开发者工具1 month ago
ModelBrew — AI you don't have to double-check
用您的数据微调语言模型并管理自定义事实，获得密码学删除证明。
@MBrew26730 · X
Dataset cleaning + fine tuning + continual learning at
完整作品展
技术栈
17 projects
用您的数据微调语言模型并管理自定义事实，获得密码学删除证明。
@MBrew26730 · X
Dataset cleaning + fine tuning + continual learning at
An intimate, aesthetic space where you see your life and the world's emotions reflected.
@app_starty · X
Track your emotions, manifest your dreams, connect with the world
Turn a public URL into a Lodven growth diagnosis preview before deciding whether to unlock the full report.
@chr1st1neldn · X
i'm currently building a marketing diagnosis and growth execution agent for small startup team and solo founders. It's still in early development phase and would welcome anyone to try out
LLM驱动的新闻聚合器，实时呈现和更新热门故事。
tdubey · HN
DWS A LLM Generated, "Drudge Report" style news site
3D骰子模拟工具，支持D4-D20，掷骰即得结果和总点数。
Nalife520 · V2EX
最近用 Codex 做了一个 3D 骰子！ 最近做了一个很小的网页工具：3D 骰子。 做完后有点纠结： 这种小工具到底应该保持极简，还是把常见功能都补上？ 抛骰子： https://wheelpage.com/zh/dice-roller/ Dice Roller： https://wheelpage.com/dice-roller/ 现在功能很简单：打开页面，点一下，骰子滚动，然后给出结果。 一开始觉得骰子就是 1 到 6 的随机数，应该很好做。 但做的时候发现，如果只是直接显示数字，又不太像“掷骰子”；做成 3D 动画，又担心有点多余。 现在倾向于先保持简单，打开就能用，不加太多设置。 顺便也做了一个抛硬币页面： https://wheelpage.com/zh/coin-flip/ 它和骰子类似，都是临时做随机决定的小工具。
压缩LLM提示词和文档以降低token使用和API成本
@marcusyul · X
THEY JUST GAVE AWAY 100 MILLION FREE TOKENS SO YOU CAN STOP BURNING THROUGH YOUR CLAUDE CODE BUDGET. if you code with AI you already know: the session fills up, starts failing, and on top of that you're overpaying there's a tool that fixes this: it shrinks the context before the model even sees it same model, same response, a fraction of the cost in a real session: from $154 to $43. a 72% drop and right now: → extend your Fable sessions in Claude Code → 100M free tokens to try it out you don't switch models you don't touch your code you just stop paying to repeat yourself link below ⬇️
Free psychoeducational self-help and coping tools for autism, ADHD, PTSD, and neurodivergent users — SUDS, feelings wheel, CBT/DBT skills, grounding. A companion to therapy, not a
@EricMRiesterer · X
is slowly turning into the most elite mental health toolbox on the entire internet... And it's free as well as coded for #neurodivergence #autism #ADHD #AuDHD #PTSD. 60+ apps, 300 modules. Free. #SaaS #PWA #MentalHealth
用你的LLM API密钥分析Hacker News公开个人资料。
Topfi · HN
Like everyone on HN, I love nothing more than to (re)read my own comments. Getting my intuition that I am among the smartest, most humble, highest quality commenters on here confirmed by an LLM so capable that the US government had to temporarily export restrict it [0] seemed only natural. Having had my perfection confirmed, I decided to share this joy with you as I had a few percent usage left before a reset. I took a few prompts, then did a review of the output which resulted in Selbstbild, a BYOK (Anthropic / OpenRouter) web app that gives you a summary and assessment of your public comments by one of our machine Gods, including Fable 5 (provided your can afford that luxury at API pricing). In all seriousness, I have, for a long time, used my own comments on social media (including HN) as part of a personal needle-in-haystack test, simply because I do know my somewhat peculiar style and what I tend to write, but also because I can sometimes write in a slightly confusing manner, ma
@launch_llama On-prem secure storage in LLMs. We think no one and no agent can crack our vault. 0 users, haha https://t.co/0xYnk4kw8d
@RedShiftAi · X
On-prem secure storage in LLMs. We think no one and no agent can crack our vault. 0 users, haha
实时可视化硬件在运行LLM推理时的性能指标
dev_dan_2 · HN
WatchMachineGo – A visualizer to show hardware performing LLM inference
