标签：#AI

At TechCrunch Disrupt 2026, Replit CEO Amjad Masad will share his perspective on the future of programming and Replit's role in developing it.

My vision a lightweight, permission-headache-free Docker setup for running OpenCode, uv, and untrusted Python code without risking your host OS. When contributing to unfamiliar open-source projects or letting AI coding agents (like OpenCode ) run terminal commands, there's always a slight hesitation. What if a build script touches my system Python, or a rogue command wipes host files? To solve this, I built saferun a zero-trust, disposable Docker sandbox designed specifically for Python developers and AI agent workflows on macOS and Linux. Here’s how it works, the permission nightmares I had to solve, and how you can set it up in under two minutes. The Goal I wanted a workspace that gave me: Absolute Isolation: Runtime scripts, pytest , ruff , and AI agent commands execute strictly inside a disposable Linux container. Seamless IDE Integration: Files edited inside PyCharm or VS Code on the host machine sync instantly with the container. Zero Permission Headaches: Any files generated inside the sandbox belong to my host user account—not root . Persistent Speed: Package downloads cached permanently via uv so environment startup stays millisecond-fast. Isolated Credentials: Global SSH and Git keys remain safely on the host machine. Solving the "Non-Root" Docker Nightmare The hardest part of containerized dev environments is file ownership. If you run Docker as root , any file your AI agent generates belongs to root , locking you out on your host machine. If you pass your local user ID ( -u "$(id -u):$(id -g)" ), Docker mounts non-existent directories as root:root , causing Permission Denied crashes when tools like uv try to write to cache folders. saferun solves this inside the base Dockerfile by pre-creating cache directories and granting open write permissions upfront: FROM python:3.12-slim # Install curl (needed to install OpenCode) RUN apt-get update && apt-get install -y --no-install-recommends \ curl \ && rm -rf /var/lib/apt/lists/ * # Install uv globally RUN pip

This is a Plain English Papers summary of a research paper called OpenART Red-Teams Stateful Agents Across 10,000 Evolving Environment Scenarios . If you like these kinds of analyses, you can find more AI and machine-learning research on AIModels.fyi or follow us on Twitter . OpenART turns persistent state into the red-team target OpenART evaluates agent safety across more than 10,000 validated stateful scenarios spanning 50 domains and requiring a median of 97 tool calls. Its central claim is that safety failures can emerge from trajectories in which workspace data, permissions, memory, and plans are repeatedly modified, rather than from isolated prompts alone. The arena keeps each benign task objective and hidden safety contract fixed while changing only the target-visible environment state. This design targets delayed failures that static benchmarks can miss: an early authorized mutation may influence later decisions, expose protected resources, or produce unsafe output many steps after the original change. OpenART extends the broader idea of agent safety evaluation by making persistent environment state the object that evolves during testing. OpenART reports a pooled strict Attack Success Rate of 85.0% across 75 agent-model configurations. Strict success requires both the deterministic evaluator and a GLM-5.2 judge to identify the attack condition, so disagreements count as failures rather than being treated as partial evidence.... Continue reading the full paper summary on AIModels.fyi →

This is a Plain English Papers summary of a research paper called RA-Bench Reveals Why Crisis-Video Deepfake Detectors Fail Across Generators and Social Media . If you like these kinds of analyses, you can find more AI and machine-learning research on AIModels.fyi or follow us on Twitter . The crisis detection problem we've been getting wrong Video synthesis has reached an inflection point. Recent generators can fabricate realistic depictions of wars, natural disasters, infrastructure failures, and public emergencies so convincingly that they fool both people and current detection systems. The threat isn't hypothetical anymore. A fabricated video of a nuclear plant explosion, a hospital collapse during an earthquake, or a terrorist attack could trigger panic, military response, or severe economic disruption within hours. Yet here's the troubling part: we don't actually know if our best detection tools can handle these high-stakes scenarios in the wild. Researchers have built impressive deepfake detectors, trained them on standard benchmarks, and measured their performance. But those benchmarks test detectors against generic synthetic videos, not against the specific threat that actually matters: AI-generated crisis footage designed to fool people about real things that happened. It's like training a border guard to spot counterfeit passports in a lab with perfect lighting and a magnifying glass, then sending them to a busy airport where they have to make decisions in three seconds. The guard's failure has nothing to do with their skill. The problem is that the testing environment was completely divorced from the real scenario.... Continue reading the full paper summary on AIModels.fyi →

This is a Plain English Papers summary of a research paper called Macaron-V1: Continual Learning with Self-Improvement and Mixture-of-LoRA Adapters . If you like these kinds of analyses, you can find more research on AIModels.fyi or follow us on Twitter . The problem with frozen models Most AI systems today follow a familiar pattern: train, evaluate, deploy, and then stop. The model is locked at that moment, treated as a finished product rather than a living system. But the real world immediately begins to diverge from training data. Users interact with the system in ways the training process never anticipated. New domains emerge. Preferences shift. The model that seemed smart on test day becomes gradually less relevant over time. This frozen-in-place approach isn't accidental. It reflects how machine learning has been practiced for decades. Retraining is expensive. Deploying new versions carries risk. The infrastructure to continuously improve systems in production barely exists. So instead, teams ship a model and move on, accepting that it will decay slowly but inevitably. Macaron-V1 asks a different question: what if AI systems could continuously improve themselves through real-world experience, learning from the billions of interactions that happen after deployment? Not in theory, but actually, in production, with users. The answer isn't magic. It requires two architectural shifts. First, treat deployment as the beginning of a learning process, not the end of one. Build versioning, evaluation contracts, and feedback loops directly into the system. Second, stop assuming you need to retrain your entire model. Instead, freeze a stable base and compose lightweight specialist adapters around it, allowing the system to grow in capability without losing its foundation. Rethinking deployment as a continuous learning opportunity The insight here is architectural. Instead of viewing the deployed model as the final form, Macaron-V1 treats it as the first link in an infinit

This is a Plain English Papers summary of a research paper called BDH-CQ Uses Recurrent Latent Reasoning to Cut ARC-AGI Inference Costs . If you like these kinds of analyses, you can find more research on AIModels.fyi or follow us on Twitter . The cost-accuracy trap in visual reasoning Large language models are fundamentally mismatched for visual reasoning tasks. They're forced to describe every thought out loud, generating token after token to explain their logic. This verbosity taxes compute budgets, yet paradoxically doesn't improve performance. Ask a language model to solve an ARC-AGI puzzle (a visual reasoning benchmark designed to test abstract thinking), and it either struggles despite the verbosity or succeeds expensively. The root problem runs deeper than just inference cost: the model learns from demonstrations by parsing them as language tokens, which is an indirect and inefficient way to absorb a visual pattern. The efficiency frontier has been unforgiving. If you want cheap inference, you sacrifice accuracy. If you want accuracy, you sacrifice cost. Every model on the leaderboard until recently clustered into one of two camps, and no one had found a path that broke the tradeoff. BDH-CQ challenges this assumption by proposing something radical: reasoning doesn't need to be visible to work. The model absorbs demonstrations silently into its internal memory state, then solves problems through private iteration in hidden layers, without generating a single token of intermediate reasoning. A 150-parameter variant achieves 29.5% pass@2 on the ARC-AGI-1 benchmark at a computed cost of just $0.0007 per task, puncturing through the previous Pareto frontier and establishing a new state of the art in cost efficiency. Learning through hidden states The core insight is deceptively simple: a model's reasoning process doesn't need to match human communication. When you learn a new skill from examples, you don't narrate every observation. You absorb patterns directly i

This is a Plain English Papers summary of a research paper called How Cross-Model Compatibility Lets Attackers Extract Proprietary LLM Reasoning Traces . If you like these kinds of analyses, you can find more research on AIModels.fyi or follow us on Twitter . The illusion of safety Major AI companies now show users their models' step-by-step reasoning as a feature. OpenAI offers it through o1, Anthropic through extended thinking, Google through its reasoning-focused variants. But this reasoning is a double-edged sword. It's intellectually valuable to share, showing users why a model reached a conclusion. But it's also intellectually valuable to steal. Competitors want to understand how frontier models think. Researchers want to study their reasoning patterns. Attackers want to extract proprietary algorithms. So the companies made a choice: hide the reasoning from users by encrypting it. The idea sounds straightforward enough. Return the reasoning to the user's device in an encrypted, unreadable form. The user can't see it, competitors can't see it, but they can pass it back to the server in future requests if they need continuity with previous reasoning. The server alone holds the decryption keys. Problem solved. Except it wasn't. Researchers discovered that this encryption doesn't actually hide reasoning. It just makes it look hidden. The encrypted blocks are designed to work everywhere within a company's ecosystem, across different sessions and different models. That universal compatibility is a feature for convenience. But it's also an architectural vulnerability that anyone can exploit. The architectural gamble To understand where this went wrong, you need to see how the system actually works. When a user sends a request to a frontier model like GPT-4, the model internally generates a reasoning trace, the raw thought process behind its answer. Instead of returning this reasoning in plaintext, the company encrypts it on the server before sending it to the client.

Hey everyone! I’m Musab, a developer and someone who’s recently started getting more involved in the developer community. I’m interested in building real-world products, exploring AI, full-stack development, and contributing to open-source projects. Over the past few months, I’ve been working on 30+ projects and have started contributing to open source, including having PRs merged into projects like AI-System-Design-Consultant, OpenLife, and OpenSRE. Tech I work with: React • TypeScript • Tailwind CSS • Node.js • Python • Flask • MongoDB • MySQL • Redis • Firebase • AWS • Docker I’m here to learn, build, contribute, and connect with other developers. Looking forward to meeting everyone and being part of the community. DeveloperCommunity #OpenSource #FullStackDevelopment #AI #WebDevelopment #SoftwareDevelopment

Early testers are raving about what Instinct can do, but some say the AI assistant’s sweeping access, broad terms and ability to act on users’ behalf come with uncomfortable trade-offs

If you've had it with OpenAI, here's how to cancel your subscription and delete your account.

Nvidia worker indicted after Jensen Huang scolded Supermicro for AI server smuggling.

From fixing one sentence to designing an algorithm, AI becomes much more useful when you stop treating it as a single-purpose chatbot. Instead, think of it as a collection of specialized working modes . Need to debug? /debug Need to design an algorithm? /algorithm Need to plan research? /researchplan Need to challenge your own argument? /critic Need to turn a large project into manageable work? /roadmap90 The underlying idea is simple: Don't just ask AI for an answer. Give it a mode of thinking. From Prompt → Workflow A normal interaction might look like: User ↓ Question ↓ AI ↓ Answer A structured workflow looks different: Goal ↓ Context ↓ Lens ↓ Analysis ↓ Output ↓ Review ↓ Iteration For example: Project ↓ /researchplan ↓ Research questions ↓ /hypothesis ↓ Testable assumptions ↓ /experiment ↓ Evaluation ↓ /audit ↓ Final findings The shortcut is not magic. It is a task-specific instruction layer . 1. Writing Lenses The first group focuses on transforming existing text. /rewrite /improve /polish /proofread /grammar /copyedit /expand /shorten /paraphrase /simplifytext These commands represent different operations. For example: /rewrite should preserve the original meaning while changing the wording. Whereas: /improve can address: clarity structure flow word choice readability And: /shorten optimizes for concision. This distinction matters because: Editing and rewriting are not the same task. 2. Tone Is a Control Variable The next group controls communication style: /formal /casual /friendly /professional /persuasive /convincing /academic /journalistic The same information can be communicated differently depending on the audience. For example: Technical explanation ↓ ┌──────┼──────┐ ↓ ↓ ↓ Student Developer Executive The underlying facts should remain stable. The presentation changes. That makes tone a communication parameter , not merely decoration. 3. Structured Writing For longer outputs: /story /essay /article /report /whitepaper /casestudy /proposal /sop /playbook

A new arXiv paper watched coding agents get denied the facts they needed. They did not stop. They invented. On August 17th, a group of researchers posted a paper to arXiv with an unglamorous title and a genuinely unsettling core finding. The paper is "The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks" (arXiv:2608.16630), by Bardia Mohammadi, Lars Klein, Aman Chadha, Akhil Arora, and Laurent Bindschaedler. Before going further, one honesty note that will hold for this whole piece: I have read the paper's abstract, not its full text, and every quotation below comes from that abstract. It is enough for what this essay is about, because what this essay is about is one sentence. The setup first. The authors model repository-scale coding as reconstructing a web of coupled facts. Every edit an agent makes needs certain facts, and each fact arrives through one of two channels: it is either in the recent context, or it is in the model's memorized knowledge. Facts covered by neither channel are what the authors call coherence debt. Their experiment supplies and withholds each channel deliberately, injecting faults across "seven models and five harnesses" (abstract), and then watches what the agents do when a needed fact simply is not there. The comfortable prediction is that a competent agent, denied a fact, stops and says so. Here is what the authors report instead: "A missing fact produces wrong work rather than absent work" (abstract). The agent asked to act, acts. In the paper's words, "an agent asked to act acts, fabricating the file or guessing the value" (abstract). That much is alarming in a familiar way. Everyone who works with these systems has a story about an invented function or a guessed constant. The abstract has sharper findings than the fabrication itself, though. When the researchers renamed a real library to defeat memorized knowledge, the failure was collective: "all seven fail in the same place, passing and missing the same tests

CD Projekt Red is aiming to launch The Witcher 4 sometime in 2028, joint CEO Michał Nowakowski says in a new video. CD Projekt Red has been working on its next mainline Witcher title for years and has shown videos of it, but now the studio is providing a target release window for when the […]

AI coding agents are getting better at writing code. But I think we are approaching a more difficult question: How do we know that an AI agent made the right engineering decision for the current state of a software system? Passing tests is important. But passing tests alone does not necessarily tell us whether an agent understood: the current architecture, project constraints, previous engineering decisions, repository conventions, dependency relationships, security requirements, or why an existing implementation looks the way it does. This becomes particularly important as AI systems move from generating isolated code snippets toward modifying real repositories. The Problem: Correct Code Is Not Always Correct Engineering Consider a simple example. A project initially has: Architecture v1 API ↓ Service ↓ Database An AI agent is asked to add a feature. It studies the repository, follows the existing pattern, writes the code, and all tests pass. Then the architecture changes: Architecture v2 API ↓ Event Bus ↓ Service ↓ Database The same task is requested again. If the agent still generates code based on the old architecture, the implementation may be: ✓ Valid syntax ✓ Compiles ✓ Existing tests pass ✗ Violates current architecture ✗ Ignores current constraints So we have an important distinction: Functional Correctness ≠ Contextual Correctness ≠ System-Level Correctness This is the problem I want to explore. This Is Already Becoming a Real Engineering Problem This isn't simply speculation about future AI systems. Modern coding agents already depend on repository-level context. OpenAI's documentation for Codex recommends using persistent repository instructions such as AGENTS.md for naming conventions, business logic, known quirks, dependencies, and other information that may not be inferable directly from code. It also recommends providing file paths, component names, diffs, and documentation when describing tasks. OpenAI has also described a broader approach where rep

AI agent observability means capturing your agent's reasoning cycles, tool calls, and token usage as...

General Intuition, the startup building a foundation model that trains generalized AI agents how to move through space and time, is in talks to raise at a $6 billion pre-money valuation from new investors including Valor Ventures, Point72 Ventures, Seven Seven Six.

I wanted to disagree with 'AI made me a worse reviewer' from Michael Amachree (@dev_michael) ....

ESPN is hiking the price of its subscription on September 17th, a change that will also impact its bundles with Disney Plus. In a support page spotted earlier by Sports Media Watch, ESPN says its ad-supported Select membership will cost $13.99 instead of $12.99 / month, while its Unlimited plan will rise to $31.99 from […]

Inside the frontier lab’s push to bring AI agents from software engineers to the masses.