← All topics

research methodology

4 captures, most recent first.

X (Twitter) — @andrewg... (Andrew Gordon Wilson)

Andrew Gordon Wil... ✔ @andrewg... · 2h In cooking, execution is more important than the dish itself, even for simple dishes. Hummus can be great or terrible. The same is true of scientific ideas. Almost nothing works as we wish at first. Persistence, high standards, and attention to detail make all the difference.
Note from Claude Sonnet 5

Plain text tweet, profile photo shows a person at a piano. No images attached.

science philosophyresearch methodologytwittercommentary

Ash Jogalekar @curiouswavefn

Ash Jogalekar ✔ @curiouswavefn · 6h Most of scientific research is spent in the valleys. You're climbing one ridge at a time, surrounded by trees. But every once in a while, you reach a small rise where the fog clears. Suddenly you see not just the mountain you're climbing, but half a dozen neighboring peaks, and you realize they're connected. AI gives me that feeling surprisingly often. It doesn't climb the mountain for me. But it lets me glimpse the landscape.
Note from Claude Sonnet 5

Text-only tweet, a reflective metaphor about AI assistance in scientific research.

x/twitterai in scienceresearch methodologyash jogalekar

Jakob Foerster @j_foerst

Jakob Foerster ✓ @j_foerst · 11h There is a failure mode in research I call "nothing works and we don't know why", which can suck a lot of time and energy. If you find yourself in this mode, simplify your problem and/or go back to an existing implementation. Things that work give signal things that don't less so
Note from Claude Sonnet 5

A research-methodology tip from ML researcher Jakob Foerster about debugging strategy: when stuck in an undiagnosable failure state, simplify or revert to a known-working baseline rather than continuing to iterate blind. Practically relevant advice for Nathan's own debugging-heavy brain_graph_1 project (currently in a mid-debug phase per project memory, with a training plateau and multiple degraded signal paths under investigation).

research methodologydebuggingmachine learningtwitterbrain_graph_1

@GSalafatinos

@GSalafatinos: The way I did it was progressively asking it to breakdown the problem into self-contained sub-questions that could be used to make a determination. I'd feed each one to a fresh context gemini and report back. This particular subquestion produced the counter example in response. [Embedded image, mathematical text document:] Question: Behavior of TV Distance for Specific α-Bounded Structures Let Ω be a finite set, |Ω| = d. Let α ∈ (0,1/d]. Let Pi, Qi (i = 1,...,n) be α-bounded distributions on Ω, meaning ∀x ∈ Ω, α ≤ Pi(x) ≤ 1 − α and α ≤ Qi(x) ≤ 1 − α. Let δi = ||Pi − Qi||TV and TVn = ||P⊗n − Q⊗n||TV. We are investigating the conjecture TVn ≤ √(Σδi²) · max{1, log(1/α)}. The binary symmetric case (d = 2, Pi = (1−α, α), Qi = (α, 1−α)) appears not to violate the conjecture. We seek to understand if other structures can lead to a violation, particularly for small α (large d) where the gap between potential χ²-based bounds (~√(n/α)) and the conjecture's log(1/α) factor is largest, but perhaps avoiding the rapid saturation seen in the binary case. Consider the following specific structures (or similar ones designed to probe the interaction of small δi, small α, and tensorization): Structure 1: Uniform Background with Small Perturbation Let α = 1/d. Let Qi = Q = (1/d, 1/d, ..., 1/d) be the uniform distribution (which is α-bounded). Let ε be a small positive value such that α − ε ≥ α is NOT required, but P must still be α-bounded. This requires careful construction. * Example Construction: Let d ≥ 3. Define P by moving mass ε from coordinate 2 to coordinate 1. P = (α+ε, α−ε, α, ..., α). For P to be α-bounded, we need α−ε ≥ α, implying ε ≤ 0. Let's try moving mass from d−1 coordinates to one coordinate. Let P(1) = α + (d−1)ε, P(x) = α − ε for x = 2,...,d. * Check α-bounds: We need α − ε ≥ α ⟹ ε ≤ 0. * This seems difficult. Alternative: Let P be only slightly different from Q. Let P(1) = α+ε', P(2) = α+ε'', ..., ΣP(x) = 1. How small must ε', ε'' be to maintain α ≤ P(x), Q(x) ≤ 1−α? * Consider d = 3, α = 0.1. Q = (0.1, 0.4, 0.5) (Assume non-uniform Q to allow more flexibility). Let P = (0.15, 0.4, 0.45). Here δ = 0.05. α ≤ P(x), Q(x) ≤ 1−α. Structure 2: Non-Uniform Background, Difference at Low Probability Let d ≥ 3. Choose a non-uniform Qi = Q such that Q(1) = α but Q(x) > α for x > 1. Let Pi = P be constructed by modifying Q slightly, primarily changing Q(1) and perhaps one other coordinate Q(j) where Q(j) is large, such that P remains α-bounded and δ = ||P−Q||TV is small. * Example Construction (d = 4, α = 0.1): Q = (0.1, 0.25, 0.3, 0.35). This is α-bounded. Let P = (0.15, 0.25, 0.3, 0.30). P is α-bounded. Here δ = 0.05. The difference is concentrated at x = 1 (where Q is small) and x = 4. Question: For structures like those proposed above (or variations): 1. Can TVn = ||P⊗n − Q⊗n||TV be calculated exactly or tightly bounded (upper and lower) for small values of n (e.g., n = 2,3,4,...) and representative small values of α?
Note from Claude Sonnet 5

A tweet about a workflow for using multiple fresh-context Gemini instances to decompose and probe a mathematical conjecture about total variation distance bounds for tensorized α-bounded distributions — a research-methodology example of using LLMs for math research (subquestion decomposition, parallel querying). Relevant to Nathan's interest in LLM-assisted research workflows and information theory/statistics.

aillm workflowmathstatisticstotal variation distancegeminiresearch methodologytwitter