Meta tags:
description=llm content on DEV Community;
keywords=software development, engineering, llm;

Headings (most frequently used words):

the, to, llm, jev, and, for, model, ai, of, typesafe, models, is, what, developers, need, better, my, local, python, it, practical, guide, your, wrong, he, in, posts, dev, community, played, chess, landed, next, reasoning, claude, watermarking, code, know, does, rag, retrieval, or, relationships, 7b, thinks, kill, process, violent, crime, regex, beat, choosing, right, langchain, memory, agent, last, mile, how, use, system, one, prompt, didn, change, did, now, optimizing, 8gb, barrier, strategic, selection, clean, json, extraction, with, ollama, built, an, tuner, benchmarking, proved, me, four, times, says, co, invented, chatgpt, his, new, won, write, word, boris, cherny, steps, adoption, through, eyes, our, pipeline, day, intro, we, asked, 330, question, korean, half, them, answered, alphabet, trending, guides, resources,

Text of the page (most frequently used words):
llm (24), the (20), and (17), comments (16), follow (16), min (15), read (15), sep (15), add (14), comment (14), dev (12), for (12), model (11), your (8), local (7), python (7), with (6), jev (6), use (5), code (5), what (5), qwen (5), #claude (5), community (4), free (4), cyber (4), ollama (4), one (4), agent (4), 27b (4), posts (4), models (4), wrong (4), reactions (4), practical (4), guide (4), typesafe (4), developers (4), need (4), better (4), create (3), 2026 (3), built (3), software (3), that (3), open (3), you (3), coding (3), through (3), agents (3), chatgpt (3), new (3), gpt (3), how (3), maya (3), technonotes (3), hacker (3), programming (3), jula (3), markova (3), machinelearning (3), gabriel (3), anhaia (3), aagam (3), flow (3), nears (3), andrew (3), atsushi (3), hara (3), prosper (3), otemuyiwa (3), dhooooooh (3), langchain (3), right (3), bernard (3), amirul (3), rag (3), valerykot (3), mohab (3), abdelkarim (3), maxim (3), saplin (3), menu (3), account (2), log (2), keep (2), gguf (2), glm (2), flash (2), when (2), best (2), not (2), same (2), fable (2), opus (2), like (2), deep (2), dive (2), into (2), explained (2), setup (2), astra (2), ability (2), sort (2), top (2), latest (2), relevant (2), sign (2), testing (2), asked (2), 330 (2), question (2), korean (2), half (2), them (2), answered (2), alphabet (2), day (2), intro (2), boris (2), cherny (2), steps (2), adoption (2), eyes (2), our (2), pipeline (2), says (2), invented (2), his (2), won (2), write (2), word (2), tuner (2), benchmarking (2), proved (2), four (2), times (2), tutorial (2), clean (2), json (2), extraction (2), optimizing (2), 8gb (2), barrier (2), strategic (2), selection (2), prompt (2), didn (2), change (2), did (2), now (2), system (2), last (2), mile (2), choosing (2), memory (2), thinks (2), kill (2), process (2), violent (2), crime (2), regex (2), beat (2), does (2), retrieval (2), relationships (2), watermarking (2), know (2), played (2), chess (2), landed (2), next (2), reasoning (2), search (2), place, where, coders, share, stay, date, grow, their, careers, made, love, 2016, ruby, rails, powers, other, inclusive, communities, source, forem, terms, privacy, policy, conduct, mlh, shop, postgres, database, contact, about, showcase, organization, accounts, advertise, help, education, tracks, videos, challenges, home, space, discuss, development, manage, career, mlx, apple, silicon, which, format, should, actually, zhipu, weight, excels, reveals, alpha, was, its, multimodal, vllm, llama, cpp, happens, doesn, fit, 24gb, vram, courses, certificates, airllm, runs, 70b, 4gb, gpu, true, interesting, part, aider, opencode, ran, tasks, cli, rtx, 4070, getting, started, kiro, crew, want, using, teach, sonnet, behave, andrej, karpathy, llms, end, undetectable, text, watermark, freellmapi, openai, compatible, endpoint, providers, mac, mini, 16gb, qwen3, newest, vision, language, powerhouse, hugging, face, download, isn, stuck, being, rate, limited, gemini, ultimate, comparison, colibri, running, 744b, laptop, run, locally, real, sizes, cache, trick, template, trap, eli5, skill, works, superpowers, skills, pocock, three, philosophies, workflows, architecture, months, apart, different, kind, upgrade, muse, spark, review, just, jargon, douche, but, there, fix, switching, from, sol, start, medium, effort, engineer, reading, list, books, matter, trending, guides, resources, opensource, i18n, llmintamil, devops, typescript, reaction, selfhosting, softwaredevelopment, valyu, automation, evaluation, security, evals, left, 1005, older, post, hide, close, powered, algolia, navigation, skip, content,

Text of the page (random words):
llm dev community skip to content navigation menu search powered by algolia search log in create account dev community close llm follow hide create post older llm posts 1 2 3 4 5 6 7 8 9 75 1005 posts left menu sign in for the ability to sort posts by relevant latest or top right menu typesafe jev played chess and landed next to reasoning models maxim saplin maxim saplin maxim saplin follow sep 17 typesafe jev played chess and landed next to reasoning models ai evals llm agents 10 reactions comments add comment 3 min read is claude watermarking code what developers need to know mohab abdelkarim mohab abdelkarim mohab abdelkarim follow sep 17 is claude watermarking code what developers need to know ai claude coding llm 5 reactions comments add comment 7 min read does rag need better retrieval or better relationships valerykot valerykot valerykot follow sep 17 does rag need better retrieval or better relationships llm ai rag machinelearning comments add comment 8 min read my local 7b thinks kill a python process is a violent crime and my regex beat it amirul cyber amirul cyber amirul cyber follow sep 17 my local 7b thinks kill a python process is a violent crime and my regex beat it ai security evaluation llm comments add comment 4 min read choosing the right langchain memory a practical guide for developers bernard k bernard k bernard k follow sep 17 choosing the right langchain memory a practical guide for developers langchain ai python llm comments add comment 3 min read the agent s last mile dhooooooh dhooooooh dhooooooh follow sep 17 the agent s last mile ai agents llm automation comments 2 comments 5 min read how to use jev a practical guide to typesafe s system one model prosper otemuyiwa prosper otemuyiwa prosper otemuyiwa follow for valyu ai sep 17 how to use jev a practical guide to typesafe s system one model ai llm softwaredevelopment tutorial 5 reactions comments add comment 15 min read your prompt didn t change your model did now what atsushi hara atsushi hara atsushi hara follow sep 17 your prompt didn t change your model did now what machinelearning testing ai llm comments add comment 5 min read optimizing for the 8gb barrier strategic model selection for local ai andrew andrew andrew follow sep 17 optimizing for the 8gb barrier strategic model selection for local ai ai llm selfhosting ollama 5 reactions comments add comment 5 min read clean json extraction with ollama and python flow nears flow nears flow nears follow sep 17 clean json extraction with ollama and python llm programming python tutorial 1 reaction comments add comment 3 min read i built an llm tuner benchmarking it proved me wrong four times aagam aagam aagam follow sep 17 i built an llm tuner benchmarking it proved me wrong four times llm ai programming python comments add comment 5 min read he says he co invented chatgpt his new ai jev won t write a word gabriel anhaia gabriel anhaia gabriel anhaia follow sep 17 he says he co invented chatgpt his new ai jev won t write a word ai llm typescript machinelearning comments add comment 10 min read boris cherny s steps of ai adoption through the eyes of our pipeline jula markova jula markova jula markova follow sep 17 boris cherny s steps of ai adoption through the eyes of our pipeline ai llm programming devops comments add comment 29 min read llm day 1 intro technonotes hacker technonotes hacker technonotes hacker follow sep 17 llm day 1 intro llm llmintamil comments add comment 3 min read we asked 330 models a question in korean half of them answered in the wrong alphabet ai maya ai maya ai maya follow sep 17 we asked 330 models a question in korean half of them answered in the wrong alphabet llm testing i18n opensource comments add comment 4 min read sign in for the ability to sort posts by relevant latest or top trending guides resources the ai engineer s reading list for 2026 10 books that matter switching from gpt 5 6 sol to gpt 6 astra start with medium effort it s not just you opus 5 is a jargon douche but there s a fix muse spark 1 3 a review qwen 3 8 27b vs qwen 3 6 27b same architecture 4 months apart and a different kind of upgrade superpowers vs agent skills vs pocock three philosophies of ai coding workflows claude code s eli5 skill explained how it works setup and when to use it run qwen 3 8 27b locally real gguf sizes the kv cache trick and the template trap colibri running a 744b ai model on your laptop gpt 6 astra vs fable 5 1 vs gemini 3 8 flash the ultimate comparison your hugging face download isn t stuck you re being rate limited qwen3 8 27b a deep dive into qwen s newest vision language powerhouse best free local ai agent setup for mac mini m4 16gb freellmapi one openai compatible endpoint for 34 free llm providers the end of undetectable ai text claude s new watermark explained andrej karpathy s deep dive into llms like chatgpt want to keep using fable 5 teach opus and sonnet to behave like it getting started with kiro crew qwen code vs aider vs opencode i ran the same 12 tasks through 3 local cli agents on one rtx 4070 airllm runs a 70b model on a 4gb gpu it s true and that s not the interesting part 5 best free ai courses in 2026 with certificates vllm vs llama cpp vs ollama what happens when your model doesn t fit in 24gb vram glm 5 3 flash z ai reveals ox alpha was its open multimodal model glm 5 3 zhipu s open weight model excels at coding and cyber mlx vs gguf on apple silicon which local llm format should you actually use dev community a space to discuss and keep up software development and manage your software career home dev challenges dev videos dev education tracks dev help advertise on dev organization accounts dev showcase about contact free postgres database dev shop mlh code of conduct privacy policy terms of use built on forem the open source software that powers dev and other inclusive communities made with love and ruby on rails dev community 2016 2026 we re a place where coders share stay up to date and grow their careers log in create account