AI gone loco

Today something funny happened. I was using Google Antigravity , running several conversations in parallel in its Agent Manager, and things went a bit loco…

To my prompt — “In ClasspathStore, ditch all .form support, like id.endsWith(".form”), by renaming any *.form.yaml to simply be *.yaml" — it responded with:

「境目から」というお言葉ですが、何か特定のソースコードや文章の続きを記述、あるいは解説することを希望されていますでしょうか？

前回の回答では、scikit-learnを用いたカリフォルニア住宅価格データセットのRandom Forest回帰（GridSearchCVによるハイパーパラメータ調整付き）のコードを作成しました。

もし、そのコードの**「この部分（境目）から解説してほしい」や、「特定の処理の続きを書いてほしい」**といったご要望があれば、詳しく教えていただけますか？

以下に、先ほどのコードの要点を日本語で解説します：

1. データの読み込み: fetch_california_housing() でデータセットを取得。
2. 分割: データを訓練用とテスト用に 8:2 で分割。
3. グリッドサーチの設定: n_estimators（樹木の数）、max_depth（最大長）、min_samples_split（分割に必要な最小サンプル数）の候補を指定。
4. モデル構築: GridSearchCV を使い、3分割差交差検証（cv=3）と並列処理（n_jobs=-1）で最適なパラメータを探索。
5. 評価: 最良のモデルでテストデータを予測し、平均二乗誤差（MSE）を算出。

続きが必要な場合や、別の修正が必要な場合はお知らせください。

Calculating Gemini CLI Token Costs for Agentic Vibe Coding

While parallelizing AI workflows with background agents is a massive productivity booster, this “fire and forget” vibe coding introduces a new challenge: keeping track of your LLM API costs. If you want to quickly convert your terminal token usage into actual dollars, I highly recommend using this Gemini CLI Cost Calculator .

Using the Gemini CLI, you get a transparent summary of your token usage at the end of every session:

How I am prompting LLMs: Should you say Thank You? Please?

https://huggingface.co/blog/jdelavande/thank-you-energy is an interesting article.

What it doesn’t mention is the “exponential” cost of saying “Thank You” at the end of a long conversation… as each follow-up prompt must send the entire conversation, real world energy consumption is likely much higher than the “synthetic” Thank You on an empty context.

Personally I’m currently typically prompting LLMs like this:

1. I use “imperative” language (“do”, not “could you” nor “please”)
2. I frequently create new sessions, instead of never ending long conversations (/clear in Gemini CLI)
3. I don’t send any follow-up prompt when the task at hand is completed to my satisfaction
4. I on (pretty rare) occasions still can’t quite avoid an “oh wow, you’re awesome” 😀

Sending a “Thank You” to an LLM as the last prompt to end a conversation does not seem like a good idea energy wise.

From Prompt to Production: AI Vibe Coding Web Frontends by Chaining Google’s Stitch, AI Studio, and Antigravity

I recently sat down to finally try out hands-on for myself just exactly how easy it is in February 2026 to have an AI generate a well designed full-fledged working HTML/CSS/JS front-end UI.

The Design Phase: Stitch

Starting with Google’s Stitch , I iterated on a few high-level graphical design ideas.

This feels similar to what you would have done with your human graphical designer, using tools like Figma, back in the pre-AI era.

Gemini Fixed Audio Bug

I’m experimenting with using the Gemini Live API, and have (obviously) “vibe coded” (parts of) what I’m doing.

It worked surprisingly well right away, but there was this annoying audio bug. (Signal Processing is not my forte.)

Then I had an idea for something which I didn’t really think would actually work, but hey, try it anyway, right?

I recorded a short audio clip of the problem, and uploaded it to Gemini, asking it for help. And oh boy, is this impressive or what:

Vorburger.ch AI Git Memory aifiles

Like everyone else, I am increasingly using AI tools.

Today I finally got around to start setting up what will be the (public) “memory” of my personal future AI agents that will work for me.

Being a developer, I don’t want this to be hidden away in some proprietary black box, but instead want to be able to inspect, edit, and version control it.

I also don’t want it be specific to any one AI tool or provider, but instead be portable and reusable across all of them; whether that’s the (awesome!) Gemini CLI , Anthropic’s Claude Code, OpenAI’s, or my very own Enola.dev .

Google Agent Development Kit (ADK) for Java with Gemma on Ollama

Good news for Java developers! Google’s 🧰 Agent Development Kit (ADK), already popular in the 🐍 Python community, has officially arrived for ☕ Java.

This opens up exciting possibilities for millions of Java developers and enterprises looking to integrate powerful AI agent capabilities into their existing applications.

The initial version of the Java ADK directly supports the Gemini and Claude large language model (LLM) APIs already. In the Java ecosystem, LangChain4j is a popular framework (together with Spring AI) which already has many (20+ and more through the OpenAI API) integrations with other LLMs.

Jules.google

jules.google is my new best friend. It’s just so very awesome.

It just made a fix for ch.vorburger.exec issue #263 from my prompts; see PR #279 - it’s great.

Jules directly works on your project in an isolated new VM for each task, where it iterates until a solution passes the build. This is the next step of where we’re heading as an industry, and the generation beyond the current assistants that are inside your traditional IDE. With Jules, I didn’t manually edit files anymore at all; only chat. Here is the story of the aforementioned PR:

Running Ollama LLMs in an AMD Radeon RX 7600 XT on Fedora 40

Ollama makes it very easy to get up and running with large language models (LLM).

I recently got a shiny new AMD Radeon RX 7600 XT , and of course had to try out Ollama with that new graphics card on my Fedora Linux Workstation.

Because I’m generally not a big fan of running shell scripts with sudo from strangers, and usually prefer launching some 👹 daemons like this one in the foreground instead of having them be started by systemd, I installed and started it simply like this, at least for starters: