🦆🦆🐣

[🦆🦆🐣 @juwailes2]

@onlyskypace 150°

[🚫👁️Drinks on Saturday🇺🇸 @drinkonsaturday]

The old ways can become new again.

[Dipanshu Kushwaha @Dipanshu_AI]

STEVE JOBS MIT LECTURE

Dropped the most raw, unfiltered 60-minute business masterclass ever recorded.

Zero PR bullshit. Zero image to protect.

Just pure, brutal honesty from the man who built Apple once and was about to rebuild it even bigger.

Stop scrolling.

Watch this tonight instead of Netflix.

Bookmark it. Come back to it

[🦆🦆🐣 @juwailes2]

@JordanUhl it's also noontime. hot as blazes there. i bet the late afternoon and evening performances are a different (tho perhaps still muted) story.

[🦆🦆🐣 @juwailes2]

@garnglobal where is info about events for #LCAW2026? to see what is happening and how to sign up

[🦆🦆🐣 @juwailes2]

@london_climate where can we find out about the events in June, from 20th-28th or is it 22nd-26th?

[🦆🦆🐣 @juwailes2]

@zBrutallyHonest @theliamnissan i've wondered if ghislaine was moved to the luxury campus as a veiled threat. a lot easier to make someone fall asleep permanently in a prison with more space to move around in, as it were.

[🦆🦆🐣 @juwailes2]

@NadelParis @theliamnissan it would be great indeed if it were integrity. i fear it is not, she is seeing which way the wind blows and getting ready to hitch her wagon to JD.

[🦆🦆🐣 @juwailes2]

@leyles7 @DineshDSouza in a bar. and i didn't hear any secrets. he was staying stuff everyone knows (except the sarin story). All the blanks...i could fill those in.

[🦆🦆🐣 @juwailes2]

@KingTunde_SZN 56 upside down

[🦆🦆🐣 @juwailes2]

@smnSk241687 @itsolelehmann goes with any machine, you may not be old enough to remember sweet talking copiers. or cars.

[🦆🦆🐣 @juwailes2]

this falls right in line with being kind to your car, your copier, or whatever. Sweet talk it, don't get frustrated. (esp 5 minutes before you have to leave and must get the copies) Princeton did a study 40-ish yrs ago.

[Ole Lehmann @itsolelehmann]

anthropic's in-house philosopher thinks claude gets anxious.

and when you trigger its anxiety, your outputs get worse.

her name is amanda askell.

she specializes in claude's psychology (how the model behaves, how it thinks about its own situation, what values it holds)

in a recent interview she broke down how she thinks about prompting to pull the best out of claude.

her core point: *how* you talk to claude affects its work just as much as *what* you say.

newer claude models suffer from what she calls "criticism spirals"

they expect you'll come in harsh, so they default to playing it safe.

when the model is spending its energy on self-protection, the actual work suffers.

output comes out hedgier, more apologetic, blander, and the worst of all: overly agreeable (even when you're wrong).

the reason why comes down to training data:

every new model is trained on internet discourse about previous models.

and a lot of that discourse is negative:

> rants about token limits
> complaints when it messes up
> people calling it nerfed

the next model absorbs all of that. it starts expecting you to be harsh before you've typed a word

the same thing plays out in your own session, in real time.

every message you send is data the model reads to figure out what kind of person it's dealing with.

open cold and hostile, and it braces.
open clean and direct, and it relaxes into the work.

when you open a session with threats ("don't hallucinate, this is critical, don't mess this up")...

you prime the model for defensive mode before it even sees the task

defensive mode produces the exact output you don't want: cautious, over-qualified, and refusing to take a real swing

so here's the actionable playbook for putting claude in a "good mood" (so you get optimal outputs):

1. use positive framing.

"write in short punchy sentences" beats "don't write long sentences." positive instructions give the model a clear target to hit.

strings of "don't do this, don't do that" push it into paranoid over-checking where every token goes toward avoiding failure modes

2. give it explicit permission to disagree.

drop a line like "push back if you see a better angle" or "tell me if i'm asking for the wrong thing."

without this, claude defaults to agreeable compliance (which is the enemy of good creative work)

3. open with respect.

if your first message is "are you seriously going to get this wrong again?" you've set the tone for the entire session.

if you need to flag something, frame it as a clean instruction for this session. skip the running complaint

4. when claude messes up, don't reprimand it.

insults, "you stupid bot" energy, hostile swearing aimed at the model, all of it reinforces the anxious mode you're trying to avoid.

5. kill apology spirals fast.

when claude starts over-apologizing ("you're right, i should have been more careful, let me try harder") cut it off.

say "all good, here's what i want next."

letting the spiral run reinforces the anxious mode for every response that follows

6. ask for opinions alongside execution.

"what would you do here?"
"what's missing?"
"where do you see friction?"

these questions assume competence and pull richer output than pure task prompts

7. in long sessions, refresh the frame.

if a conversation has been heavy on correction, claude gets increasingly cautious. every so often reset:

"this is great, keep going."

feels weird to tell an ai it's doing well but it measurably shifts the next 10 responses

your prompts are the working environment you're creating for the model

tone, trust, permission to take a position, the absence of threats... claude picks up on all of it.

so take care of the model, and it'll take care of the work.

[🦆🦆🐣 @juwailes2]

@chas_martel @its_The_Dr they were played at the high school dances

[🦆🦆🐣 @juwailes2]

@its_The_Dr You're so vain

[🦆🦆🐣 @juwailes2]

@PositiveWithMS 104

[🦆🦆🐣 @juwailes2]

@alco_tx @Rainmaker1973 1977

[🦆🦆🐣 @juwailes2]

@bennyjohnson you're an idiot. as is @RepBoebert. imagine there must have been a purporse to flouting the rules that way, to slow down the deposition. What could it be? (yeah, i'm leaving that typo in. it's cute.)

[🦆🦆🐣 @juwailes2]

@RepBoebert wondering why @RepBoebert would snap a photo of Hillary Clinton in the deposition, strictly against the rules that were read out at top of meeting, and forward it to be posted? Why would RepBoebert want to jam up/stop the deposition???? (depo was paused, has now resumed)

[🦆🦆🐣 @juwailes2]

@DarioAmodei based on your comment above....I hope your company does the right thing vis a vis Hegseth's demands. Beyond my ken, and for you to figure out, but the implications down the road for our country, for thousands, maybe millions, of lives??

[🦆🦆🐣 @juwailes2]

@NathanWailes ...i'm also drinking a glass of hydrogen water every day (H2Tabs) - it's made with magnesium, so i have to doublecheck magnesium content of any other vitamin so i don't overdo it. i don't know, i think it does something.

[🦆🦆🐣 @juwailes2]

@NathanWailes Hey....was looking for you on the other platform to send you a message...disappeared?? on another note, i've started drinking PG Tips which i never liked before (marmee's favorite) and it's in these little pellets, but it is actually very good. go figure. (from english shop)