#Coding

AIJeremy Howard reports that Opus 4.8 is more cooperative and less over-agentic than Opus 4.7 while coding. He says it pauses to ask for input where Opus 4.7 and GPT 5.5 would push ahead, but he calls it far too expensive.

AICognition describes autonomous testing in Devin, where the agent writes a source-grounded test plan, operates the app through computer use, and returns labeled screenshots and an annotated video. Login steps are handled by a deterministic testing skill, and the company says test runs approved per day more than doubled in recent months. Known limits include timing errors with transient UI elements and models sometimes triggering states through JavaScript instead of clicking the interface.

Why it matters: The post explains how computer use, test plans, deterministic login scripts, and annotated recordings let Devin verify its own code changes end to end.

AICognition raised over $1B at a $26B valuation, led by Lux Capital, General Catalyst, and 8VC. Enterprise Devin usage grew more than 10x since the start of this year, and run-rate revenue reached $492M. The company also said it launched SWE-1.6, which reaches up to 950 tok/s and has become the most used model in Devin Desktop.

AIGoogle claimed a team of agents built an operating system from a single prompt for about $916 in API fees, using Gemini 3.5 Flash and Antigravity 2.0. The authors argue the prompt was many thousands of lines, the scaffold and human intervention are undefined, and no code, logs, or similarity analysis were released to verify the claim. They still see value in such open-world evaluations, which need stronger methodological norms and independent scrutiny.

AITri Dao says that after a mathematical rewrite, all transformer operations can be expressed as a series of GEMMs with epilogues. Given a few optimized primitives, LLMs and novice humans can write near speed-of-light kernels for transformer ops. The related CODA work fuses memory-bound surrounding ops into the matmul epilogue, and LLMs can also write CODA kernels approaching speed-of-light.

AICursor is doubling usage for new users invited on the Teams plan for the next month. The offer applies only to users invited by a Teams plan member during that period.

AICognition's Devin AI software engineer can now build, run, and test code natively in its own Windows virtual machine, including migrating .NET Framework apps to .NET Core. The Windows capability is in beta for Enterprise Cloud and Dedicated Deployment customers, with the same SOC 2 Type II and ISO 27001 controls as the Linux version. Citi and Mercedes-Benz are named as existing Devin users.

AICursor has added Gemini Flash 3.5 to CursorBench, its main coding agent evaluation. The company says the leaderboard will be updated as new models are released, with results available at

AIGoogle's Gemini 3.5 Flash outperforms Gemini 3.1 Pro on Terminal-Bench 2.1 (76.2%), GDPval-AA (1656 Elo), and MCP Atlas (83.6%). The post also claims it is 4x faster than other frontier models, or 12x in Antigravity, and reports 83.6% on MMMU-Pro for multimodal performance.

Why it matters: The post gives specific benchmark scores against Gemini 3.1 Pro, letting readers compare coding, agentic, and multimodal results directly.

AIGemini 3.5 Flash produces fully tactile, interactive HTML/SVG hardware simulations in a single shot when given complex agents and tasks. The output includes bump-mapped metals, spring physics, and procedural audio, according to the post.

AIComposer 2.5 is now the most-chosen model in Cursor, according to Cursor co-founder Michael Truell. To celebrate, Cursor is giving users 10x usage for the rest of the day.

AIMichael Truell of Cursor says Composer 2.5 is a significant step up from Composer 2. He adds that this is only the start of work with SpaceXAI, with more improvements expected soon. Cursor's announcement describes the model as more intelligent, better at long-running tasks, and more reliable at complex instructions, with doubled included usage for the next week.

AICognition's Devin can now spin up an Android Virtual Device, letting it build, run, and test Android applications directly on its own machine. The new emulator support gives Devin an Android equivalent of computer and browser use, so it can open apps, inspect behavior, reproduce issues, and verify changes. The feature is available now for teams using Devin.

AIAwni Hannun says Claude Code's new agent view is where he starts and manages much of his work, calling it an exceedingly useful feature. Anthropic's Claude account introduced agent view as a single list of all sessions, available now as a research preview.

AIAnthropic's Claude Security is now in public beta for Claude Enterprise customers, scanning codebases for vulnerabilities. It validates each finding to reduce false positives and suggests patches that users can review and approve. The main post from Eugene Yan simply shares the launch and expresses hope it helps people improve cybersecurity.

AIOpenAI released Auto-review in Codex, which replaces user approval at the sandbox boundary with a separate agent that approves or denies boundary-crossing actions. In internal deployment, Codex sessions stopped for human approval about 200x less often than in manual mode, and Auto-review approved around 99% of escalated actions. The post also states that Auto-review is not a guarantee of security and cannot protect against model scheming.

Why it matters: The post explains how Auto-review replaces human approval at the sandbox boundary, with internal deployment figures and stated limits that help readers judge the tradeoff for coding agents.

AIAndrej Karpathy describes a December 2025 shift in which coding agents began producing larger, more reliable chunks of work, changing programming toward orchestrating agents. He argues that models automate what can be verified and that their capability is jagged, depending on verifiability and what labs emphasize in training, so users need to stay in the loop. He also says hiring, founder opportunities, and agent-native infrastructure should adapt to this shift.

AIMercedes-Benz is deploying Cognition's Devin and Windsurf across its global engineering teams, from the United States to Europe and Asia. In a four-week pilot, Devin analyzed over 200,000 lines of COBOL code and cut modernization time from an estimated eight months to eight days. The company is now rolling out the full suite, with Windsurf for development, Devin as an autonomous cloud agent, and Devin for Terminal for the most complex tasks.

AIXiaomi released and open-sourced MiMo-V2.5-Pro, a 1.02T-parameter Mixture-of-Experts model with 42B active parameters and a 1M-token context window. The company reports gains in agentic tasks, software engineering, and long-horizon work, including a Rust SysY compiler task finished in 4.3 hours across 672 tool calls. Weights and tokenizer are on Hugging Face, and API pricing is unchanged.

Why it matters: The release pairs a 1.02T-parameter open-weight model with long-horizon agent results and token-efficiency claims, useful for judging its fit in coding and agent workflows.

AICognition has released Devin CLI, a local coding agent that runs in the shell with access to the codebase, tools, and environment. Users can choose among frontier models including Opus 4.7, GPT-5.5, and SWE-1.6, and hand sessions off to cloud agents with their own computer, which keep working after the laptop is closed.

AIDeepSeek is offering a 75% discount on the DeepSeek-V4-Pro API until May 5, 2026, 15:59 UTC. For Claude Code, users can set the model to deepseek-v4-pro[1m] to unlock a 1M context window, while OpenCode requires v1.14.24 or later and OpenClaw requires v2026.4.24 or later.

AIMckay Wrigley says his coding split moved from 80/20 Claude/GPT to 80/20 GPT/Claude within three months, and he trusts GPT 5.5 for engineering. He still finds Claude better for non-coding agent work, calls Opus 4.7 underwhelming, and attributes Anthropic's issues to compute constraints.

AIApple has released CADD-Base-7B on Hugging Face, a 7B masked diffusion language model for code generation that uses Continuously Augmented Discrete Diffusion (CADD) to guide discrete denoising with a continuous flow-matching signal. The model loads through Transformers with trust_remote_code, and its diffusion_generate method supports CADD sampling modes "weighted" and "argmax" with alg options such as "entropy" and "maskgit_plus". The release builds on DiffuCoder and reuses Dream's modeling architecture and generation utilities.

AICognition reports that multi-agent setups work best when writes stay single-threaded and extra agents contribute intelligence instead of actions. It describes a code-review loop where a clean-context review agent catches bugs in Devin-written PRs, averaging 2 bugs per PR with roughly 58% severe. The post also says the smart-friend pattern, pairing a smaller primary model with a stronger one, has not yet worked well with asymmetrically weaker primaries and is an open training problem.

Why it matters: The post gives concrete findings on which multi-agent setups work, including clean-context code review and smart-friend escalation, and where they still fail.

AICursor's Michael Truell says the company is partnering with the SpaceX team to scale up Composer, calling it a meaningful step toward building the best place to code with AI. The quoted SpaceX post says Cursor gives SpaceX the right to acquire Cursor later this year for $60 billion, or pay $10 billion for the work together. It also cites SpaceX's Colossus training supercomputer, described as a million H100-equivalent system, as a source of training capacity.

AIEugene Yan shares a Mozilla writeup reporting that Mythos found 271 vulnerabilities fixed in Firefox 150, while Opus 4.6 found 22 fixed in Firefox 148. Mozilla quotes its finding that no category or complexity of vulnerability humans can find has been beyond the model so far.

AICognition says Windsurf 2.0 lets developers plan work locally, then send it to Devin with one click for implementation. Devin runs on its own machine, opens a pull request for review in Windsurf, and can keep working after the laptop is closed.

AIMoonshot AI released Kimi K2.6, an open-source native multimodal agentic model with 1T total and 32B activated parameters and a 256K context length. The model card reports benchmark results against GPT-5.4, Claude Opus 4.6, and Gemini 3.1 Pro across agentic, coding, reasoning, and vision tasks, and supports swarms of up to 300 sub-agents.

Why it matters: The model card gives specific agent swarm scale, context length, and benchmark comparisons against several frontier models, useful for judging its coding and agent capabilities.

AICognition and Applied Compute RL-trained SWE-check, a specialized bug detection model for the Windsurf IDE. It matches frontier performance on in-distribution evals and is an order of magnitude faster with cheaper inference, though it trails frontier models on out-of-distribution evals (delta F1 0.29 versus 0.49 before training). A preview is available in Windsurf Next, with a mainstream release planned.

Why it matters: The post explains how production environment replication, reward linearization, and two-phase post-training trade bug-detection quality against latency for an IDE specialist model.

AIDevin is retiring its Core and Team plans for a new lineup of Free, Pro at $20/month, Max at $200/month, Teams with usage-based billing and an $80/month minimum, and custom-priced Enterprise. Ask Devin's Deep Mode, Devin Review after a 2-week free trial, and higher-quality DeepWiki generation will move to usage-based billing, with DeepWiki's existing generation and open-source Devin Review remaining free. Self-serve usage beyond included quota will be billed in dollars rather than ACUs.

AIAndrej Karpathy argues that people judging AI from free-tier ChatGPT or Advanced Voice Mode miss the strong capabilities of current agentic models like OpenAI Codex and Claude Code. He says gains are "peaky," concentrated in verifiable technical domains like programming and math that suit reinforcement learning and attract B2B investment, while writing and everyday advice improve less. Those who use frontier agentic tools professionally in these fields see far greater capability, which is why the two groups talk past each other.

AIMiniMax has released MiniMax-M2.7 on Hugging Face, describing it as its first model to participate in its own evolution. The source reports 56.22% on SWE-Pro, 46.3% on Toolathon, and 62.7% on MM ClawBench, and says an internal version autonomously optimized a programming scaffold over 100+ rounds for a 30% performance improvement.

Why it matters: The source ties its benchmark claims to a self-evolution process and a named comparison set, which helps readers weigh how the reported gains were achieved.

AICognition describes how Devin handles COBOL modernization at several Fortune 500 companies, citing a shortage of COBOL developers and 68% failure rates for such efforts. The post identifies three obstacles for agents: untraceable data across copybooks, little COBOL in model training, and no way to run code on Linux-based VMs. It says Devin succeeds on documentation, batch migrations, and large-scale refactoring, while transactional workloads remain out of reach.

Why it matters: The post explains why agents struggle with COBOL and which workloads they can migrate, giving a framework for judging where automation fits legacy systems.

AIZ.ai's GLM-5.3 delivers a 50% coding gain over GLM-5.2 on Z.ai Code Bench, reaching open-source state-of-the-art on public benchmarks including Terminal Bench 3.0. GLM-5.3-Flash uses 320B total parameters with 18B activated, combining linear and sparse attention to reduce compute and KV-cache needs. GLM-5.2 supports a 1M lossless context window for long-horizon tasks.

AIWindsurf has made SWE-1.6, its model for software engineering agents, generally available, with the company saying it improves on the SWE-1.6 Preview by reducing overthinking, looping, and sequential tool calls. The model is free for three months, with a free version offered at 200 tok/s through Fireworks and a faster paid version at 950 tok/s through Cerebras.

AIZ.ai has released GLM-5.1, its next-generation flagship model for agentic engineering, with stronger coding than GLM-5. The model is described as staying effective over longer agentic tasks, sustaining optimization over hundreds of rounds and thousands of tool calls. The release lists benchmark results including SWE-Bench Pro at 58.4 and Terminal-Bench 2.0 at 63.5, and local deployment is supported through SGLang, vLLM, xLLM, Transformers, and KTransformers.

Why it matters: The release gives benchmark tables against several rival models, letting readers compare GLM-5.1's coding and agentic results with GLM-5 and frontier systems.

AIAI Futures Project moved Daniel Kokotajlo's Automated Coder median from late 2029 to mid 2028 and Eli's from early 2032 to mid 2030. The main reasons cited are a faster METR time horizon doubling time and the impressive results of Claude Opus 4.6. The authors also say progress in agentic coding has been faster than expected over the past 3 to 5 months.

AIMistral AI released Mistral Medium 3.5, a dense 128B model with a 256k context window that handles instruction-following, reasoning, and coding in a single set of weights. It replaces Mistral Medium 3.1, Magistral, and Devstral 2, and reasoning effort is configurable per request. The model accepts text and image input and is released under a Modified MIT License that excludes companies with large revenue.

Why it matters: The release merges instruction, reasoning, and coding into one 128B model with per-request reasoning control, giving developers one set of weights to compare against separate specialized models.

AIIntern Large Models introduced Kernel-Smith, a framework for generating high-performance GPU kernels and operators using an evolutionary agent and post-training recipe. The post says it outperforms Gemini-3.0-pro and Claude-4.6-opus on Kernel-Bench, and that optimized kernels have been merged into SGLang and LMDeploy. The accompanying figure compares best program score trajectories across evolution steps, with Kernel-Smith-235B-RL reaching the highest peak.

AIAnthropic's Labs team describes a three-agent harness with planner, generator, and evaluator agents for building full-stack applications over multi-hour autonomous coding sessions. The evaluator uses Playwright to test the running app against sprint contracts, and a retro game maker built with the harness worked end to end where a single-agent run's core feature did not. The author later removed the sprint construct and kept only the components still needed on Opus 4.6.

Why it matters: The post shows how a generator-evaluator loop, with explicit grading criteria and a tuned QA agent, turned a solo run's broken output into a working app, and how the harness was pruned as models improved.