Please confirm you are human

This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.

A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.

Hold with a pointer, or hold Space or Enter.

News

DEV Community
dev.to > ryan_zhao > deepseek-r1-the-open-source-reasoning-revolution-that-changes-everything-48m6

DeepSeek R1: The Open-Source Reasoning Revolution That Changes Everything

1+ hour, 37+ min ago   (16+ words) The... Tagged with ai, deepseek, moe, reasoning....

DEV Community
dev.to > ashish_sinha_5241c7673d93 > i-described-1245-tables-with-an-llm-and-retrieval-got-worse-58a

I described 1,245 tables with an LLM and retrieval got worse

5+ hour, 49+ min ago   (1126+ words) The cataloguing step is supposed to be the easy win. You have a schema whose tables are called ecm_template_link and v_pmpm, your users ask questions in English, and the gap between those two vocabularies is why retrieval misses. So you point a…...

DEV Community
dev.to > n1x3n > what-has-working-with-multiple-languages-been-like-on-your-projects-2118

What has working with multiple languages been like on your projects?

6+ hour, 32+ min ago   (236+ words) Hey everyone. I’m exploring a programming-language project and want to understand how people currently work across languages. Thinking about your most recent project where code in different languages needed to work together: What were you building, which languages were involved,…...

Medium
medium.com > @umeshcapg > the-database-connection-pool-was-configured-with-50-connections-so-why-did-the-20th-request-time-e559f67397cb

The database connection pool was configured with 50 connections, so why did the 20th request time…

6+ hour, 3+ min ago   (30+ words) The database connection pool was configured with 50 connections, so why did the 20th request time out? Understanding how parallel database queries inside a single HTTP request can exhaust your …...

Medium
medium.com > @AIbatros > openai-lets-you-swap-embedding-models-in-one-line-59885c0ef9f2

OpenAI Lets You Swap Embedding Models in One Line.

6+ hour, 19+ min ago   (31+ words) Your Vector Database Won’t Tell You It Broke Everything. Same dimension count, same index, no error message — and retrieval that quietly stops …...

DEV Community
dev.to > mahirhir > the-measurement-in-my-permanent-log-was-a-string-literal-4gd5

The measurement in my permanent log was a string literal

10+ hour, 52+ min ago   (474+ words) This line is in a record I cannot edit, because the record is append-only and that is the point of it: It reads as a measurement that found nothing. It is a placeholder. The three zeros are characters in the…...

DEV Community
dev.to > mahirhir > my-negative-test-stopped-being-negative-when-a-config-file-grew-by-four-rows-1hi0

My negative test stopped being negative when a config file grew by four rows

11+ hour, 17+ min ago   (528+ words) A test whose entire job was to prove a rule gets refused had quietly started proving that the rule passes. It plants a violation and asserts the checker rejects it. It had been green for weeks. It was green because…...

Medium
medium.com > @0s.and.1s > llm-discussions-01-training-vs-inference-3186217ba0b3

LLM Discussions (01): Training Vs. Inference

7+ hour, 35+ min ago   (92+ words) Training is Largely Compute-bound & Inference is Largely Memory-bound — But Why? If this is the first story you have come across in our LLM Discussion …...

Medium
medium.com > @guptanikhil8424 > llm-vs-gpt-the-difference-i-wish-someone-had-explained-to-me-sooner-3ce78cd97251

LLM vs GPT: The Difference I Wish Someone Had Explained to Me Sooner

7+ hour, 58+ min ago   (246+ words) A few months ago, someone asked me a question that stopped me cold. “So is GPT the same thing as an LLM, or not?” I opened my mouth to answer and realized I didn’t actually know. I’d been throwing around…...

DEV Community
dev.to > shohruh_sharipov > your-app-went-viral-adding-servers-made-it-worse-heres-why-nhd

Your app went viral. Adding servers made it worse. Here's why.

12+ hour, 32+ min ago   (94+ words) It's midnight, someone huge shares your app, 100,000 people show up — and the page dies. You add three servers. It gets worse. The rule that finally made this click for me: before you add capacity, find out where the request is…...