Tagged · LLM
Field notes,
LLM.
37 articles in this tag — part of the Jaypore Labs journal.
- 01Engineering
Retry strategies that don't compound errors
Apr 30, 20263 min read - 02Engineering
Fall-back chains: cheap → expensive → human
Apr 27, 20263 min read - 03Engineering
Self-consistency: when N=3 beats a smarter prompt
Apr 24, 20263 min read - 04Engineering
Pinning model versions through provider migrations
Apr 22, 20262 min read - 05Engineering
Drift catchers: detecting style shifts
Apr 21, 20262 min read - 06Engineering
Prompt invariance: prompts that survive paraphrase
Apr 21, 20263 min read - 07Engineering
Context engineering: what to load, what to defer
Apr 20, 20264 min read - 08Engineering
Output validation: pydantic, zod, and friends in production
Apr 20, 20262 min read - 09Engineering
Versioning model + prompt as a unit
Apr 20, 20263 min read - 10Engineering
Constrained decoding: the underrated lever
Apr 16, 20263 min read - 11Engineering
Confidence calibration: when 'I don't know' is the answer
Apr 15, 20263 min read - 12Engineering
Counter-example mining
Apr 15, 20263 min read - 13Engineering
Caching deterministic prefixes
Apr 10, 20263 min read - 14Engineering
The judge pattern for confidence
Apr 9, 20263 min read - 15Engineering
Hallucination checks: cite-or-it-didn't-happen
Apr 3, 20263 min read - 16Engineering
Red-teaming your own prompt
Apr 3, 20263 min read - 17Healthcare
What medieval scribes teach us about AI scribes
Mar 30, 20265 min read - 18Engineering
Structured output: JSON mode, schemas, why one beats the other
Mar 30, 20267 min read - 19Engineering
Idempotency keys for LLM calls
Mar 27, 20263 min read - 20Engineering
Prompts are recipes, not spells
Mar 27, 20264 min read - 21AI
RAG is a public library (and Dewey was right)
Mar 24, 20264 min read - 22AI
Your AI agent should plan like a kitchen brigade
Mar 23, 20265 min read - 23Engineering
Why probabilistic systems still need deterministic contracts
Mar 20, 20267 min read - 24Engineering
Refusal grammars: predictable, not surprising
Mar 20, 20263 min read - 25Engineering
ML: eval harness from a spec
Mar 19, 20264 min read - 26Engineering
The deterministic-envelope pattern
Mar 17, 20263 min read - 27Engineering
Few-shot drift: why golden examples poison new versions
Mar 16, 20263 min read - 28Engineering
Temperature, top-p, and the production tradeoff
Mar 10, 20263 min read - 29Engineering
Output post-processors that don't hide the truth
Mar 6, 20263 min read - 30Engineering
Determinism for tool calls: keys, ordering, side-effects
Mar 4, 20262 min read - 31Engineering
Output diffing in CI
Mar 4, 20263 min read - 32AI
Small models are underrated: a case for boring infrastructure
Feb 24, 20264 min read - 33Engineering
Multi-model routing: the dispatcher pattern for LLMs
Feb 20, 20264 min read - 34Engineering
Semantic caching: why your top 1% of queries cost 60% of your bill
Feb 17, 20264 min read - 35Engineering
AI cost attribution: a chargeback model for LLM spend
Feb 12, 20264 min read - 36Engineering
RAG vs. fine-tuning: a 90% decision tree
Jan 22, 20264 min read - 37Engineering
Token economics: what your unit cost actually is
Jan 19, 20264 min read