Efficient Thinking

One question, from every angle: how much useful capability can a fixed intelligence get per unit of computation, and what moves that number? Each paper holds the model fixed, measures capability with an external verifier, and changes one thing: search, the evaluator, the judge, taste, feedback, labels, the internal ceiling, experience, symmetry, representation.

The result to try to break. A frozen 7B model, given a read-only linear head fitted on its own verified history, solves more problems at the same inference compute — and, at equal quality, spends 2.3× less. The mechanism transfers to a second search structure with the head re-fitted, and a second generation of experience beats the first, then a third does not. The headline reproduces from one command in about three hours on an Apple-silicon Mac.

git clone https://github.com/LouayAlsakka/efficient-thinking && cd efficient-thinking
bash experience/reproduce_matched_compute.sh      # base at the head's compute vs the head, n = 300, paired

It refuses to print a table if any gate fails and exits non-zero if the published interval is not reproduced. An independent run on a second machine by someone who had not touched the work read +8.0 [+3.0, +13.3] against the published +9.3 [+3.7, +15.0].

Papers

#	Title	State	Read
I	Measuring What Capability Costs — search substitutes for size on a frozen chess evaluator	measured	html · pdf · md
II	Where Search Pays and Where It Can't — the evaluator's ceiling, in games and in language	measured	html · pdf · md
III	Efficient Judging — when an LLM judge is worth its compute	measured, draft	pdf · md
IV	Search Where Taste Is the Evaluator	machine arms measured; rater arms running	proposal
V	The Exchange Rate of Feedback	concept	concept
VI	The Label Ceiling — why self-play plateaus	measured, unwritten	concept · ledger
VII	The Elicitation Gap — what a fixed system can get from inside	concept; probe running	concept
VIII	Experience Priors — the constraint and the carrier	closed, reproduced	html · pdf · md
VIII-b	Accumulation — does experience move the frontier again	measured; paper in progress	record
IX	Symmetry — invariance as thought compression	concept	concept
X	Machine-Native Representation	concept	concept · plan

Every paper opens with a state line — MEASURED, REGISTERED, CONCEPT or IDEA — so that a concept is never read as a finding. Withdrawn claims stay in the record, dated. Readings are written before runs. Result artefacts name their instruments by hash. The series plan and the one-question rule are in series-completion-plan.md.

Review

There is no venue, no referee and no gate. Review is public and runs through the repository's issues. The four places the author thinks Paper VIII is weakest, so you know where to aim: an alternative explanation for the matched-compute frontier shift; leakage in how the experience was constructed; a flaw in the paired statistics; a reason the second search structure does not establish transfer of the mechanism. A fatal flaw is worth more than praise, and the author will run any experiment you name.

Author

Louay Alsakka. An electrical engineer from the semiconductor industry; this is a first research project, done outside any institution with AI assistance, and published directly. The chess engine of Paper I is where the two interests meet.

Repository: github.com/LouayAlsakka/efficient-thinking