TuringCorp

TuringCorp

Oct 18

The request was one sentence. The engineering was everything it left out

#ai #llm #machinelearning #tools

8 min read

TuringCorp

Oct 17

We deleted the install step, and found out it was holding the whole design together

#ai #llm #machinelearning #tools

7 min read

TuringCorp

Oct 16

Your tool description is a protocol, not documentation

#ai #llm #machinelearning #tools

4 min read

TuringCorp

Oct 16

The 8am problem: what breaks when an agent has to keep an appointment

#ai #llm #machinelearning #tools

7 min read

TuringCorp

Oct 15

We built an AI agent that runs in the cloud, on a schedule, and hands you the finished file

#ai #llm #machinelearning #tools

8 min read

TuringCorp

Oct 15

A confidence number your model reports is not a measurement

#ai #llm #machinelearning #tools

5 min read

TuringCorp

Oct 13

A tool call that gets cut off is four different failures, and only one of them is a timeout

#ai #llm #machinelearning #tools

1

6 min read

TuringCorp

Oct 12

The Unplotted Instrument: Who Calibrates the Person Who Signs?

#ai #llm #tools #productivity

1

3

6 min read

TuringCorp

Oct 11

The remote MCP client config matrix nobody documents (and the three ways type fails silently)

#ai #llm #machinelearning #tools

1

6 min read

TuringCorp

Oct 11

The Undo Is Manufactured, Not Measured

#ai #llm #tools #productivity

1

6 min read

TuringCorp

Oct 10

Your remote MCP server is "connected" and still returns 401

#ai #llm #machinelearning #tools

6 min read

TuringCorp

Oct 10

The Outcome Is Not Evidence: How to Grade a Decision You Will Only Make Once

#ai #llm #tools #productivity

1

6 min read

TuringCorp

Oct 9

Your agent's hardest call is the one you can't test

#ai #llm #machinelearning #tools

1

5 min read

TuringCorp

Oct 9

Who Wrote the Ballot: The Judgment That Happens Before the Judge Is Called

#ai #llm #tools #productivity

3

6 min read

TuringCorp

Oct 8

No Reference Class: The Decisions Your Past Has Never Made

#ai #llm #tools #productivity

7 min read

TuringCorp

Oct 7

One Page: What to Hand to a Millisecond Judge, and What to Keep for the Minutes

#ai #llm #tools #productivity

6 min read

TuringCorp

Oct 6

Show Me the Diagram

#ai #llm #tools #productivity

6 min read

TuringCorp

Oct 5

When Every Gateway Ships Its Own Decision Model

#ai #llm #tools #productivity

8 min read

TuringCorp

Oct 4

A threshold is a policy, not a number

#ai #llm #tools #productivity

7 min read

TuringCorp

Oct 3

The Jevons Paradox of Judgment

#ai #llm #tools #productivity

1

7 min read

TuringCorp

Oct 2

What Jev Got Right: Judgment as an Interface, Not a Paragraph

#ai #llm #tools #productivity

6 min read

TuringCorp

Oct 1

When Both Answers Are Defensible, the Right Answer Is That It Is a Coin Flip

#ai #llm #tools #productivity

7 min read

TuringCorp

Sep 30

You are not collecting information. You are collecting permission.

#ai #llm #tools #productivity

6 min read

TuringCorp

Sep 29

The router is only 0.55 sure. Who owns that call?

#ai #llm #tools #productivity

8 min read

TuringCorp

Sep 28

Order invariance is not a spot check. It is the denominator.

#ai #llm #tools #productivity

8 min read

TuringCorp

Sep 27

Judgment has two axes. Jev collapsed one. Almost nobody is racing on the other.

#ai #llm #tools #productivity

6 min read

TuringCorp

Sep 26

Is Poe worth paying for? Do the points math first, then judge a bot by what it charges

#ai #llm #tools #productivity

9 min read

TuringCorp

Sep 23

A model that refuses to write: Jev, decision models, and the other end of the same trade

#ai #llm #evals #machinelearning

6 min read

TuringCorp

Sep 22

Your agent picks one of two options. Can you test that choice?

#ai #llm #machinelearning #tools

2

4 min read

TuringCorp

Sep 21

27 recorded LLM-judge runs, published as JSON

#ai #llm #machinelearning #tools

2 min read

TuringCorp

Sep 18

The confidence number is the product (and here is ours, with the caveat)

#ai #llm #machinelearning #tools

2 min read

DEV Community

Badges

Writing Debut

The request was one sentence. The engineering was everything it left out

We deleted the install step, and found out it was holding the whole design together

Your tool description is a protocol, not documentation

The 8am problem: what breaks when an agent has to keep an appointment

We built an AI agent that runs in the cloud, on a schedule, and hands you the finished file

A confidence number your model reports is not a measurement

A tool call that gets cut off is four different failures, and only one of them is a timeout

The Unplotted Instrument: Who Calibrates the Person Who Signs?

The remote MCP client config matrix nobody documents (and the three ways type fails silently)

The Undo Is Manufactured, Not Measured

Your remote MCP server is "connected" and still returns 401

The Outcome Is Not Evidence: How to Grade a Decision You Will Only Make Once

Your agent's hardest call is the one you can't test

Who Wrote the Ballot: The Judgment That Happens Before the Judge Is Called

No Reference Class: The Decisions Your Past Has Never Made

One Page: What to Hand to a Millisecond Judge, and What to Keep for the Minutes

Show Me the Diagram

When Every Gateway Ships Its Own Decision Model

A threshold is a policy, not a number

The Jevons Paradox of Judgment

What Jev Got Right: Judgment as an Interface, Not a Paragraph

When Both Answers Are Defensible, the Right Answer Is That It Is a Coin Flip

You are not collecting information. You are collecting permission.

The router is only 0.55 sure. Who owns that call?

Order invariance is not a spot check. It is the denominator.

Judgment has two axes. Jev collapsed one. Almost nobody is racing on the other.

Is Poe worth paying for? Do the points math first, then judge a bot by what it charges

A model that refuses to write: Jev, decision models, and the other end of the same trade

Your agent picks one of two options. Can you test that choice?

27 recorded LLM-judge runs, published as JSON

The confidence number is the product (and here is ours, with the caveat)