🚀 I just built my first ever 2D game - Death’s Job! 💀🎮 
A little ghost. A sky full of obstacles. And a lot of physics.

I started this project purely out of curiosity - 
“How do people make a game from scratch using something low-level like Pygame?”

So, I opened a new Python file… and a few days later, I surprisingly had most of the game logic working. 
Gravity, physics, collisions, obstacle generation - all fun to implement.

But then I hit the real boss fight in game development: 
🎨 finding assets that actually match. 
I was using random images from the internet… and the game looked like a cursed collage.

Then Diwali happened. Then my university exams happened. 
And the project sat untouched.

Once exams ended, I returned with fresh energy and decided to finish it properly. 
So, I generated matching sprites using Gemini + creative prompting, and honestly… asset creation was harder than the coding 😅

For sound effects and background music, I went digging through Pixabay and finally found pieces that fit the vibe.

Today - after polishing the UI, splash screen, physics, and gameplay. 
I’m proud to say the game is complete. 🎉

🎮 Death’s Job — Features

<ul>
<li>Interactive splash screen with animated buttons</li>
<li>Flappy Bird–style jumping with horizontal controls</li>
<li>Smooth physics (gravity, velocity, damping)</li>
<li>Pixel-perfect mask-based collision detection</li>
<li>Randomized obstacles with recycling system</li>
<li>Infinite scrolling cloud background</li>
<li>Jump/Collision SFX + looping background music</li>
<li>Auto-reset system</li>
<li>Runs at 60 FPS</li>
</ul>

🎥 Gameplay Recording Gif:

<a href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2F0xhi2ul08ia2zu8ouifw.gif" class="article-body-image-wrapper"><img src="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2F0xhi2ul08ia2zu8ouifw.gif" alt="Gameplay gif" width="426" height="240"></a>

🔗 GitHub Repository: 
<a href="https://github.com/IamVatsal/Deaths-Job" rel="noopener noreferrer">Death's Game</a>

This project taught me:

<ul>
<li>How game engines handle physics at a low level</li>
<li>How deceptively hard good asset selection is</li>
<li>How much polish simple games actually need</li>
<li>And how fun it is to give life to something you built from scratch</li>
</ul>

I’d love feedback, ideas, or critiques - especially from anyone into game dev or Python.

Thanks for reading! 😊

يتناول المقال إنشاء لعبة ثنائية الأبعاد بعنوان 'Death's Job'، تم تطويرها باستخدام Pygame. بدأ المطور هذا المشروع بدافع الفضول حول تطوير الألعاب. بعد تنفيذ منطق اللعبة في البداية، بما في ذلك الجاذبية والفيزياء، واجه المشروع تحديات في العثور على أصول مناسبة. بعد فترة توقف بسبب ديوالي وامتحانات الجامعة، عاد المطور لإنهاء اللعبة، حيث قام بإنشاء شخصيات متطابقة باستخدام Gemini والحصول على مؤثرات صوتية من Pixabay. المنتج النهائي يتضمن شاشة بداية تفاعلية، قفزات على طراز Flappy Bird، فيزياء سلسة، واكتشاف دقيق للتصادم.

El artículo trata sobre la creación de un juego 2D titulado 'Death's Job', desarrollado utilizando Pygame. El desarrollador comenzó este proyecto por curiosidad sobre el desarrollo de juegos. Después de implementar inicialmente la lógica del juego, incluyendo gravedad y física, el proyecto enfrentó desafíos para encontrar activos adecuados. Tras un descanso debido a Diwali y los exámenes universitarios, el desarrollador regresó para completar el juego, generando sprites coincidentes con Gemini y obteniendo efectos de sonido de Pixabay. El producto final cuenta con una pantalla de inicio interactiva, saltos al estilo de Flappy Bird, física suave y detección de colisiones precisa.

L'article traite de la création d'un jeu 2D intitulé 'Death's Job', développé avec Pygame. Le développeur a entrepris ce projet par curiosité pour le développement de jeux. Après avoir initialement mis en œuvre la logique du jeu, y compris la gravité et la physique, le projet a rencontré des difficultés pour trouver des ressources adaptées. Après une pause due à Diwali et aux examens universitaires, le développeur est revenu pour terminer le jeu, générant des sprites correspondants avec Gemini et trouvant des effets sonores sur Pixabay. Le produit final comprend un écran de démarrage interactif, des sauts de style Flappy Bird, une physique fluide et une détection de collision pixel-perfect.

The article discusses the creation of a 2D game titled 'Death's Job,' developed using Pygame. The developer embarked on this project out of curiosity about game development. After initially implementing game logic, including gravity and physics, the project faced challenges in finding suitable assets. Following a break due to Diwali and university exams, the developer returned to complete the game, generating matching sprites with Gemini and sourcing sound effects from Pixabay. The final product features an interactive splash screen, Flappy Bird-style jumping, smooth physics, and pixel-perfect collision detection.

Death’s Job Game

arXiv:1906.07172v5 Announce Type: replace-cross 
Abstract: Equivariant neural networks are a class of neural networks designed to preserve symmetries inherent in the data. In this paper, we introduce a general method for modifying a neural network to enforce equivariance, a process we refer to as equivarification. We further show that group convolutional neural networks (G-CNNs) arise as a special case of our framework.

Equivariant neural networks and equivarification

arXiv:2311.13745v4 Announce Type: replace-cross 
Abstract: Diffusion models have become the most popular approach to deep generative modeling of images, largely due to their empirical performance and reliability. From a theoretical standpoint, a number of recent works have studied the iteration complexity of sampling, assuming access to an accurate diffusion model. In this work, we focus on understanding the sample complexity of training such a model; how many samples are needed to learn an accurate diffusion model using a sufficiently expressive neural network? Prior work showed bounds polynomial in the dimension, desired Total Variation error, and Wasserstein error. We show an exponential improvement in the dependence on Wasserstein error and depth, along with improved dependencies on other relevant parameters.

Improved Sample Complexity Bounds for Diffusion Model Training

arXiv:2410.22995v2 Announce Type: replace-cross 
Abstract: A hallmark of advanced artificial intelligence is the capacity to progress from passive visual perception to the strategic modification of visual information to facilitate complex reasoning. This advanced capability, however, remains critically underdeveloped in current Large Multi-modal Models (LMMs). The deficiency is often masked by evaluation metrics that prioritize final-answer accuracy, creating an illusion of competence where genuine reasoning is absent. Using the domain of geometric problem-solving as a precise instrument, we probe this issue through tasks that require constructing visual aids. To this end, we introduce \textbf{VisAidMath}, a challenging benchmark, and our novel Three-Layered Funnel Evaluation Framework. This framework moves beyond simple accuracy (ACCU) to scrutinize the generation of valid visual aids (PVA) and the soundness of subsequent reasoning steps (SPRS). Our extensive experiments on state-of-the-art models, including Doubao-Seed-1.6 and o4, reveal a profound ``Reasoning Illusion''. We observe that high surface-level accuracy conceals a catastrophic failure in the models' ability to produce valid visual aids or to reason from them. Our findings expose a fundamental schism between visual perception and logical deduction in modern LMMs. We host an evaluation platform at CodaBench for testing publicly. Homepage: https://nlp2ct.github.io/VisAidMathHomepage/ Evaluation: https://www.codabench.org/competitions/7634/

VisAidMath: Benchmarking Visual-Aided Mathematical Reasoning

arXiv:2508.01249v3 Announce Type: replace-cross 
Abstract: Large Language Model (LLM) agents offer a powerful new paradigm for solving various problems by combining natural language reasoning with the execution of external tools. However, their dynamic and non-transparent behavior introduces critical security risks, particularly in the presence of prompt injection attacks. In this work, we propose a novel insight that treats the agent runtime traces as structured programs with analyzable semantics. Thus, we present AgentArmor, a program analysis framework that converts agent traces into graph intermediate representation-based structured program dependency representations (e.g., CFG, DFG, and PDG) and enforces security policies via a type system. AgentArmor consists of three key components: (1) a graph constructor that reconstructs the agent's runtime traces as graph-based intermediate representations with control and data flow described within; (2) a property registry that attaches security-relevant metadata of interacted tools \& data, and (3) a type system that performs static inference and checking over the intermediate representation. By representing agent behavior as structured programs, AgentArmor enables program analysis for sensitive data flow, trust boundaries, and policy violations. We evaluate AgentArmor on the AgentDojo benchmark, the results show that AgentArmor can reduce the ASR to 3\%, with the utility drop only 1\%.

AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt Injection

arXiv:2511.14691v1 Announce Type: cross 
Abstract: Attention is the brain's ability to selectively focus on a few specific aspects while ignoring irrelevant ones. This biological principle inspired the attention mechanism in modern Transformers. Transformers now underpin large language models (LLMs) such as GPT, but at the cost of massive training and inference energy, leading to a large carbon footprint. While brain attention emerges from neural circuits, Transformer attention relies on dot-product similarity to weight elements in the input sequence. Neuromorphic computing, especially spiking neural networks (SNNs), offers a brain-inspired path to energy-efficient intelligence. Despite recent work on attention-based spiking Transformers, the core attention layer remains non-neuromorphic. Current spiking attention (i) relies on dot-product or element-wise similarity suited to floating-point operations, not event-driven spikes; (ii) keeps attention matrices that suffer from the von Neumann bottleneck, limiting in-memory computing; and (iii) still diverges from brain-like computation. To address these issues, we propose the Spiking STDP Transformer (S$^{2}$TDPT), a neuromorphic Transformer that implements self-attention through spike-timing-dependent plasticity (STDP), embedding query--key correlations in synaptic weights. STDP, a core mechanism of memory and learning in the brain and widely studied in neuromorphic devices, naturally enables in-memory computing and supports non-von Neumann hardware. On CIFAR-10 and CIFAR-100, our model achieves 94.35\% and 78.08\% accuracy with only four timesteps and 0.49 mJ on CIFAR-100, an 88.47\% energy reduction compared to a standard ANN Transformer. Grad-CAM shows that the model attends to semantically relevant regions, enhancing interpretability. Overall, S$^{2}$TDPT illustrates how biologically inspired attention can yield energy-efficient, hardware-friendly, and explainable neuromorphic models.

Attention via Synaptic Plasticity is All You Need: A Biologically Inspired Spiking Neuromorphic Transformer

arXiv:2511.08955v2 Announce Type: replace-cross 
Abstract: Simulating microstructure evolution (MicroEvo) is vital for materials design but demands high numerical accuracy, efficiency, and physical fidelity. Although recent studies on deep learning (DL) offer a promising alternative to traditional solvers, the field lacks standardized benchmarks. Existing studies are flawed due to a lack of comparing specialized MicroEvo DL models with state-of-the-art spatio-temporal architectures, an overemphasis on numerical accuracy over physical fidelity, and a failure to analyze error propagation over time. To address these gaps, we introduce MicroEvoEval, the first comprehensive benchmark for image-based microstructure evolution prediction. We evaluate 14 models, encompassing both domain-specific and general-purpose architectures, across four representative MicroEvo tasks with datasets specifically structured for both short- and long-term assessment. Our multi-faceted evaluation framework goes beyond numerical accuracy and computational cost, incorporating a curated set of structure-preserving metrics to assess physical fidelity. Our extensive evaluations yield several key insights. Notably, we find that modern architectures (e.g., VMamba), not only achieve superior long-term stability and physical fidelity but also operate with an order-of-magnitude greater computational efficiency. The results highlight the necessity of holistic evaluation and identify these modern architectures as a highly promising direction for developing efficient and reliable surrogate models in data-driven materials science.

MicroEvoEval: A Systematic Evaluation Framework for Image-Based Microstructure Evolution Prediction

<h1>
 
 
 AI Amnesia: Erasing Knowledge Without a Trace
</h1>

Imagine your AI model accidentally learned something it shouldn't have – sensitive customer data, for example. Current methods for deleting this information often require retraining the entire model, an expensive and time-consuming process. What if we could surgically remove that knowledge without starting from scratch?

The key lies in a novel approach: creating artificial "forgetting cues." We're teaching the model to unlearn specific data patterns by exposing it to carefully crafted synthetic examples. These examples are designed to strongly contradict the information we want the model to forget, effectively overwriting the problematic associations in its memory. This works even if you don’t have access to the original data you need to erase.

Think of it like this: you're trying to forget a bad song stuck in your head. Instead of trying to actively suppress it (which rarely works), you blast an even more catchy song. The new song overwrites the old one, effectively erasing it from your mental playlist.

Benefits of Selective Forgetting:

<ul>
<li> Enhanced Data Privacy: Remove sensitive data without compromising the overall model's performance.</li>
<li> Reduced Retraining Costs: Avoid full model retraining, saving significant time and resources.</li>
<li> Improved Model Security: Eliminate vulnerabilities introduced by unintentionally learned patterns.</li>
<li> Adaptable Learning: Enables continuous refinement of AI models based on evolving data landscapes.</li>
<li> Compliance Ready: Supports compliance with data privacy regulations like GDPR.</li>
<li> Scalable Solutions: Works efficiently even with limited access to training data.</li>
</ul>

Practical Tip: One challenge is ensuring the synthetic data accurately targets the information you want to remove without negatively impacting the model's ability to generalize. Rigorous testing and validation with holdout datasets are crucial.

The promise of AI that can truly 'forget' opens exciting possibilities for responsible AI development. By enabling precise data deletion, we pave the way for more secure, compliant, and adaptable machine learning systems. Imagine AI models that can adapt to changing ethical guidelines or quickly unlearn incorrect information, all without massive retraining efforts. This is a crucial step towards trustworthy and responsible AI that respects data privacy and aligns with societal values. Future exploration could include extending this to different data modalities and model architectures.

Related Keywords: machine unlearning, data privacy, few-shot learning, zero-shot learning, synthetic data, model editing, catastrophic forgetting, incremental learning, continual learning, deep learning, neural networks, data security, algorithmic fairness, responsible ai, ethical ai, federated unlearning, privacy-preserving ai, model retraining, AI governance, data deletion, GDPR compliance

يتناول المقال نهجًا جديدًا لمعالجة مشكلة نسيان الذكاء الاصطناعي، حيث قد تحتفظ نماذج الذكاء الاصطناعي عن غير قصد بمعلومات حساسة. تتطلب الطرق التقليدية لحذف هذه البيانات غالبًا إعادة تدريب كاملة للنموذج، وهو ما يعد مكلفًا ويستغرق وقتًا. تتضمن التقنية الجديدة إنشاء 'إشارات نسيان' اصطناعية تساعد النموذج على نسيان أنماط بيانات معينة من خلال تعريضه لأمثلة صناعية تتناقض مع المعلومات غير المرغوب فيها، مما يسمح بإزالة المعرفة المستهدفة دون الحاجة للوصول إلى البيانات الأصلية.

El artículo aborda un nuevo enfoque para tratar el problema de la amnesia de la IA, donde los modelos de IA pueden retener inadvertidamente información sensible. Los métodos tradicionales para eliminar estos datos a menudo requieren un reentrenamiento completo del modelo, lo que es costoso y lleva tiempo. La nueva técnica implica crear 'señales de olvido' artificiales que ayudan al modelo a desaprender patrones de datos específicos al exponerlo a ejemplos sintéticos que contradicen la información no deseada, permitiendo así la eliminación selectiva de conocimientos sin necesidad de acceder a l…

L'article traite d'une nouvelle approche pour résoudre le problème de l'amnésie de l'IA, où les modèles d'IA peuvent involontairement conserver des informations sensibles. Les méthodes traditionnelles pour supprimer ces données nécessitent souvent un réentraînement complet du modèle, ce qui est coûteux et long. La nouvelle technique consiste à créer des 'cues d'oubli' artificiels qui aident le modèle à désapprendre des schémas de données spécifiques en lui présentant des exemples synthétiques qui contredisent les informations indésirables, permettant ainsi une suppression ciblée des connaissan…

The article discusses a novel approach to address the issue of AI amnesia, where AI models may inadvertently retain sensitive information. Traditional methods for deleting such data often require complete retraining of the model, which is costly and time-consuming. The new technique involves creating artificial 'forgetting cues' that help the model unlearn specific data patterns by presenting it with synthetic examples that contradict the unwanted information, allowing for targeted knowledge removal without needing access to the original data.

Death’s Job Game

Was this article worth reading? Share it