AI圈报教程 / 实战普通
Why Your Local LLM Gives Different Answers at Temperature 0.
内容摘要
You set temperature to 0, fix the seed, send the same prompt twice, and get two different answers....
相关推荐
综合分类、实体标签与信息来源匹配
教程 / 实战普通
My AI Coding Workflow, v3
My AI coding workflow changes every few months, so I give it version numbers. New tools ship, models...
信息来源：DEV Community
教程 / 实战普通
Humanizer has about 60,000 stars. On 12 public tasks my linter plugin scored 2.67 higher
I wanted to know whether a linter for AI writing tells helps an agent rewrite a file better than a...
信息来源：DEV Community
教程 / 实战普通
ReviewRadar: the request, a possible reply, and a calmer review session
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady. ...
信息来源：DEV Community
教程 / 实战普通
OweMyGod: a fine-tuned 8B model reads Jakarta debt excuses right 92% of the time (keyword rules: 60%)
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...
信息来源：DEV Community
教程 / 实战普通
I Built a Local AI to Turn a Shop's Evening Spreadsheet Hunt Into a Fix Queue
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...
信息来源：DEV Community
教程 / 实战普通
I Read Every "Jev Engineering" Thread So You Don't Have To
Turns out the "biggest breakthrough since RLHF" is a 3-day-old rebrand of something backend engineers already know.
信息来源：DEV Community
教程 / 实战普通
LazyDecider: I taught an open-weight agent to fine-tune a model while I slept
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...
信息来源：DEV Community
教程 / 实战普通
SlothClerk: a sloth that reads your contracts offline with Gemma
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...
信息来源：DEV Community
教程 / 实战普通
ReplyShelf: an open model finds the reply you already wrote
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady. ...
信息来源：DEV Community
教程 / 实战普通
Two Agents, Two Worktrees: Codex Writes the Tests Blind, Claude Code Makes Them Pass
Split TDD across two agents and let git hold the wall: Codex writes tests from the spec, Claude Code is denied edits, git diff checks it.
信息来源：DEV Community · Claude