There's nothing more dangerous than the person who shows up every single day even when the rewards are uncertain. The one who can tolerate the most uncertainty is the one who will eventually win.
Fable 5 is state-of-the-art on nearly all tested benchmarks, with exceptional performance in software engineering, knowledge work, scientific research, and vision.
The longer and more complex the task, the larger Fable 5’s lead over our other models.
what is agent looping
for the last two years we prompted agents one task at a time. that is starting to change
instead of asking an agent to build the landing page and then driving every step yourself, you set up a loop that handles discovery, planning, the work, checking, and iterating until the goal is met
looping is a setup you build. almost any agent harness can run it, it just depends on how you wire it up
at its simplest, looping is one agent working on itself:
> researches
> drafts
> checks the draft against a goal
> fixes what is weak
> runs that cycle again until the work clears the requirements
you are not prompting each step anymore. the agent repeats the cycle for you
the bigger version is a fleet looping. you give an orchestrator agent a goal, it breaks the goal into pieces, hands each piece to a specialist agent, and those specialists hand smaller jobs to their own subagents
the whole tree keeps looping through discovery, planning, execution, and verification until the goal is met
one agent looping is like a person redoing their own draft. a fleet looping is a whole team running a project end-to-end
you create a goal, and the system runs the loop until it finishes within the reqs you set
open and closed looping:
OPEN LOOPING is exploratory. it still has conditions and a goal, but you give the agent or the fleet a wide space to move in. it can try different paths, discover things, build something you did not fully spec out
this is the exciting end, it is what Peter and others are doing, and tbh it is where I want to spend more time
the catch is cost, an open loop with real room to explore burns an insane amount of tokens. for the 90 percent of people without an unlimited budget it is not runnable yet, and pointed at projects with a loose standard it turns into a slop machine
CLOSED LOOPING is bounded. a human designs the end-to-end path first:
> clear goal
> defined steps
> an eval at each step
> a point where it stops or hands back to you (and feeds back performance data)
the agents still loop, but inside framework you built. it gets better every run because each pass feeds the next, and it runs on a normal budget because the path is tight.
for most marketing work, closed is the one that pays off today.
> the orchestrator owns the goal
> the specialists own the steps
> the subagents do the narrow work
> an eval gate make sure its not slop
i rarely if ever truly prepare for anything anymore.
at some point, your entire life either becomes the preparation or it doesn’t.
& if the accumulated pattern of how i think, work, notice, respond, synthesize, improvise, & stay calm under pressure hasn’t prepared me for the thing in front of me, i doubt a few frantic days/hours beforehand are going to save me.
i find it way more useful to just breathe & not think about it too much.
I'm Boris and I created Claude Code. I wanted to quickly share a few tips for using Claude Code, sourced directly from the Claude Code team. The way the team uses Claude is different than how I use it. Remember: there is no one right way to use Claude Code -- everyones' setup is different. You should experiment to see what works for you!
Andrej Karpathy says today's agents aren't ready to work like real coworkers or interns
They lack intelligence, can't use computers, aren't multimodal, lack continual learning, and forget what you tell them
Fixing these gaps will take about a decade
Just woke up in the middle of the night, I know I keep saying this stuff but my dopamine receptors are already fried from the other 50 times my portfolio has gotten fucked so it's fine.
A lot of you are getting zeroed for the first time. I already have a few friends who might not even be alive right now on the other side of the world who said they were gonna end it a few days ago and haven't been online since then.
Not trying to ramble, but my point is, every time you lose unfathomable amounts for the first time it feels like your life is just completely over and there's no chance you'll ever make it back.
If that's you, then you need to completely stop thinking about whatever your ATH port value was. It doesn't matter, nobody ever sells or exits at their exact top anyway, that number is irrelevant.
You need to realize, if you even made that much in the first place then you did something that 99.9% of other people will never do in their lives.
You clearly are capable of recovering from this even though it feels like the world has ended. That feeling of hopelessness will become less and less every day, it might be hard to talk to family or friends for a while.
Take a few days to cry or whatever you need to do but make sure you find at least one person to actually talk to about what happened.
It is INFINITELY harder to deal with this stuff alone, trust me. You don't need to go into specifics or anything. Keeping it bottled up will make this feel significantly worse.
If you still have high 5 figs or 6 figs then you should absolutely not trade for at least a week, revenge trading will make it far worse than it has to be. Your judgement will be severely clouded whether you realize it or not.
Sorry, didn't mean to type so much but just realize that, as much as it feels like the end, it isn't, and MANY people in this space can relate to how you feel right now. I'm not posting this for engagement or anything, I just know exactly how a lot of you feel and have genuinely been there many times.
In a year or so, you will think back to this moment and it'll feel ridiculous that you ever thought it was over, trust me.