“10×” LLM Engineer
What does 10× actually mean?
How do we use it to ship real work?
What's the honest reality behind the “10× engineer” — or the “10× LLM engineer”?
Same math, different role. The multiplier is bounded by inventory, not skill.
Top of funnel is configurable, standard, repeatable. Offload to an LLM API with a rules harness — scan, classify, extract — and the multiplier grows with the inventory. Just tokens.
The multiplier collapses at the bottom, where a human reviews the findings. Design your work so more of it lives at the top of the funnel and the multiplier goes with you.
nanochat — a minimal LLM trainer with exactly one knob.
Ships as a single Python entry point. One argument --depth. Width, heads, learning rate, batch size, and total tokens all auto-derive from scaling laws.
That design bet is what makes ablations tractable for a single researcher on a single GPU.
Hypothesize → run → reflect → propose the next hypothesis. The loop is the product.
Agents that pick what to try next and run the experiment.
Shape: the agent generates candidates, runs them, reads the results, picks the next. The operator sets the frame.
Whether the operator or the agent picks the next experiment is the axis this talk cares about.
I've been running autoresearch — and harness engineering — on nanoGPT.
Nothing about the pattern is new. The nanoGPT README already flags it. What's worth talking about is the delta between running the agent once and running it fifty times — that's where harness engineering lives.
e/acc — building your own tools, skills, and (maybe) your own agent.
The layer you write on top of the base agent — scripts, skills, cached artifacts, guardrails, cost estimators, retry policy.
Optional: your own agent. PI-agent, a bespoke harness, whatever fits. You don't have to live inside Claude Code or Codex.
The models were trained on Claude Code and Codex-shaped harnesses. Off-the-shelf, the odds favor the harness the model was raised in.
A custom harness still makes sense — specialization, cost, sovereignty — but you're fighting the trained prior. Know the trade before you pay it.
Running nanoGPT on a cheap cloud GPU is a compilation problem before it's a training problem.
torch.compile writes, keyed by SM arch + PyTorch tag. sm86_pt24, sm89_pt24, sm80_pt24 — three files, not one.None of these is a novel idea in isolation. The value is that together, they turn a $0.44/hr GPU into a reproducible instrument.
The harness moves the setup cost from per-run to once-ever.
Once boot is free, the harness starts eating real experiments.
The point isn't the specific clustering result. It's that the same harness now runs a data-curriculum ablation with the same cost profile as a single training run — because setup is amortized.
» The 10× from the DevSec funnel — same math, different domain.
The whole thesis is affordable. Same trainer, different denominator. The math changes when each experiment gets cheap enough that you stop needing to plan them.
A transformer that does in-context learning on tables — row-wise, then cross-row attention.
TabPFN as a meta-learner for hyperparameters — trained on Kaggle.
A transformer that does in-context learning on tabular data. It ships with a semantic prior — it knows “software engineer in SF” predicts high income before ever seeing the label. World knowledge as a feature.
Same trick, applied to training hyperparameters: which knobs correlate with which outcome, across problems it has never seen.
Scrape Kaggle. Tabular datasets across every domain.
Auto-train. Small models per dataset, sweeping hyperparameters. Log (dataset features, params, outcome).
Feed TabPFN. Predicts good hyperparameters for a new dataset from its features alone — leveraging the semantic prior.
Cheap boot → auto-train → feed a meta-learner. Same pattern.
github.com/PriorLabs/tabpfn · the model is upstream. My second harness built the training set: Kaggle scraper + auto-trainer. Two harnesses, one thesis.
Every multiplier has a failure mode. Here are five.
Every knob I stopped touching became a tool.
Anthropic's performance take-home asks you to optimize the kernel.
My take-home is optimizing the harness around it.
Same craft — measurement, ablation, budgeted cost, honest numbers. One layer up.
The kernel is the innermost loop. The harness is the loop around it. Optimize both.
The kernel matters only when the harness stops being the bottleneck. For most of us, the harness IS the bottleneck.
The 10× is a function of skill count. Each solved-once problem becomes reusable leverage.
Claude Code, help me think about which of these to build next — and which one you would add first.