Ideas for building
better software.

Engineering perspectives on architecture, product development, AI, and the everyday decisions behind useful software.

From the engineering desk

Browse practical articles or follow the latest technology updates.

Subscribe via RSS →

Curated links from external sources — not 360Softy original articles.

ExternalSoftware Engineering

DEV Community8 Aug 2026

Fine-Tuning an Embedding Model on Your Own Data

Fine-tuning an embedding model is unusually cheap — a base model of a hundred million parameters, fifty thousand pairs and an hour on one GPU. What is not cheap is everything that happens after: a fine-tuned model is a new model, and every vector you have stored becomes incompatible on the day you deploy it. Fine-tuning pays when your domain’s notion of relevance differs from the general one the base model learned. Concretely: your users search with vocabulary the model has never associated with

aidatasciencellm

DEV CommunityRead original

ExternalSoftware Engineering

DEV Community8 Aug 2026

Filtering and Vector Search in One Query

Add WHERE tenant_id = 42 to a working vector query and one of two things happens: it gets slow, or it returns fewer rows than you asked for. Both are the same underlying fact — an approximate index and a filter cannot be applied at the same time — and the selectivity at which it becomes fatal is calculable in advance. A B-tree index and a GIN index can be combined: Postgres builds a bitmap from each and ANDs them. An HNSW index cannot participate in that, because it does not produce a set of mat

aidatabasetutorial

DEV CommunityRead original

ExternalSoftware Engineering

DEV Community8 Aug 2026

Few-Shot Prompting: How Many Examples Is Enough?

“How many examples” is two questions wearing one coat. The cost of another example is arithmetic you can do exactly. The benefit depends on what you believe examples are for — and the published evidence on that is more surprising than the advice built on it. Examples are input tokens on every single call, forever. Take a classification prompt whose examples run about 180 tokens each (input plus label plus the delimiters around them): shots prompt tokens $/call @ $3/M in $/month @ 200k call

aillmmachinelearning

DEV CommunityRead original

ExternalSoftware Engineering

DEV Community8 Aug 2026

A SaaS App Eval Ledger for Direct API Token Cost, Fallbacks, and a Unified Key

Short answer: don't choose an LLM API for a SaaS app from a public token-price table alone; replay a representative eval set through direct OpenAI, direct Claude API, and an OpenRouter-style routing path, then choose the smallest integration whose measured quality, billed usage, retry behavior, and recovery policy meet your release constraint. The cheapest path is workload-dependent. A low input rate can hide engineering overhead, while a chatty agent can turn one user action into several model

aisaaspython

DEV CommunityRead original

ExternalSoftware Engineering

DEV Community8 Aug 2026

Federated Learning, Practically: The Protocol and What It Does Not Protect

Federated learning trains a shared model across many devices without collecting their data on a server. That is a real and useful property. It is also routinely stated as though it were three properties, and the other two — that the server learns nothing about individuals, and that the resulting model cannot leak training data — are not true unless you add machinery that costs something. The canonical algorithm is federated averaging. One round looks like this: The server selects a cohort of el

aidevopsllm

DEV CommunityRead original

ExternalSoftware Engineering

DEV Community8 Aug 2026

Feature Stores and the Problem They Solve

A feature store exists because the same feature gets computed twice — once in a batch job for training and once in a service for scoring — and the two definitions drift apart. This page shows one feature breaking, in eight lines, and the join that stops it. The feature is avg_order_value_30d. It appears in a fraud model. The training set is built in the warehouse: -- training pipeline, run nightly over history SELECT o.order_id, o.customer_id, o.created_at, AVG(h.amount) OVER ( PARTI

aimachinelearningllm

DEV CommunityRead original

ExternalSoftware Engineering

DEV Community8 Aug 2026

What an Unused AI Feature Actually Costs

An AI feature that nobody uses is not free. It has three separate cost lines, only one of which stops when usage does, and the largest of the three is usually the one that is never written down. Here is how to total them with your own numbers, and what could have been known before the build started. The usual accounting for an unadopted feature is engineering time, treated as sunk and therefore ignored. That undercounts badly, because two of the three lines keep running for as long as the featur

aidiscussllm

DEV CommunityRead original

ExternalTechnology Trends

HN RSS Newest8 Aug 2026