In a crossover experiment in a Harvard physics course, the class in which students scored 0.46 standard deviations higher on the test was the one they rated 0.56 lower; in an experiment with generative AI available, self-ratings rose more than actual improvement could explain. Viewing time, platform activity, and models predicting a pass mostly measure how much was done, not learning measured separately. This site's traffic statistics are aggregate, and none of its signals can measure whether readers learned.
In a randomized experiment in one AI course, an order built from rated transition difficulty beat a historical order by about 5 percentage points. Among 8 studies that sequenced interdependent content with algorithms, none significantly beat a fixed human-designed order. Practicing four problem types mixed across eight worksheets gave 61% versus 38% on a test about a month after review, a combined effect of interleaving and spacing. Spiral curricula have almost no efficacy research. MOOC learners who earned certificates still skipped 22% of the content on average.
Spreading practice across days shows an effect of about d = 0.54 in a meta-analysis of real classroom studies, which its authors consider smaller than a meta-analysis that mixed in lab studies. Spacing embedded in mathematics courses (which also involves interleaving) is g = 0.24, and when eight university STEM courses used the same procedure, the gain averaged only 1.5 percentage points, with no detectable difference. Rereading a week later showed no detectable advantage a week after that, and none of the studies in that classroom meta-analysis let learners decide for themselves whether to come back and review.
The most complete attempt, Quantum Country, embedded 112 questions in an essay that takes about four hours to read and then emailed readers to schedule reviews. Its authors rate the evidence that readers would remember much less without review as only emerging, and say there is no evidence it generalizes to other domains. When a MOOC pushed review questions to learners, about 80% of those assigned never touched them, and grades showed no detectable difference; the example that worked was a classroom experiment where review was scheduled into class time.
Telling readers what something is good for makes them rate the material as more useful, but across seven experiments no difference was detected in immediate test scores; in classroom studies where students wrote about usefulness themselves, results flipped across students and courses. Interesting details unrelated to the main point lowered immediate test scores on average, by an uncertain amount; only one pair of experiments detected no harm when learning was voluntary.
In HarvardX and MITx courses, about half of registrants on average never entered the course; among those who did enter, only 3.13% passed in 2017–18. A prompt to write a study plan raised completion from 13.8% to 17.7% in three courses, but at 247 courses no difference in completion was detected. These are all MOOC numbers; this site's traffic statistics are aggregate, with no data on individual readers' behavior.
A TEE is a hardware-isolated execution environment meant to keep even the machine's operator from seeing what runs inside; remote attestation lets an outsider verify which program is running in that room. WhatsApp's Private Processing uses it for AI summaries. Meta's bounty page lists code execution (including bypassing code attestation), privilege escalation and VM escape at up to $300,000 each, data leaks at $150,000 and persistence at $10,000, invitation only, with lower caps for internal-only scenarios. Trail of Bits' review found 28 issues, 8 of them high severity, which shows the hard part of TEEs is implementation detail, not the concept.
AI bounty pages mostly do not pay for what a model says (jailbreaks, hallucinations, harmful output). They pay when a model is made to act against someone else (actions and data theft through indirect prompt injection), and for ordinary bugs in the software around it. Google's AI VRP base rewards run from $100 to $20,000; OpenAI's Safety Bug Bounty ranges are $250 to $7,500 per report. Rules as read on 2026-10-14.
Google multiplies the reward by 0.8, 1 or 1.2 depending on report quality across seven dimensions, and only counts what you provided before triage; later additions usually do not change it. Write to a one-page template (title, summary, preconditions, steps, impact, fix suggestion), then estimate hourly expected value as probability x amount / hours. A bigger ceiling can still lose to a small payout once the odds are low enough. Only Resolved is guaranteed to pay; duplicates and invalid reports are common. Every probability and hour count in this post is an assumption, not a statistic.
A chat model is rewarded for a single response people prefer; an agent has to be rewarded for whether a multi-step task actually finished, which needs different data and environments.
Reasoning is the intermediate tokens between input and output; RL fine-tuning beats imitating human solutions because of a reliable verifier, and sampling several times then taking the most frequent answer pushes accuracy further.
AlphaGeometry2 relies on a symbolic engine and AlphaProof on Lean, for a combined 28 points in 2024; in 2025 Gemini Deep Think scored 35 points in natural language, with verification done by human graders.
Laskin's view is that engineers spend 80% of their time understanding systems rather than writing code, and that how far RL goes depends on clean rewards, a problem he considers as hard as superintelligence itself.
A VLA adds an action module to a vision-language model; letting that module's gradients flow back harms language understanding, so knowledge insulation blocks the gradient, while π0.5 co-trains on web data and data from many robots to gain generalization.
Alexandr Wang says Meta listed 100+ behaviors a personal agent needs, built an eval for each, and set two thresholds per row: a launch-blocking floor and a bar for 'good'. They shipped after the first all-green checkpoint and a hands-on check that it was clearly better; they also ran new-user testing. The method is reusable, but post-launch safety reports show all-green is not the same as safe.
This lecture puts the first concrete content into the flowchart from Lecture 1: the hypothesis set H is all lines (perceptrons), and the algorithm A is PLA, which adds yₙxₙ to w whenever it sees a misclassified point. When the data is linearly separable, PLA started from w₀ = 0 halts after at most R²/ρ² corrections; when the data cannot be separated, switch to pocket, which keeps the line with the fewest mistakes seen so far in its pocket.
This lecture takes the learning flow diagram from Lecture 1 and swaps one part at a time along four directions: the output space Y (binary classification, multiclass classification, regression, structured learning), the labels yₙ (supervised, unsupervised, semi-supervised, reinforcement learning), the way data reaches the algorithm (batch, online, active), and the input space X (concrete, raw, abstract features). Each direction has one core option, and together they mark the home ground for the rest of Foundations: batch, supervised binary classification and regression on concrete features.