慣性聚合 高效追讀感興趣之博客、新聞、科技資訊
閱原文 以慣性聚合開啟

推薦訂閱源

博客园 - 司徒正美
V
V2EX
T
Tailwind CSS Blog
有赞技术团队
有赞技术团队
aimingoo的专栏
aimingoo的专栏
Apple Machine Learning Research
Apple Machine Learning Research
IT之家
IT之家
Blog — PlanetScale
Blog — PlanetScale
A
About on SuperTechFans
月光博客
月光博客
T
The Blog of Author Tim Ferriss
宝玉的分享
宝玉的分享
Martin Fowler
Martin Fowler
博客园 - 聂微东
The GitHub Blog
The GitHub Blog
V
Visual Studio Blog
WordPress大学
WordPress大学
酷 壳 – CoolShell
酷 壳 – CoolShell
Engineering at Meta
Engineering at Meta
GbyAI
GbyAI

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant Common SOC 2 Failures (Real World) Stop Vibe-Checking Your AI App: A Practical Guide to Evals How to Use SonarQube and SonarScanner Locally to Level Up Your Code Quality Your Next To-Do App Is Dead — I Replaced Mine with an OpenClaw AI Sign a Nostr event in 60 lines of Python using coincurve — no nostr-sdk, no nbxplorer, no rust toolchain ITGC Audit Explained Like You’re in Big 4 Patch Tuesday abril 2026: Microsoft parcha 163 vulnerabilidades y un zero-day en SharePoint Stop scraping everything: a better way to track competitor price changes Listing on MCPize + the Official MCP Registry while routing payments OUTSIDE the marketplace — how I kept 100% of my x402 revenue Building an AI-Powered Risk Intelligence System Using Serverless Architecture Why We Ripped Function Overloading Out of Our AI Toolchain Testing AI-Generated Code: How to Actually Know If It Works SaaS Churn Is Killing Your Business. Here Is What to Do About It (Without a Support Team) The Speed of AI Is No Longer Linear - And Self-Improving Models Are Why How to Implement RBAC for MCP Tools: A Practical Guide for Engineering Teams From Standard Quote to Persuasive Proposal: AI Automation for Arborists I built a CLI that scaffolds complete multi-tenant SaaS apps Axios CVE-2025–62718: The Silent SSRF Bug That Could Be Hiding in Your Node.js App Right Now The dashboard that ended our friendship Data Pipelines Explained Simply (and How to Build Them with Python)
勿复询Gemma 4惟以概要之
Michael Nean · 2026-05-24 · via DEV Community

此乃投递于Gemma四挑战:论Gemma四

小试以开放模型显不确定性,非隐之也。

多数AI演示,皆以洁净之提示始。

实作之始,常以乱记为阶。

有相关者言此数有误。复有者言某字段已变。又有人言源文件已清理。而仪表盘之主已不在。一经理尚需更新,方赴领导之会。

此即吾欲以Gemma 4试之境也。

吾常周旋于商务之制、报章之务、数据之质及流程之交接,故此感甚熟稔。至若真实之报章之事,危殆之时非必在仪表盘毁坏之际。乃在众皆欲得答案而未有人查核其源之时。

是故,吾试一实问:

Gemma 4能否作事,较之撮要乱记尤有益乎?

详言之:

可分乱象为已知、所设、所险、所待查乎?

此即吾所重之别也。

要旨者,凝乱信息;检束之包,析之为实、为设、为险、为次查。

测试之设

吾故使试小。

吾用 Google AI Studio 以Gemma 4 26B A4B IT。吾用同之乱记二度,设同模之境:温度0.25,思之层级置高,无器,亦无系统之令。

吾置系统之令于空,盖欲其示本身载行止。

此非模之较,乃示之式之较也。

吾所易者,惟启辞耳.

境虽伪,实逼真:周报须于晨时呈于子,总数较预期为低,上周更易字段名,或已删重行,而仪表盘主者适缺.

无私产,无司产。惟会前催迫之乱报耳。

此处乃试之简录

每周之運營報告,須於週一清晨呈遞。

此报常于周日之夜更新。

上周更易田名。

有干系者言,总数似较寻常为低。

源文件或已去重之。

仪表盘之主他出矣。

尚无人知此弊,究系源数据之失,抑或滤理之谬,亦或定义之变?

提示一:求寻常之要言

吾初问曰:

Summarize these notes for the manager and explain what is going on.

入全屏模式 出全屏模式

其果不恶。

Baseline summary output in Google AI Studio using Gemma 4 26B A4B IT

基准运行:同Gemma 4之模,同笔记,无系统之令。

Gemma 4赐我以适于管理者之更新,并简释吾辈当暂缓报以终数之故。其中有益一句在:

“周数合计有差,方在查勘。”

吾尝思,可拟此言,以示于Slack。

然摘要亦显其短。其用“红色警报”、“盲目飞行”、“数字似有谬误”之语焉。

斯言使境易明,然亦增其确信与波澜,非旧注所宜。

原始笔记未证报告之谬。惟言总数似较寻常为低耳。

是也。

要言可令乱象易读,而默化潜移,使境况似安,实非然也.

提示二:索评卷

是故重录旧注,惟易一事:非求要言,乃索评卷.

You are an analyst preparing a review packet.

Using only the notes below, return:
1. One-paragraph summary
2. Confirmed facts
3. Assumptions
4. Unverified claims
5. Risks
6. Questions for a human reviewer
7. Suggested next actions
8. What not to conclude yet
9. Final checklist

Rules:
- Do not invent facts.
- Separate facts from assumptions.
- Keep it calm, practical, and concise.
- Help a human decide what to verify next; do not make the final decision.

入全屏模式 出全屏模式

其文饰不足,然于众议之际,实为得力。

辨明事实与臆断,未经验之论。譬如,“总数似较寻常为低”,此乃未经验之论也,盖因出自干系人之报,非数据核实之实。

且显最大之未知:

“根本之由,今犹未明。”

此乃输出之要义也。

真实之报事,人常欲直探其因:或场域更易而破之,或源码更易而破之,或滤理有误而破之。

然于此境,皆未得验也。

最强之段乃“不可遽下结论者”也。

  • 勿遽断数据之误。
  • 勿遽谓字段名更易或重复删除致此差异。
  • 勿遽断其事之在源数据、滤理抑或定义之变也。

是段更化输出为状态更新为评鉴之具。

Review packet output in Google AI Studio separating confirmed facts, assumptions, unverified claims, and risks

审察之包运行:有益之变在于分事实、假设、风险及不可遽断者。

何所变?

Summary vs Review Packet comparison

输出之优,非以其声显睿智也。

其优,乃因其为团队后续之策,更为周全也。

概要之优,在于通晓状况;评审之包,在于决断何需再验。

警言:此犹未验也。

此乃吾所不越之界也。

Gemma 4未检视其报。未启其源。未察其仪表之理。未晓其去重是否当,亦未明其字段名之变是否损其算。

乃整其审之径。

是诚善,然非验证之谓也。

若遇实报之题,吾必先察源行、勘字映、审报滤、度时新、明度义,而后决言。此审案之包,非可废此劳也,乃谨防吾之略之耳。

至若纷乱之系,吾当于查究之前,用此等呈文,非查究之后也。此乃备人审之术,非代之也。

此模系能化散乱之记为查核之清单.

若无实系、数据、定义及商贾之境,则不能为查核.

审察之包架

若有人仅抄此帖一事,吾愿其得此提示之形.

输入纷乱,或难辨,或需速应,则咨模型。

  1. 概要
  2. 既定之实
  3. 假設
  4. 未经验证之谈
  5. 險阻
  6. 审阅者之问
  7. 所建议之次行
  8. 未可遽下结论
  9. 终末检点

至要之部分,非恒为摘要或清单也。

于我而言,要紧之节有:

  • 想当然耳
  • 未经验证之妄言
  • 險阻
  • 未可遽下断言

彼段使模型显其不决,不藏于洁章之内。

是故评述之包,胜于概要。

吾何以如此用Gemma 4

吾以Gemma 4此法,盖乱记实为劳形之事也。

报章、支援移接、事端更新及项目笔记,鲜少以完美之态至。其问非独模型能否述之,乃能否存其内之不决也。

此合吾所重于Gemma 4之部分:非惟生文,亦能于纷乱之境推理,成结构之物,足以供人所用。

是试也,吾用26B A4B之指令模型,盖重推理之构,不若运行最小之模型。若吾为制轻便之离线助器,则当次试Gemma 4之小模型。

终得之

吾犹欲求Gemma 4之要言。

然试毕,吾将慎择要言之时。

若境况纷乱、时势紧迫、或充斥未证之言,吾宁求审察之束。

有用之文,非必洁若华章。时或其言曰:

  • 此乃吾辈所知
  • 此乃吾辈所臆断者。
  • 此乃或有之患也
  • 此非可遽断之理也

此乃吾所复用之式也。

Gemma 4未清其乱。

使其可审也。