Professor @uni_bamberg_of | privacy, information security, and ethics | digital teaching @dikule_uba | enthusiastic speaker | typography nerd | EN/DE

Bamberg, DE
Joined March 2008
Dominik Herrmann retweeted
Initially, I had Claude make this animation in 2D. It wrote the piano score and drew every frame in JavaScript. I gave this 2D version as reference to another Claude. Because the whole film was code, Claude was able to use its exact choreography and make the 3D one in Blender.
51
39
2
922
38,950
Dominik Herrmann retweeted
Over the last few weeks I've been running a few workshops on Practical AI for academics. I thought I would share the slides and reflect a bit on what I have learned. You can find the slides and some material here: claesbackman.com/ai_workshop…
8
69
4
340
28,752
Dominik Herrmann retweeted
This AGENTS.md fixes the 𝘁𝗵𝗿𝗲𝗲 𝗺𝗼𝘀𝘁 𝗮𝗻𝗻𝗼𝘆𝗶𝗻𝗴 𝗵𝗮𝗯𝗶𝘁𝘀 of Codex and Claude Code: writing backward-compatible code for a project nobody uses yet, never deleting old code and docs it no longer needs, and adding a pile of tests just to change a button color. After using them every day for months, the lines I'd want in there from day one are the ones at the top: if the project has no real users yet, skip compatibility and migrations, and go straight to 𝘁𝗵𝗲 𝘀𝗶𝗺𝗽𝗹𝗲𝘀𝘁 𝗰𝗼𝗱𝗲 𝘁𝗵𝗮𝘁 𝘄𝗼𝗿𝗸𝘀. Then a four-step loop: docs first → tests → smallest implementation → clean up. Copy and paste it into your AGENTS.md 👇
39
25
2
484
36,332
Dominik Herrmann retweeted
A week of Claude Code sessions is too much to remember. Every weekend, have Opus 5.5 vibe-code a quick 𝘄𝗲𝗲𝗸𝗹𝘆 𝗰𝗮𝗹𝗲𝗻𝗱𝗮𝗿 like this from your local session logs. Then give it 𝗮 𝘀𝘂𝗯𝗮𝗴𝗲𝗻𝘁 𝘁𝗵𝗮𝘁 𝗼𝗻𝗹𝘆 𝗯𝘂𝗶𝗹𝗱𝘀 𝘄𝗲𝗲𝗸𝗹𝘆 𝗰𝗮𝗹𝗲𝗻𝗱𝗮𝗿𝘀: → Name it week-calendar, set its effort to medium, and preload a design skill → The first time, it asks which colors you like and whether to color by project or by task, and saves that to memory. After that, every calendar follows it → Call it when you want to look back on the week or write a weekly report. It regenerates the calendar and writes up a 3-line weekly report for you → The calendar shows four things: when you worked each day, what each session did, 𝘄𝗵𝗶𝗰𝗵 𝘀𝗲𝘀𝘀𝗶𝗼𝗻𝘀 𝘀𝘁𝗼𝗽𝗽𝗲𝗱 𝘄𝗶𝘁𝗵𝗼𝘂𝘁 𝗮 𝘀𝗶𝗻𝗴𝗹𝗲 𝗰𝗼𝗺𝗺𝗶𝘁, and how many hours each project took this week Send this prompt to Claude Code 👇 "Set up a subagent that only builds weekly calendars: 1. Create week-calendar in ~/.claude/agents: model: opus, effort: medium, memory: user. Preload the design skills I have installed (for example impeccable). Give it Bash so it can run git log and the script that builds the calendar. It only writes files to ~/.calendar/ and its own memory. 2. The first time, it asks me what style I like: dark or light, one accent color, color by project or by task type, and whether the week starts on Monday or Sunday. It saves my answers to memory and follows them every time. 3. The calendar is one HTML file. The script writes the data straight into it, so it opens with a double-click. Use this week's session logs: Claude Code's are in ~/.claude/projects/ (skip the subagents folders), and if I use Codex, add ~/.codex/sessions/. Before writing the script, open one file to check the fields. Convert times to my local time zone, and use the cwd in each record to tell projects apart. One block per session; start a new block after any gap longer than 30 minutes. Clicking a block shows the project, start and end time, the model used, the session title (if there isn't one, sum up my first typed message in 3 to 5 words), my first typed message, and my commits and changed files in that repo during that time (skip folders that aren't git repos). Sessions that stopped without a single commit get a red outline and also go in a separate list. At the top, total this week's hours per project, counting parallel sessions only once. Keep everything local. 4. Add a rule to ~/.claude/CLAUDE.md: when I say "what did I do this week" or "write my weekly report", have week-calendar regenerate the calendar first, then write a 3-line weekly report from it: what I mainly got done this week, which project took the most time, and which no-commit sessions to pick up first next week. Show me the contents of the files you'll create or change, then explain the whole flow in words a 10-year-old could follow. Don't write anything until I confirm."
53
42
6
1,019
81,358
Dominik Herrmann retweeted
I asked Opus 5.5 to write, produce, and create me an educational 'cartoon' about The History of Light - using whatever resources it had available to it. I didn't expect it to make a 36 minute video and spend $200+ dollars though 😂 The study of light is genuinely fascinating, and we have spent thousands of years trying to understand it. This is that story. Opus 5.5 wrote and produced the entire film. I told it to use any keys in my keychain to generate the voices, create any images or video it might need, and to create whatever motion graphics it could to explain concepts in electromagnetism. It used > Gemini 3.8 Flash TTS for the narration, and I must say, it did an excellent job. > Lyrica 3 for the background music, which is also essentially perfect. > GPT Image 2.5, Nano Banana Pro and NB2 Flash for some of the scenes imagery It's certainly not perfect but I was still really impressed with how well it did producing the film. It's very interesting if you're a physics nerd like me. Opus is genuinely creative in a way that I've not really seen with other models. I just gave the model a few constraints and just let it make all the decisions end to end. It even wrote itself credits at the end lol. It's going to be so fun to create bespoke educational videos like this for my children to learn from
168
263
58
2,170
159,357
Dominik Herrmann retweeted
🔐 Days 3 & 4 of #ARES2026 featured research across AI, critical infrastructure, cyber risk, forensics, PQC & more. 🏆 Congrats to Best Paper winners Ralf Gundelach, Michael Mühlhauser & Dominik Herrmann! ✈️ Day 3 ended at Flygvapenmuseum with the banquet and choir performance. – at Sweden
1
4
149
Tippst du besser als die KI? 🤖⚽Zur WM 2026 haben wir ein Tippspiel gebaut, bei dem du nicht nur selbst tippst – du konfigurierst eine eigene KI, schaust ihr beim Tippen zu und trittst gegen sie an. Ist ChatGPT oder Claude besser? #KI #WM2026 tippspiel.wiai25.de/
71
Zum 25-Jährigen der Fakultät WIAI haben wir einen Stiftplotter aus der Werkstatt geholt. Auf wiai25.de/dein-muster/ könnt ihr ein eigenes Muster designen – wir zeichnen es auf A3, schwarz auf weiß oder Silber/Gold auf Schwarz. Auf Wunsch auch kleiner.
1
82
Wir plotten in vier Runden bis zum Fest. Die erste schließt am 26. Mai, 23:59 Uhr. Abholung am 26. Juni beim Fest in der WE5 in Bamberg, kostenlos. 20 Muster sind schon in der Galerie.
1
81
Ein Stiftplotter ist die einfachste Maschine, die zeichnen kann – drei Befehle reichen ihm: links/rechts, oben/unten, Stift hoch oder runter. Man programmiert dabei, ohne eine Zeile Code zu schreiben. Informatik zum Anfassen, passend zum Jubiläum.
39
4 Jahre lang haben wir im Bayer. Forschungsverbund ForDaySec.de untersucht, wie IT-Sicherheit im Alltag funktioniert. Informatik, Soziologie und Recht, 5 Unis, 8 Teilprojekte. Am Mittwoch (25.3.) stellen wir die Ergebnisse in München vor. 1/2
2
1
114
Dominik Herrmann retweeted
Let me blow your mind real quick: When you use Remote Desktop (RDP), Windows secretly takes screenshots of what you are doing. It’s called the RDP Bitmap Cache. To make the connection faster, Windows saves small tiles (images) of the remote screen to your hard drive in a bin file. Even if the session is over and the remote server is destroyed... your laptop still holds the cache files. Forensics teams use tools like BMCViewer to stitch those tiles back together. They won't just see logs but the literal email, document, or picture you were looking at. 💀
165
1,538
84
13,288
850,141
Dominik Herrmann retweeted
In security, when you do your job perfectly, nothing happens. And people don't see when nothing happens.
36
229
46
1,116
105,374
Finally! An LLM grades 3000 free-text exam answers – while I drink coffee! Too good to be true? Exactly. After field testing at Uni Bamberg: We’re not grading faster with AI, we’re grading twice. 🧵
1
170
Made me chuckle, but totally right. 37 iterations later at 3 AM: Procrastination in the AI age. But quality improved.
1
73
Part 2 of my series on exams and AI is live: Automated grading, prompt injection (the LinkedIn flan experiment!), and why we spend more time discussing AI policies than actually teaching. Bike-shedding at its finest. uni-mal-anders.de/en/shorts/… #HigherEd #AI #AcademicTwitter
83
70% fail the final exam. 60% fail the retake. Less than half pass. Our intro programming course numbers – not unique. The disturbing part? By Week 4, students know they can’t program. Four months later: still can’t. Nothing changed. Why? uni-mal-anders.de/en/shorts/…
1
1
105
What can I do? Mandatory mid term tests? Legally not allowed. Mandatory exercises? Only voluntary – outsourced to AI. Labs? Not feasible with 250 students, 5 TAs. The German university system only allows subtle incentives. No binding structures.
1
82
Unlimited exam attempts. Optional exercises. No mandatory checkpoints. Is 70% failure about personal responsibility – or a system designed to produce it? I refuse to lower standards until we ask: “Name a language starting and ending with C.” That’s theater, not education.
1
88