#Coding

AIGoogle has released Android Bench 2.0, an updated benchmark that evaluates AI models on long-horizon tasks such as building apps from scratch, migrating cross-platform codebases to Android, and making complex architectural transitions. The benchmark uses continuous completion scoring to show which tasks each model performs well on.

AIGitHub's latest podcast episode examines five common AI hot takes, including whether developers must still read AI-generated code. It argues review effort should match risk, and that Skills and MCP solve different problems. It also says retrieval-augmented generation (RAG) remains useful and works alongside agents, skills, and MCP.

AIMiniMax has opened its Code CLI, making it available on GitHub at The post provides only the repository link and offers no further details on features or availability terms.

AIA global fintech scaled its AI coding agent traffic by running the GLM-5.2 model on Together AI's Dedicated Model Inference, after capacity planning failed to keep pace with unpredictable engineering-hour bursts. The customer gained self-service endpoint provisioning, a metrics API for diagnosing queuing, and live configuration changes that shipped with zero downtime. The setup runs dozens of B200 GPUs at 256K context across multiple replicas.

AIOpenAI has released ChatGPT for Word, letting users access ChatGPT and Codex directly inside Microsoft Word. The post says ChatGPT for Excel and PowerPoint has been growing rapidly, and Word completes that set. The quoted ChatGPT post adds that the tool can draft from notes, rewrite paragraphs, proofread, suggest edits, and flag formatting issues.

AIBoris Cherny says Projects in Claude Code have changed how he codes: he sends thoughts as they come, and Claude splits them into threads that the project remembers. The quoted ClaudeDevs post says Projects is rolling out on desktop and web in beta for select users, running work as parallel cloud sessions that pass context between them.

AIGoogle AI Studio announced that Speakeasy is open sourcing its OpenAPI client generation suite under AGPLv3, following a May 2026 vendor shutdown that disrupted Google's SDK pipeline. The suite covers SDK generation for 7 languages, an agent-native CLI generator, and a documentation MCP server generator. Google says its pipeline now serves six targets with roughly one engineer maintaining it.

AIAnthropic's Claude Code is rolling out Projects on desktop and web, in beta for select users. A project splits work into threads, runs them as parallel cloud sessions, passes context between them, and keeps running after the user leaves. The author says Claude keeps context across tasks and can give an aggregated status update on request.

AIJetBrains describes building Air Context, a RAG pipeline that gives LLM agents semantic code search over real repositories instead of grep. The first installment covers parsing, chunking, and vectorization, arguing that fixed-size line chunks split related code and that structure-aware chunking using language grammar produces better retrieval units.

AIAmp runners can now serve multiple directories, specified with repeated --dir flags or found automatically with --discover-dirs, which scans Git checkouts up to two levels deep by default. Runners also check for new releases about once an hour, install them, and restart into the new version once no thread is running, at most once every 12 hours, with auto-update disabled via amp.runner.autoUpdate.enabled: false.

AIDatabricks rolled out Astra to every engineer, about 3,500 people, after a pilot with around 200 users. Engineers given Astra increased coding spend by roughly 60% compared to baseline. The company reports Astra outperforms Opus 5 and Sol 5.6 on highly complex system design tasks, but sees no clear gain on medium or low complexity coding. Astra gets a separate sub-budget in Unity Gateway to encourage selective use.

AIDatabricks rolled out Astra to all of its engineers and reported internal measurements. Engineers given Astra increased overall coding spend by around 60% compared with baseline, and Astra outperformed prior top models on highly complex system design tasks, while the gain on medium or low complexity tasks was unclear.

AIMatei Zaharia says agent harnesses make a large difference in cost, even on open-source coding benchmarks, and Melissa Pan's research examines why. Her quoted evaluation of seven models across Claude Code, Codex, and Pi found harness choice had little effect on task success but significantly affected cost. A simple harness can be competitive, and the native harness is not always the best.

AIGreg Brockman shared a demo of Codex voice running in CarPlay, letting users build software by speaking while driving. A quoted post from Jonathan Roomer says the setup runs through a third-party iOS app that connects ChatGPT Voice to Codex and his Mac.

AIFormer DeepSeek kernel engineer Shengyu Liu argues that AI industrializing software production could reduce programming to a recreational craft and erode students' engineering skills. His central concern is less whether AI can outthink humans than whether access to it stays widespread or gets concentrated in a few corporations. The post, cited by X.PIN, contrasts this with Western warnings about AI escaping human control.

AIZed has launched the public beta of Delta, a multiplayer environment for coding with agents and reviewing their work, which replaces pull requests with shared threads. Delta is built on DeltaDB, which records edits and messages between Git commits, and it is free during the beta, with paid plans for individuals and teams to follow.

Why it matters: The post explains how Delta replaces pull requests with shared agent threads and DeltaDB, showing a concrete alternative to the GitHub review workflow.

AIGrok Build now has memory, which records conventions, decisions, and project facts after each completed turn and reads them in later sessions. Notes are stored per project plus a global set, and the /dream command organizes them into topic files while /memory opens a read-only browser. The feature is available now and applies to new sessions.

AICognition and AWS have entered a multi-year Strategic Collaboration Agreement to help enterprises deploy the Devin autonomous engineer in production. Devin can be purchased through AWS Marketplace, and the companies are exploring deeper engineering integrations within customers' AWS environments. Mercedes-Benz reportedly used Devin to analyze more than 200,000 lines of COBOL, reducing an estimated eight-month modernization project to eight days.

Why it matters: The collaboration shows how an autonomous coding agent is being packaged for enterprise legacy modernization inside existing AWS environments, with concrete customer migration figures.

AIFactory has raised $200M at a $5B valuation from investors including Blackstone, Khosla Ventures, and Sequoia Capital, bringing its total funding to over $400 million. The company says it will use the capital to accelerate research, product, and global go-to-market efforts. Factory says hundreds of thousands of developers use its platform, with customers including Nvidia, Blackstone, and T-Mobile.

AIMicrosoft Research's latest Research Focus issue covers how coding agents behave at scale, evaluations of AI models that find lymphoma lesions in PET/CT scans, and understanding AI chatbot dependence. It also features research on advancing large-scale decision-making systems.

AIFireworks AI reports that DeepSeek-V4.1-Flash scores 74.34% pass@1 on DeepSWE at $0.430 per task, close to GPT-6-Astra's 74.12% at $6.524. On Terminal-Bench 2.1 it scores 86.5% against Astra's 87.5% at about 12x lower cost per task, while on HLE it trails Astra alone at 34.52% versus 50.40%. The post also reports that a combined oracle router reaches 54.80% on HLE, and that serverless and dedicated API access is available with US-hosted endpoints coming soon.

AIAugment Code reports that size-adjusted output per active developer rose from 12.3 to 55.7 between November 2025 and July 2026, while median time to merge fell from 11.2 to 3.1 hours. The post says the company added specialized agents wherever work was piling up, across planning, review, verification, feedback, and incident response, and kept engineers responsible for product decisions, architecture, and production risk.

Why it matters: The post pairs internal productivity and quality metrics with the order in which agents were added, showing how review and verification bottlenecks shaped a software delivery pipeline.

AIDeepSeek released open weights for V4.1-Flash, which Baseten now offers through its Model APIs. The model has 552B total parameters, 8B active for prefill and 16B for decode, a 1M token context window, and text plus image input. Its Causal Encoder-Decoder design runs only the encoder during prefill and reuses a projected KV cache, and the source reports the global KV cache at a quarter of V4-Flash's memory.

Why it matters: The post explains how the CED architecture splits prefill and decode compute and cuts KV cache memory, which matters for coding agent costs.

AIAndrew Ng argues that skilled AI engineers increasingly drive the build loop and make product decisions rather than merely implementing specifications from product managers and designers. He identifies four key skills for shaping the build: driving the build loop, making product decisions, communicating and leading, and high-agency ownership.

AICognition is making Fusion available in Devin Desktop and CLI, a harness where a frontier lead model plans and reviews while a cheaper sidekick executes. Across listed coding benchmarks, Cognition reports Fusion cuts cost per task by about 11% to 46% versus the lead model alone, while the sidekick does the implementation work. The post recommends pairing Fable 5.1 with SWE-2, and argues price per task matters more than price per token.

AIShanghai Artificial Intelligence Laboratory has released Atria Dawn Preview, an agentic model built on the 744B-parameter MoE GLM-5.2 foundation model, with a 256K context window. The release page reports benchmark results across search, coding, tool use, productivity, and cybersecurity, and describes text-only setup for Codex and Claude Code.

Why it matters: The release page gives a full benchmark table against named rivals and setup steps for Codex and Claude Code, useful for anyone evaluating agentic models.

AIClare Liguori published a manifesto with 10 principles for developers who use AI coding tools but feel they are not shipping much faster. Werner Vogels, owner of this account, called it mandatory reading. The principles are drawn from practices she has seen work across Amazon teams.

AICognition introduces SWE-2, a coding model post-trained from Kimi K3 that scores 50.0% on FrontierCode 1.1 Main, within one point of Fable 5.1 while costing 64% less. The post attributes the gains to an RL algorithm that trains all reasoning-effort levels in one run, with cost penalties tuned to the base model's Pareto frontier. SWE-2 is available starting today in Devin Desktop and CLI, with rollout to Devin Web and Fusion.

Why it matters: The post explains how the cost penalty and length-weighted baseline are derived, which helps readers judge the tradeoffs in coding model post-training.

AISherwin Wu, an OpenAI executive, says employees now use Astra to vibe-code custom forms, deploy them on ChatGPT, and share the links instead of Google Forms. The post describes this as an emerging internal use case around ChatGPT sites.

AIMistral AI helped a European energy operator migrate 40,000 lines of Fortran 77 to C++ for a reservoir simulator with no test suite. The post explains a parity harness that checks numerical agreement between the two codebases, and a workflow where agents coder, tester, and reviewer migrate modules under human review. Its authors note the approach covered the self-contained first sprint of 40,000 of 300,000 lines and that dependent systems would bring additional challenges.

AIGoogle Developers Blog argues that teams building AI coding agents should replace end-to-end benchmark scores with behavioral evaluations that test discrete, observable actions. Examples include asking clarifying questions on underspecified prompts, running a local validator before marking a build change complete, and consulting live search for current information. The post recommends fast, deterministic unit-style checks, outcome-based LLM-as-a-judge checks for complex tasks, and batch runs that track aggregate pass rates over time.

AIAmazon is giving students a free full year of Kiro, its spec-driven coding agent, at 132 universities across 18 countries. The program aims to help students move from idea to working application, the same way teams at Delta, Ericsson, Siemens, and Amazon do.

AICognition has raised over $2B at a $48B valuation, led by Andreessen Horowitz and Accel. The company says run-rate revenue grew from $492M to almost $900M since its May round, and Devin now offers Auto-Triage, Security Swarm, and Automations.

AIXiaomi MiMo has launched MiMo Desktop in invite-only beta, a desktop agent that turns Office files, images, video, audio, and zips into finished, editable output. Invitees also get limited access to next-gen MiMo models, and the post lists features including live previews, region-based editing with versioned rollback, automatic model routing, and browser and computer use with record and replay.

AIOrbital is building an operating system that lets non-CS domains like science and mechanical engineering use its team's computer science expertise to build complex apps and research tools. The author argues that clearly specifying what you want from AI is the key lever for getting value, and that robust results are possible without a CS degree if the right pieces are in place. A quoted post on an ETH Zurich study of 100 developers suggests computer science background predicts vibe coding success more strongly than writing skill.

AIOpenBMB has released MiniCPM5-2B, a dense 2B Transformer built for on-device and resource-constrained deployment, with an average score of 53.9 in its comparison set. The release also opens the UltraData datasets behind it, including UltraX, UltraData-Code, UltraData-SFT-Agent-2609 and UltraData-RL-2609, and includes GGUF, MLX, GPTQ and DSpark variants for common runtimes.

Why it matters: The release pairs a 2B model with open training datasets and reports per-benchmark comparisons against named same-size and larger models, letting readers check the claims directly.

AIMeta's AIRA₃ entered the live competition with an ensemble of models, and the 8th-ranked gold-medal entry combined GPT 5.5 (w/ OpenCode) and Claude 4.8 (w/ ClaudeCode). Post-hoc testing found Muse Spark 1.2 (w/ MuseCode) also reached gold-medal level, while Muse Spark 1.1 (w/ OpenCode) and GLM 5.2 (w/ OpenCode) reached silver-medal level, all graded on the same private test set.

AIA Berkeley Sky Lab researcher says stronger open models and new inference systems will make powerful local AI practical. The linked post reports Qwen3.8-Flash-Next running at 68.3 tok/s on a single RTX 5090 using an NVFP4 checkpoint, with 63GB host RAM and a 51GB n-gram table stored on NVMe at about 0.5% throughput cost.

AIAndrew Ng presented an AI Engineering Skills Map for using coding agents such as Claude Code, Codex, Cursor, OpenCode, and Pi. The workflow he describes covers planning, execution, and deployment with monitoring, and he identifies five key skills: directing the workflow, enabling agent autonomy, reviewing the work, customizing the agent and its environment, and coding agent foundations. The source says these skills matter more as the agents evolve quickly.

AIOpenAI researcher Mark Chen announced GPT-6 Astra, which he described as the company's most capable and aligned model yet. He said it can build and test software, work across apps on a computer, and help with open scientific problems. The post also highlights improved computer use compared with Operator and stronger monitoring that can stop potentially unauthorized agent actions.

Why it matters: The post links a named model release to specific capabilities like computer use and aligned agent behavior, giving readers concrete claims to check against the model.