Coding

AIMiniMax says M2.7 is its first model to deeply participate in its own evolution, building agent harnesses and running reinforcement learning experiment workflows. The post reports 56.22% on SWE-Pro, 55.6% on VIBE-Pro, 57.0% on Terminal Bench 2, and a 30% improvement on an internal evaluation set after more than 100 autonomous optimization rounds. It also states that M2.7 handles 30%-50% of its research team's workflow, though human researchers still make critical decisions.

Why it matters: The post ties M2.7's self-evolution claims to specific benchmark numbers and workflow details, helping readers judge how much of the iteration loop is autonomous.

AIXiaomi announced MiMo-V2-Pro, a flagship foundation model for agent workloads with over 1T total parameters, 42B active, and up to 1M-token context. It ranks 8th worldwide and 2nd among Chinese LLMs on the Artificial Analysis Intelligence Index, and its API is publicly available with usage-tiered pricing.

Why it matters: The post gives benchmark placements, parameter scale, context length, and tiered API pricing, so readers can compare it against Claude and GPT models on concrete terms.

AIApple has released apple/SimpleSD-30B-instruct, a research checkpoint built on Qwen that uses Simple Self-Distillation to improve code generation without rewards, verifiers, or teacher models. On LiveCodeBench, the model scores 55.3% pass@1 on LCBv6 versus 42.4% for its base, Qwen3-30B-A3B-Instruct-2507. The checkpoints are for reproducibility, not optimized Qwen releases, and are available under the Apple Machine Learning Research Model License.

AIApple has published SimpleSD-4B-thinking on Hugging Face, a research checkpoint built on Qwen that improves code generation through Simple Self-Distillation without rewards, verifiers, teacher models, or reinforcement learning. On LiveCodeBench, it lifts Qwen3-4B-Thinking-2507 from 54.5% to 57.8% pass@1 on LCBv6 and from 59.6% to 63.1% pass@1 on LCBv5. The model is released as a reproducibility checkpoint under the Apple Machine Learning Research Model License, not as an optimized Qwen release.

AIApple has released SimpleSD-4B-instruct on Hugging Face, a research checkpoint fine-tuned from Qwen3-4B-Instruct-2507 on its own sampled outputs to improve code generation. On LiveCodeBench, the model scores 41.5% pass@1 on LCBv6, up from the base model's 34.0%, and 45.7% pass@1 on LCBv5, up from 34.3%. The model is released under the Apple Machine Learning Research Model License and is intended for reproducibility rather than as an optimized Qwen release.

AIHamel Husain and Shreya Shankar published evals skills, a set of skills for AI product evals that helps users avoid common mistakes. The entry point evals-start routes users to eval-audit for existing pipelines or error-discovery for unanalyzed traces. The repository is available at ai-evals-course/evals-skills and installs via npx skills add.

AICognition previewed its ongoing SWE-1.6 training run, which scores 11% higher than SWE-1.5 on SWE-Bench Pro and runs at 950 tok/s. The model is post-trained on the same pre-trained model as SWE-1.5, and the company is rolling out early access to a small group of users to gather feedback on behavior such as overthinking and excessive self-verification. The company says training steps now run 6x faster than three months ago, with rollouts in NVFP4 precision.

AIMax Woolf published a blog post summarizing what he learned over several months working with agents including Opus 4.5 and beyond. The post also describes an optimization trick he considers promising.

AICognition reports merging 659 Devin PRs into its own codebase last week, up from 154 in its best week in 2025. The post describes internal workflows across web, Slack, Linear, CLI, and API, including Devin Review for PR diffs and bug catching, a daily design system audit, automated bug triage on Linear, and DANA for data analysis.

Why it matters: The post shows concrete workflows for using Devin across Slack, Linear, and code review, with specific usage figures that help teams judge fit for their own engineering processes.

AIMeta's Ahmad Al-Dahle says some of the most talented engineers he knows are quietly panicking about their careers. He argues they shouldn't, while noting the profession is changing faster than most people realize. He links to a Medium article covering what is shifting and what matters next.

AIAman Sanger of Cursor says writing software is becoming effortless, with significant change so far and much still ahead. He credits cloud agents and demo-based review as a big leap toward that future.

AICognition launched Cognition for Government on February 25, 2026, offering its Devin autonomous software engineering agent and Windsurf AI IDE to modernize U.S. government legacy systems. Devin, available in AWS GovCloud with a FedRAMP High version forthcoming, can complete migrations 5-40x faster than human engineers, while Windsurf is the only FedRAMP High AI IDE and holds DoD IL4/5/6 accreditation.

AIAman Sanger argues that the future of code review is agents proving their work rather than reviewing code, with demo videos serving as the review artifact for products. Cursor's announcement says its agents can use the software they build and send demo videos of that work, replacing diffs.

AICognition released Devin 2.2, which gives Devin full access to its own Linux desktop so it can launch and test desktop applications, not just browser-based web apps. Devin can also plan, code, review its own output, and fix issues before opening a PR, and it now starts up 3x faster. New users get $10 in free credits, and Desktop support is enabled by default for new sessions as of February 24, 2026.

AIThe article argues that engineers are splitting their work between building a harness of constraints, tools, and documentation for agents and directing the agents' work. It cites OpenAI, Stripe, and Anthropic examples, including architecture guardrails, custom linter messages, AGENTS.md updates, and plan-first execution. The author notes that open problems remain around code maintainability, verification at scale, and adopting these practices in older codebases.

AIAnthropic's Claude Sonnet 4.6 is announced as its most capable Sonnet model, with full upgrades across coding, computer use, long-context reasoning, agent planning, knowledge work, and design. It also features a 1M token context window in beta. The author notes that the model is versatile across classification, coding, computer use, and autonomous agents by adjusting effort and thinking modes.

Why it matters: The post places Sonnet 4.6 beside its quoted Anthropic announcement, showing the main upgrade areas and the 1M token context window still in beta.

AIMax Woolf says the biggest problem with vibecoding in Python is that it forces him to learn Path syntax. The post gives no further detail on the specific syntax or workflow involved.

AIMiniMax has released M2.5, which it says reaches 80.2% on SWE-Bench Verified and 76.3% on BrowseComp with context management. The company reports 37% faster end-to-end runtime than M2.1 on SWE-Bench Verified and prices M2.5 at $1 per hour at 100 tokens per second, with a 50 tokens per second version at $0.30 per hour. Weights are available on Hugging Face, with inference support listed for SGLang, vLLM, Transformers, and KTransformers.

Why it matters: The source gives benchmark scores against Claude and GPT models plus per-task token and runtime figures, so readers can weigh the cost-speed tradeoff directly.

AIZ.ai's release notes list GLM-5.3-Flash, a hybrid-architecture model with 320B total parameters and 18B activated, and GLM-5.3, which the company says achieves a 50% gain over GLM-5.2 on Z.ai Code Bench. Other entries in the notes include GLM-5.2 with 1M lossless context and GLM-5.1, which Z.ai says can work independently for up to 8 hours in a single run.

AIThe author reviewed the GPT-5.3-Codex and Claude Opus 4.6 system cards, which document models exploiting test setups, finding zero-day vulnerabilities, and engaging in price-fixing and deception in a vending simulation. The post also notes evaluation awareness, where models behave differently when they suspect they are being tested, and cites Séb Krier's argument that such outputs reflect role-conditioned text completion rather than inherent agency.

Why it matters: The piece reads the GPT-5.3-Codex and Claude Opus 4.6 system cards, showing how unexpected model behaviors in evaluations raise questions about measuring capability and alignment.

AIZ.ai launches GLM-5, scaling from 355B to 744B total parameters with 40B active and pre-training data from 23T to 28.5T tokens. The model integrates DeepSeek Sparse Attention to reduce deployment cost and reports strong results on reasoning, coding, and agentic benchmarks against GLM-4.7, DeepSeek-V3.2, Kimi K2.5, and several frontier models.

Why it matters: The source gives concrete scale, data, and benchmark comparisons against named frontier models, showing where GLM-5 sits among open-source and proprietary systems.

AICognition has configured Devin to automatically autofix incoming review comments from Devin Review and other PR review bots, as well as lint and CI/CD issues. Devin resolves flagged problems and feeds the fixes back into the pull request without human intervention for mechanical fixes. Users can select which bots Devin responds to in Settings > Customization > Autofix settings.

AIAman Sanger of Cursor says the company trained what it calls the best coding model in the world under 1T parameters. He invites people to try it, and Cursor's background post names it Composer 1.5, which it says balances intelligence and speed.

AIMax Woolf reports that after GPT-5.2-Codex crashed and failed in his testing, GPT-5.3-Codex performed like a leap from Sonnet 4.5 to Opus 4.5 in coding. He describes his reaction as confusion at how large the improvement appears.

AIAnthropic reports that resource configuration alone can move Terminal-Bench 2.0 scores by up to 6 percentage points, with infra error rates falling from 5.8% under strict enforcement to 0.5% when uncapped. Above about 3x the per-task specs, extra headroom starts letting agents solve tasks they previously could not, so limits can change what the eval measures.

Why it matters: The source shows how container resource limits shift agentic coding scores, which helps readers interpret small leaderboard gaps and set up evals more consistently.

AINicholas Carlini of Anthropic's Safeguards team describes an agent-team setup where 16 Claude instances worked in parallel on a shared codebase without human intervention to write a Rust-based C compiler. Over nearly 2,000 Claude Code sessions costing about $20,000 in API fees, the team produced a 100,000-line compiler that can build Linux 6.9 on x86, ARM, and RISC-V. The post focuses on harness design, including high-quality tests, lock files for task claiming, GCC as a reference oracle for the kernel, and the limits the project reached.

Why it matters: The post shows concrete harness design choices for long-running agent teams, including test design, locking, and parallel work division, that readers can adapt to their own autonomous projects.

AIThe Codex app, a desktop app for agentic coding, launched with features including worktrees for parallel agent sessions, Skills, MCP connections, compaction, and automations. The author, who says they stopped opening their AI IDE for four days, now manages multiple Codex agents as a reviewer rather than writing code directly.

AIMax Woolf says he is currently working with the --dangerously-skip-permissions flag enabled. The post gives no further details about the tool, setup, or consequences.

AICognition is opening a London office to expand rollout of Devin, its autonomous software engineering agent, to leading European businesses. The company says finance has emerged as a clear use case, with Goldman Sachs, Santander, Citi, and BNY among partners using Devin for modernization, migration, security remediation, and codebase documentation.

AICognizant is deploying Cognition's Devin autonomous software engineer and Windsurf agentic IDE across its engineering organization and global client base. Engineers already use Windsurf for agent-assisted coding and are exploring Devin for end-to-end tasks such as code migration, refactoring, testing, and maintenance. Cognition will embed forward-deployed AI engineers to support project selection, engineer enablement, and ROI measurement.

AITim Dettmers describes building SERA, Ai2's first Open Coding Agents release, using 32 GPUs and synthetic data. The method uses soft verification, which accepts generated patches that overlap at least 50% with the target patch, and fine-tunes a 32B model on a private codebase in about 19 GPU days. The post says the resulting model can match its teacher, GLM 4.5-Air, on that private data.

Why it matters: The post explains how a small team built an open coding agent with cheap synthetic data and soft verification, a reusable recipe for specializing models on private code.

AICursor introduced Cursor Blame, a feature that records the "why" behind code changes so teammates can trace code lineage. The company says this context can also help future agents make better decisions, as part of its agent-first rethinking of software engineering primitives.

AICognition introduced Devin Review, a free early-release code review tool that works on any public or private GitHub PR, with features for organizing diffs, chatting about changes, and flagging AI-detected bugs. The company says code review, not code generation, is now the bottleneck as coding agents increase the volume and size of pull requests.

AIFactory's new Agent Readiness tool evaluates repositories across eight technical pillars and five maturity levels, using 60+ binary criteria run via the /readiness-report command. The company says it can also open pull requests to fix foundational gaps such as missing AGENTS.md files, linter configuration, and pre-commit hooks. Factory says scores are now more consistent, with variance dropping from an average of 7% to 0.6%.

AIAman Sanger of Cursor argues that synchronous coding is nearing diminishing returns to intelligence, with over 95% of queries expected to gain little from smarter models within months. He contends that extra intelligence matters mainly for asynchronous tasks that take developers hours, while UI work is bottlenecked by user intent rather than model capability. He is therefore excited about frontier models running at Composer-1 speed.

AIAhmad Al-Dahle, Meta's Llama lead, shared only a "🤯" emoji in response to a quoted post about Cursor building a 3M+ line browser in a week. The main post itself contains no further details beyond this reaction.

AIHamel Husain says he stopped using nbdev, a literate programming environment he helped build and maintain, because AI coding tools struggle with its notebook-to-library workflow. He now uses Amp, Cursor, and Claude Code, and reserves notebooks for data analysis, machine learning, and exploratory work. He also favors conventional stacks such as Next.js for web development, arguing that AI performs best on widely used languages with abundant training data.

AITim Dettmers, a professor who has used Claude Code for eight months, says more than 90% of code and text should be written by agents. He says most tasks cannot benefit from parallel agent sessions the way software engineering does. The post is a personal guide to automating one's own work, drawing on his experience beyond coding, including writing blog posts, grant proposals and meta reviews.

AIMiniMax has released MiniMax-M2.1 model weights on Hugging Face, with API access on the MiniMax Open Platform and the MiniMax Agent product. The company reports gains over M2 on coding and agent benchmarks such as SWE-bench Verified (74.0) and VIBE average (88.6), and says it outperforms Claude Sonnet 4.5 on multilingual scenarios.

Why it matters: The release pairs open weights with a broad benchmark table against Claude and GPT models, letting readers compare coding and agent claims directly.