Pinned Tweet
Do you ever feel like facilitation practices seem like some form of illegitimate grift practiced as a way to control the frame?
If you sometimes feel this way, I feel like I can offer a few klews 🧶🧵👇
It's only through such 'lawfully' consistent frames that participants are able to make sense of and interpret the unfolding journey on their own terms.
Without such an affordance it would seem that a group cannot meaningfully consent to any subsequent activity!
If you resonate with this commentary, perhaps reach out. You can also get in contact further or share my services with others via:
facilitation.joshafairhead.c…
Groovy content, appreciated aesthetics and inspiration that seems most fitting to the twinkles of hope starting to glisten this round.
Yes, but beyond purely cognitive perhaps we can perceive this phenomena more as an "envelope of being" - possibly related to energetic modalities?
This Post is from an account that no longer exists. Learn more
Josh retweeted
thinking about, writing about my own social reality validates my experience
sharing my experiences about social reality with others helps corroborate, expand, correct/improve my sensemaking
Imagining this from the perspective of a "strange loop" we get a futures method:
Assuming a causal loop the forms change but the underlying pattern remains the same. Over time the agent gathers details on the underlying structure of the loop.
This is agent centric learning.
What the fuck just happened 🤯
Stanford just made fine-tuning irrelevant with a single paper.
It’s called Agentic Context Engineering (ACE) and it proves you can make models smarter without touching a single weight.
Instead of retraining, ACE evolves the context itself.
The model writes, reflects, and rewrites its own prompt over and over until it becomes a self-improving system.
Think of it like the model keeping a living notebook.
Every failure becomes a lesson. Every success becomes a rule.
And the results are absurd:
+10.6% better than GPT-4–powered agents on AppWorld
+8.6% on financial reasoning
86.9% lower cost and latency
No labels. Just feedback.
Everyone’s obsessed with “short, clean” prompts.
ACE flips that. It builds dense, evolving playbooks that compound over time and never forget.
Because LLMs don’t crave simplicity.
They crave context density.
If this scales, the next generation of AI won’t be fine-tuned.
It’ll be self-tuned.
We’re entering the era of living prompts.
What are the most effective futures methods you know of?
I find that when one enters a cognitive state of being unable to predict the future, it often evokes the emotional state of fear.
While this reaction is natural, what if we possessed a framework — structured methods of reasoning — that could help us discern patterns within these presently unknown futures?
Codynamic Theory provides exactly such a framework.
