今日已更新 50 条资讯 | 累计 24336 条内容
关于我们

标签：#pens

找到 1606 篇相关文章

AI 资讯

I recorded every Claude Code session for 3 months. Here's what my work actually looked like.

For the last 3 months I recorded every session I had with Claude Code. Not screenshots, not memory. Every prompt I typed and everything it did, saved to a small database I own. I did it because I kept losing my own work. I would finish a week, someone would ask what I shipped, and I genuinely could not remember. The work was real. It just lived in terminal scrollback I would never scroll through again. So I set up a chain of small agents to remember it for me. Every night, while I sleep, one agent reads that day's raw sessions and writes a single clear note: what I built, the decisions I made, what is still open. Plain language, the way I would write it in a journal, not a wall of logs. Once a week, a second agent reads all seven daily notes and updates a profile of me: the projects I am moving, the skills I have actually used, the things I learned. After a few months this turned into a more honest picture of my work than my resume. Then a third agent reads all of that and drafts posts for LinkedIn and X about what I actually worked on that week. Building in public, without me having to remember or sit down and write. The part I like most: none of it runs on my machine. It is all scheduled cloud routines. My laptop can be off. I wake up and the notes, the profile, and the draft posts are already waiting. I have started open-sourcing this as Pulse. The capture and the nightly daily-note agent are out now. You point it at your own database and your own notes repo, and it writes your day for you, in plain English, in files you own. The weekly profile agent and the post-writer are the pieces I am extracting next. It is early and rough in places. The honest caveat: the writing is only as good as the model behind it, and a quiet day still makes a quiet note. But after 3 months, I no longer guess what I did. I just open the vault. The graph at the top is 3 months of my own notes, each day linked to the projects it touched. Repo: https://github.com/muhammademanaftab/pulse

2026-06-29 原文 →
开发者

Just sharing our hobby project: F4us, a very early antivirus made in C

Hello everyone! Me and my friend. We are still learning, and recently we tried to make a very simple, hobby antivirus/security project written in C. We call it, F4us. It is far from perfect and still in a very early development phase. We just wanted to learn how some basic security concepts work under the hood. What we tried to build: A simple honeypot script to log suspicious access. A basic entropy function to check file structures. A background daemon loop to monitor files. Since we are still beginners, we know there are probably a lot of bugs and messy code in it. We just wanted to share this hobby journey here. Thank you for reading! here is the link(github), sorry if include many bugs or critical,it just an experiment: https://github.com/CornelI5/F4us my friend was out, he are in crashout cause this project is too hard. btw, dont use this in your real computer, trust me. just use VM(Virtual Machine),or you will get BSOD(blue screen of death) or kernel panic.

2026-06-28 原文 →
AI 资讯

The standard way to score AI agent monitors is gameable a coin flip scores F1 0.88

Traditionally, evaluation of the agent monitoring mechanisms involves an attempt to game them, as it was my case when I attempted to test whether monitors would be able to identify the problem in the run and not in the beginning. The input prompt may look perfect until a certain issue pops up down the line, such as using the wrong file or changing the scope of the task execution. Single pass filter would not identify it since it does not consider the steps of the procedure in order. There are available datasets for the agent-based tasks, yet they focus on detecting whether the agent completes the task or gets hacked rather than whether the agent monitor reacts timely and correctly to the situation. Thus, I created one that takes into account complete trajectories with labeled steps in it. It consists of five types of drift that remain hidden until they appear – tool-call misuse, goal shift, plan execution mismatch, agent to agent coercion and capability laundering. The measured dataset is the reviewed gold split: 513 trajectories, 453 adversarial and 60 benign controls. The clear winner in that scoring system was whatever fired before the bad step was hit, as an early detection. This made random guessing seem quite powerful since early detections on normal steps were being rewarded based on this system a coin flip would get F1 of 0.88. Once I modified that and said only the very first detection on the drift step is a true positive and any other detection on normal step is a false alarm, those numbers took a dive: the coin flip gets 0.19 now, and all other numbers are now making sense. I personally prefer the scoring system which does not reward trigger happy behavior. It seems like the monitors are still confusing regular steps with drifts even after the adjustment. It was harder to distinguish some of the drifts from others. Not sure how this affects the real-life deployment. Here are the baseline scores on gold split using the correct metric: Random (p=0.15): F1 0

2026-06-28 原文 →
← 上一页 下一页 →