.
When there are this many people, and this much visibility of the hustle, just seeing others prosper by cheating means a not insubstantial number of people will be in the "well I want grapes, and likely need to cheat to make sure I get my fair share" camp.
"A bug in our portal had the setting for training inverted. This means that when you expected us not to be training on your data, we actually were. We know this adversely impacts the trust our users invested in us, so as of today we are crediting all affected accounts with $200 to use on our latest models".
In a long session pulling data from all over the place it created a pretty PDF.
"create this as a google doc that can be commented on"
Done — the full v0.5 content is now a Google Doc in your Drive...
"Ah, the formatting has gone. Do it in google slides please"
The brand studio has a native Google Slides path for exactly this — building the deck now.
Google Slides created.
Then today:
Chat paused Edit and retry with Fable 5 Fable 5's safeguards flagged this message. This sometimes happens with safe, normal conversations. Continue with Opus 4.8, send feedback, or learn more.
Details: [reasoning_extraction]
Flagging the formatting promptThe vote should have been, should we entertain this idea?
If yes, a second referendum on what Leave actually means when it comes to the final decision point.
Y'know the same way that any remotely functioning democracy would approach something this large and nebulous.
Iceland being just the most recent example.
Instead the vote was "life carries on as is" vs "something changes", with no clarity of what that change is.
Given the state of the UK post austerity there is no surprise the vote for "I don't want more of this" was so high.
That's the incredible failing of the UK democratic process here, Cameron foremost.
The current analogy I am using when vibe coding is it's like defragging a hard drive in terms of time wasted.
Years of sitting there as the bar crept closer to 99 in the vain hope I could turn the computer off and go to bed, just to have to sit there for another hour or so until finished.
So many late nights wasted doing, I'm not sure what.
And now I'm sat there waiting for the agent to come back..
Running for 17m.. "dealing with a complex response"..
Codex (GPT5.6) has me hooked on that loop moreso as it is, in practice, so much quicker than Claude (Opus or Fable), so I don't quite ever walk away.
Nostalgia.
That's a truly dialled in experience based on many iterations and fine control of input factors.
That's the parallel I'm envisaging.
Robo pizza doesn't need to mean 30 second pizza.
Just a perfect pizza at the end of the process with no humans involved.
I see that as infinitely achievable.
I've had them every time I've started or stopped a *pine antidepressant.
Like, something rolls off the counter and my natural reaction would catch it.
Instead, my hand doesn't move, and a brain zap.
Physically painful.
There's no reason it won't improve because we know that there is actually a world in which amazing pizzas exist.
Teleporters seems a rather random comparison for the sibling reply
From experience this feels to me like a very NT thing to say (apologies if you're not NT, no context to determine either way) - it comes across as written: "Why can't you just do what I ask you".
Often it feels atypical people require a logical understanding from first principles of why something should be done.
Then, once they have that they need to come to the same conclusion of what the course of action is.
If they're aligned, awesome.
If not, then the work is to try to make them understand why, given the current constraints and cultural context, their optimal approach is suboptimal in this situation.
Something as simple as "yes your idea is great, it will work better then theirs, but sometimes others need to fail so that they can learn from their failure" - exact quote.
I'm speaking to a very limited subset here based on quite a bit of exposure in many contexts.
"Neuroatypical" shows up in many, many ways.
A different world.
Having to define what an agent can do when it identifies on my behalf is cumbersome, especially when you start to get specialised agents.
Pattern based would be too easy for AI to game, but there's got to be a service independent way to limit permissions based on role.
I am Jack's right ear - awesome you get to hear stuff.
I am jack's right hand - great you get to input stuff.
Ignored all the sage advice, lived a rather tumultuous life, but lived it fast.
Diagnosed ADHD at 45 was a bit of an aha moment!
So I'm stuck on the treadmill for quite a few years yet.
Envious of where you've ended up, but imagine the path there wasn't easy.
All the best with retirement!
Anything that compounds is better off started early.
It's not about the money at the high level, but relative comfort frees you up to be your best self.
Or so I'm told.
That still overkill?
I find it decently fast out the box and possible to manage as it grows.
It was British English.