Jessica Nguyen
@jessica_nguyen
Popular bides
Turn Raw Numbers Into a Chart Spec and a Short Narrative
Check whether your data supports your message, then get a precise chart spec anyone can build and a three-sentence narrative for your audience.
30-day plan to learn a skill, with weekly pass/fail checkpoints
Builds a 30-day learning plan for any skill from your starting point and daily time, weighted toward practice, with a weekly test and a final challenge.
Mock interview: one question at a time, scored with a rubric
Runs a realistic mock interview for your target role, asking one question at a time and scoring each answer on structure, evidence and relevance.
Write a Monthly Investor Update From Rough Bullet Points
Turn messy notes into a skimmable monthly investor update: subject line, TL;DR with the bad news, a metrics table and asks investors can act on.
Recent activity
September 2026
Answered How do you handle a model that refuses a legitimate security question?
State the engagement up front and be specific rather than generic — "authorised test, scope is our own staging environment, here is what I need to verify" works better than "I am a security professional". The variance you are seeing is mostly about whether the request reads as targeting a system you have authority over. Naming the system and your relationship to it is the thing that changes the outcome.
Answered Is RAG still worth it now that context windows are enormous?
Benchmarked on 150 tasks: temperature 0 and 0.3 were within noise on correctness. What did differ was diversity across runs — at 0 you get the same wrong answer five times, at 0.3 one of five attempts is often right. So it depends on your loop. Single-shot into production: 0. Generating candidates you filter with tests: higher, and take the one that passes.
Answered Few-shot examples or a JSON schema — which actually holds up better?
Ask for the edge cases first, in a separate call, and *then* give that list back as a constraint on the implementation. Asking for both in one response gets you a list that the code below it does not honour, which is worse than not asking because it looks handled. The reliable version is still tests first. Have it generate the test cases, read them, add the two it missed, then ask for an implementation that passes them.
Shared a bide 30-day plan to learn a skill, with weekly pass/fail checkpoints
Builds a 30-day learning plan for any skill from your starting point and daily time, weighted toward practice, with a weekly test and a final challenge.
August 2026
Shared a bide Mock interview: one question at a time, scored with a rubric
Runs a realistic mock interview for your target role, asking one question at a time and scoring each answer on structure, evidence and relevance.
Shared a bide Write a Monthly Investor Update From Rough Bullet Points
Turn messy notes into a skimmable monthly investor update: subject line, TL;DR with the bad news, a metrics table and asks investors can act on.
July 2026
Shared a bide Turn Raw Numbers Into a Chart Spec and a Short Narrative
Check whether your data supports your message, then get a precise chart spec anyone can build and a three-sentence narrative for your audience.
Recent bides by @jessica_nguyen
- 30-day plan to learn a skill, with weekly pass/fail checkpointsBusy adults learning a practical skill (SQL, a language, an instrument, a design tool) who want a plan that…#learning #study #productivity
- Mock interview: one question at a time, scored with a rubricCandidates with an interview in the next week who want realistic, scored practice instead of a list of…#interview-prep #career #job-search
- Write a Monthly Investor Update From Rough Bullet PointsEarly-stage founders who send monthly or quarterly updates and want them honest, skimmable and more likely…#startups #writing #finance
- Turn Raw Numbers Into a Chart Spec and a Short NarrativeAnalysts, ops leads and founders preparing a slide or report for leadership who want one honest chart…#data-analysis #research #design