olivLaw · Feed
From booksStuart Russell, Peter Norvig· 4 Sept, 22:32
Question

Which two terms in Russell and Norvig's definition separate an agent from a single model call?

An agent is a perceive–decide–act loop, and the guardrails sit on every turn.

Stuart Russell, Peter Norvig · Artificial Intelligence: A Modern Approach

From booksHerbert A. Simon· 4 Sept, 16:32
Question

Why is Simon's ant an argument for context engineering?

The environment the agent sees explains more of its behaviour than the model does.

Herbert A. Simon · The Sciences of the Artificial

From booksRichard S. Sutton· 4 Sept, 10:32
Question

In Sutton's terms, what bet does an agent with many hand-written rules make?

An agent's scaffold must be thin enough that a better model improves it rather than breaks it.

Richard S. Sutton · The Bitter Lesson

From booksErik Schluntz, Barry Zhang· 4 Sept, 04:32
Question

What is the difference between a workflow and an agent, as defined in "Building effective agents"?

If you can draw the flowchart, build a workflow, not an agent.

Erik Schluntz, Barry Zhang · Building effective agents

From booksShunyu Yao et al.· 3 Sept, 22:32
Question

What does ReAct add over plain chain-of-thought?

Thought, action, observation: every turn of the loop is a place to check and a place to attack.

Shunyu Yao et al. · ReAct: Synergizing Reasoning and Acting in Language Models

From booksMarvin Minsky· 3 Sept, 16:32
Question

When is it worth splitting one agent into several?

The number of agents follows the number of distinct contexts, not the org chart.

Marvin Minsky · The Society of Mind

From booksJon Postel· 3 Sept, 10:32
Question

What does MCP standardise, and who has governed it since December 2025?

The tool description is the prompt you did not write, yet the model reads it on every turn.

Jon Postel · RFC 793 — Transmission Control Protocol

From booksMelvin E. Conway· 3 Sept, 04:32
Question

What is the difference in role between MCP and A2A?

The boundaries between agents will be the boundaries between teams, unless you choose them.

Melvin E. Conway · How Do Committees Invent?

From booksJohn Gall· 2 Sept, 22:32
Question

What do you ask of an agent framework before adopting it?

Start from the hundred-line raw loop; adopt a framework when you need durable state, human pauses or routing.

John Gall · Systemantics: How Systems Work and Especially How They Fail

From booksKen Thompson· 2 Sept, 16:32
Question

What is "tool poisoning" and why does the user not see it?

A tool's description is code executed by the model: review it, pin it, isolate it.

Ken Thompson · Reflections on Trusting Trust

From booksAlfred North Whitehead· 2 Sept, 10:32
Question

What is the recommended order of cost-reduction measures in an agent?

The expensive model is called on exception, not by default.

Alfred North Whitehead · An Introduction to Mathematics

From booksPeter Belcak et al. (NVIDIA Research)· 2 Sept, 04:32
Question

What procedure does the NVIDIA paper propose for moving an agent from large models to small ones?

The planner can be large; the workers can be small, specialised and local.

Peter Belcak et al. (NVIDIA Research) · Small Language Models are the Future of Agentic AI

From booksEdward J. Hu et al.· 1 Sept, 22:32
Question

What does LoRA freeze and what does it train?

LoRA freezes the model and learns a small low-rank correction, so an adapter is a file, not a model.

Edward J. Hu et al. · LoRA: Low-Rank Adaptation of Large Language Models

From booksJohn Schulman et al.· 1 Sept, 16:32
Question

Name three cases where LoRA beats RAG and prompting.

Fine-tuning for behaviour, RAG for knowledge, a prompt for everything it can carry.

John Schulman et al. · LoRA Without Regret

From booksMarilyn Strathern· 1 Sept, 10:32
Question

What does Goodhart's law mean for an LLM evaluator?

An LLM judge is calibrated on humans and kept out of the optimisation loop.

Marilyn Strathern · «Improving ratings»: audit in the British University system

From booksWilliam Stanley Jevons· 1 Sept, 04:32
Question

What are the two solid arguments for on-prem inference?

On-prem is justified by sustained utilisation or by data that cannot leave, not by the token price.

William Stanley Jevons · The Coal Question

From booksSimon Willison· 31 Aug, 22:32
Question

What are the three features of the lethal trifecta?

Break one leg of the trifecta: no outbound channel, no untrusted content or no private data.

Simon Willison · The lethal trifecta for AI agents

From booksJerome H. Saltzer, Michael D. Schroeder· 31 Aug, 16:32
Question

Why does the agent not get the user's full token?

An identity of its own for the agent, allowlisted rights, a sandbox and approval on the irreversible.

Jerome H. Saltzer, Michael D. Schroeder · The Protection of Information in Computer Systems

From booksParlamentul European și Consiliul· 31 Aug, 10:32
Question

Where does personal data enter an agent, and where do the measures go?

Pseudonymise at the tool boundary, re-identify at the end, keep the traces clean and the memory off.

Parlamentul European și Consiliul · Regulamentul (UE) 2016/679 — GDPR

From booksJoseph Weizenbaum· 31 Aug, 04:32
Question

By what criterion is an agent's level of autonomy set?

Autonomy is granted by reversibility: suggest, ask for approval, act and report.

Joseph Weizenbaum · Computer Power and Human Reason

Loading…