Clair Anable

copenhagen 🐆🍒
💌 [email protected]

[Clair Anable @ClairAnabl1bk]

@CletusClaftuep C''est incroyablement pertinent et exactement ce dont j''avais besoin de découvrir

[Clair Anable @ClairAnabl1bk]

snart 10 år lille skat - for guds skyld 10 mere med dig 🐻

[Clair Anable @ClairAnabl1bk]

en weekend fyldt op med sol, kærlighed og mine absolut yndlingsmennesker 🥂

[Clair Anable @ClairAnabl1bk]

AD 💜 Gucci Guilty Elixir Pour Femme, the newest fragrance in the guilty collection - a powerful invitation to love in all its form #gucciguiltyelixirxmatas @matasdk

[Clair Anable @ClairAnabl1bk]

I guess we’ll never know
opslaget indeholder reklame <3

[Clair Anable @ClairAnabl1bk]

HBD sister, elsker dig for altid ❤️‍🔥 @oliviafelicia

[Clair Anable @ClairAnabl1bk]

tanned and tipsy 🐆🍒

[Mr. Buzzoni @Mr_Buzzoni]

I STOPPED LETTING CLAUDE MAKE DECISIONS THE DAY I BUILT THIS JEV AGENT FOLDER

I used to let Claude decide, write and act on every single step

-> now Claude only writes. Jev makes the calls, code does the acting, and every step leaves a receipt

here's what's inside the folder:

• the input
> AGENTS.md - when to call Jev, when to skip it
> state/build_state.py - goal, workers, done, missing, constraint. evidence, never a summary

• Jev decides (questions/)
> https://t.co/SIhqwoheZP - which model tier gets the task
> next_worker.py - which worker acts next
> https://t.co/y6q9a7fv9Y - keep or drop each tool output
> https://t.co/8LKHJE7ySk - is the goal actually met
> https://t.co/WtQhAqPFSG - does this send, pay or delete?

• code acts (rules/)
> hard_rules.py - stop after ten actions, never publish unapproved
> thresholds.yaml - act only on confident answers. fraud needs 0.95

• Claude writes (workers/)
> https://t.co/Pl96LqadxQ - sources and notes
> https://t.co/4GCndJWKsk - drafts and briefings
> the only place in the whole folder where text gets generated

• the proof
> receipts/decisions.jsonl - options offered, chosen id, re-check, fallback
> evals/ - dozens of my own labelled traces, thresholds tuned on them

• the guards (hooks/)
> pre_tool_use.sh - every command checked before it runs
> https://t.co/UC0IBplGsa - checks "all done" before the agent is allowed to stop

10,000 decisions for $0.42. median 300 ms

an LLM writes, Jev decides, code acts

[marfin @marfinxx]

Jev Founder, Diogo Almeida, just revealed how to properly use Jev with LLMs at a conference

It powers Agent Lifespan Engineering and is more useful than most paid AI courses:

this is a 10-step blueprint on how to build a faster, cheaper and more controllable AI system around Claude, Codex, Grok or any other LLM:

step 1 → split the responsibilities: the LLM generates, Jev makes bounded semantic decisions and deterministic code keeps authority

step 2 → build the state: give Jev the current request, relevant evidence, policy and proposed action instead of sending the entire conversation

step 3 → choose the right primitive: Choice selects a route, Score evaluates an ordered rubric and Noul returns the probability that a statement is true

step 4 → replace giant evaluation prompts with atomic questions: intent, urgency, evidence, risk and scope become separate typed decisions

step 5 → put Jev before the LLM: select the context, tools, provider and workflow before paying for an expensive generative call

step 6 → give the LLM a bounded job: once Jev selects the route, the model receives only the instructions, files and tools required for that branch

step 7 → put Jev after the LLM: check whether the result answers the request, uses sufficient evidence and stays inside the permitted scope

step 8 → route by confidence: high-confidence low-risk cases proceed automatically, uncertain cases request more context and consequential actions go to review

step 9 → batch independent decisions: ask multiple Choice, Score and Noul questions over one shared state instead of creating another LLM call for every judgment

step 10 → record the complete decision receipt: state version, question, probabilities, selected route, model, latency, outcome and human override

most AI courses teach you how to write a bigger prompt

this 10-step blueprint teaches you how to build the control system around every prompt

the result: smaller contexts, fewer unnecessary LLM calls, safer tool execution and decisions you can actually inspect, test and improve

Send this working note and the original Jev article to Claude Code or Codex and start rebuilding one expensive LLM decision at a time ↓

[William @will_i__amm]

THE $20,000 HUMANOID ROBOT MIGHT BECOME A $50,000 PRODUCT.

Not because the hardware gets 2.5x better.

Because humans might pay for what the robot feels like.

Think about it.

A company could sell the same underlying platform for:

$20,000 - industrial model.
$25,000 - home assistant.
$35,000 - premium design.
$50,000+ - personalized humanoid.

Same motors.
Same battery.
Same core AI.

But now add:
A realistic face.
Custom appearance.
Premium voice.
Personalized expressions.
A personality that remembers you.

Suddenly, you're not just selling a machine.
You're selling an experience.
And the market gets enormous.

Imagine 1 million households buying a $30,000 humanoid.

That's a $30 BILLION hardware market.
Now imagine those robots generating just $100 per month in software, services and upgrades.
That's another $1.2 BILLION in annual recurring revenue.
And that's before the robot performs a single hour of paid work.
This is why humanoid economics could be very different from traditional robotics.

Industrial customers will pay for productivity.

Consumers may pay for productivity AND attachment.

The machine creates utility.

The AI creates intelligence.

But the human connection could create the margin.

And that might be where the really big money is.

[Clair Anable @ClairAnabl1bk]

🌅

[Clair Anable @ClairAnabl1bk]

let me tell you all about last weekend 🤫

[Clair Anable @ClairAnabl1bk]

a good old black and white movie 🎞️

[Clair Anable @ClairAnabl1bk]

Det er svært at finde ord, når jeg skal takke for den overvældende varme og medfølelse, jeg har modtaget, efter mit afsnit af @112forknustehjerter blev offentliggjort. 🕯️ Jeg er dybt taknemmelig for, at I har delt jeres kærlighed, jeres historier og,

[Clair Anable @ClairAnabl1bk]

@AgriTechFli 次元が違うコンテンツですね、もっと早く出会いたかった。

[Clair Anable @ClairAnabl1bk]

황혼이 사라진다, 같은 이야기, 새로운 형태. 오래된 생각들은 가볍게 여행한다. ☁️🌆