The Redis Guy Wrote a Local LLM Engine That Refuses to Be General. That's Why It Works.

·1 views

Salvatore Sanfilippo (antirez, the guy who wrote Redis) shipped a local inference engine called DwarfStar 4, or ds4. It hit the Hacker News front page this week and the repo is sitting around 23k stars after about two weeks. The pitch is one sentence from the README: The code is self-contained and deliberately narrow, not a general GGUF runner: you need to use the GGUF files the project produces. Everyone else is racing to support every model on earth. antirez went the other way.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Two of our guide pages are instructions and one is a list, so only one of them emits a HowTo

Try this: curl -s https://pub-trivia.app/guides/how-to-host-a-pub-quiz \ | grep -o '"@type":"HowTo"' # "@type":"HowTo" curl -s https://pub-trivia.app/guides/pub-quiz-round-ideas \ | grep -o '"@type":"HowTo"' # nothing Two pages in the same cluster, built from the same component, with the same metadata pipeline behind them. One of them is a numbered procedure a reader follows from start to finish. The other is a list of ideas you pick from. Only the first one is a HowTo, and the restraint is the part of structured data that is actually hard. We run a 72 page marketing site for quiz software.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

null meant unlimited, so for a while our free trial could build more question packs than Pro

Here is a bug that passes review, passes types, and reads correctly in both of the places it is wrong. trial: { // ... maxCustomPacks: null, // no custom packs on the trial }, pro: { // ... maxCustomPacks: 5, }, The interface says what null means, two lines above: /** Max custom question packs. null = unlimited */ maxCustomPacks: number | null So the trial had unlimited custom question packs and Pro, which people pay £30 a month for, had five.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

How to Do Amazon Keyword Research with Python

Amazon keyword research starts with one question: what do shoppers actually type into the search bar? The most direct answer is Amazon's own autocomplete. When you type "coffee b", Amazon suggests "coffee beans", "coffee bean grinder", and "coffee bar accessories". Those suggestions are coming from real search behavior. Amazon Homepage Most free Amazon keyword research tools are built on the same data, but they limit how many lookups you can run, and it's hard for you to integrate them into your own workflow.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

5 fun, easy-to-start, runnable creative projects for JEV | 5个好玩、好上手、能直接跑的创意项目

一句话先记住TEV能干啥 JEV*不会写作文、不会讲故事，它就像一个超快的选择题阅卷员*。你一次性丢给它好几个判断题/单选题/打分题，它一瞬间全部做完，每一题附带「我有几成把握」的概率。搭配一个会写东西的大模型（System2）一起玩，才出彩。大模型负责思考、写内容；JEV负责快速判断、做选择、把关校验。思路分支判断、选项选择、状态校验。玩家输入一句话，TEV并行一次性判断多件事： Noul：玩家这句话是不是攻击NPC？（是/否+概率） Choice：玩家动作属于【交谈 / 偷东西 / 逃跑 / 战斗】哪一类 Score：NPC愤怒等级（1平静～5暴怒）代码写规则：如果TEV判断「攻击」概率>0.8，直接触发战斗线；如果置信度低（0.4~0.7），交给大模型仔细理解；低于0.3，按普通对话走。亮点大量分支自动分流，游戏手感丝滑。你甚至可以做：TEV判断任务是否完成，满足条件自动解锁结局。 System1=TEV（快直觉）；System2=Qwen/Llama（慢思考）分工 TEV（高频调用，便宜快） Choice：我下一步该调用哪个工具？【搜索 / 读文件 / 代码执行 / 直接回答】 Noul：当前任务做完了吗？要不要继续思考？ Noul：模型输出内容有没有违规？是不是幻觉？大模型（低频调用，耗资源）只在TEV拿不准的时候（概率落在中间区间），才调用大

0 comments Read more at DEV Community