#Coding

AIOpenRouter has released Ori Eval, an agent-driven tool that runs your app's prompts against candidate models and returns a comparison table of catch rate, latency, cost per PR, and pass/fail results. The tool asserts on called tools and grades open-ended answers with an LLM judge, pinning the harness and model during each run. Its evals are code files that can run in CI to block regressions and re-run when new models ship.

AIAndrej Karpathy gave Claude Opus 5 the first paragraph of Lord of the Rings with a 1M token budget and asked for a Three.js render. Opus spent about two hours writing 5500 lines of code that procedurally renders the story, which Karpathy calls janky but fun. He notes the model struggled to audit its work because it cannot efficiently perceive video or play the resulting game, relying on slow screenshots that led to several errors.

AIDeepSeek has released the official DeepSeek-V4-Flash API in public beta, with substantially upgraded agent capabilities. The company says its benchmark scores now far surpass those of V4-Pro-Preview. The official V4-Flash natively supports the Responses API format and is adapted for Codex, with configuration details in DeepSeek's API docs.

AIDeepSeek has released the DeepSeek-V4-Flash API in public beta, and developers can use the latest version by setting the model name to deepseek-v4-flash. The source reports agent benchmark results far above V4-Pro-Preview, including 82.7 on Terminal Bench 2.1 and 70.3 on Toolathlon verified. V4-Flash natively supports the Responses API format and is adapted for Codex, while V4-Pro and the APP/WEB models are unchanged.

Why it matters: The release lists agent benchmark results against V4-Pro-Preview and notes Responses API support for Codex, which helps developers gauge the upgrade's practical effect on their workflows.

AIThe model scores 31.6% on HLE, ahead of Inkling's 29.7%, and keeps that advantage at every thinking budget. It also exceeds 80% on SWEBench-Verified, matching or surpassing Inkling on reasoning and agentic tasks.

AIThinking Machines says Inkling-Small began training after its larger counterpart and benefits from the lessons learned. The post cites an improved pre-training data mix, a refined ML recipe, on-policy distillation using Inkling as the teacher, and two additional weeks of agentic coding RL.

AIPoolside released Laguna S 2.1, an open-weights agentic coding model with 118 billion total parameters and about 8 billion active per token, supporting up to a million tokens of context. Quantized, it fits on one NVIDIA DGX Spark, and Poolside reports 70.2% on Terminal-Bench 2.1 with thinking enabled, with its evaluation trajectories published online. The same week it shipped the Poolside Desktop Assistant for macOS, which runs Laguna locally or alongside Claude Code, Codex, and Gemini agents.

AIAugment Code has made GPT-5.6 Sol the default model in Cosmos, choosing it as the most token-efficient model to clear its pass-rate floor for long-horizon software engineering tasks. The company ranks models by cost per task rather than list price per million tokens, since retries on failed steps add token spend. Users can still select any model, and the default will change as more token-efficient models emerge.

AIJetBrains tested the ponytail skill for Claude Code across 80 paired tasks and found a median 10.3% cost reduction, with p=0.004. Code written fell about 15% median versus the advertised 54%, reaching 31% on larger builds and little on already-lean tasks. No quality difference was detected, and the skill only self-activated when its ruleset was injected by a plugin hook.

Why it matters: The benchmark separates advertised savings from measured results and shows the code cut depends on how much the baseline agent over-builds.

AISkywork Design claims to replace a multi-step design process of requirements, meetings, revisions, and handoffs with a single step: prompt to editable prototype. The post frames the change as reducing steps and waiting time rather than improving creativity, though it provides no benchmarks or timing figures.

AICursor says its India user base tripled in the past year and that Indian users make more agent requests per user than any other country. It is launching Cursor Start, a ₹649/month plan with generous access to Grok 4.5 and Composer for Indian developers.

AIKimi K3 is now available on Together AI, which is a Day 0 launch partner for the model. Together AI offers developers immediate access to K3 through high-throughput inference aimed at coding agents and production workloads.

AIFireworks AI made the open-weight Kimi K3 available for inference and training on its platform, with US-only serverless endpoints and Zero Data Retention. In its own head-to-head with Opus 5, the post reports K3 at 92.7% accuracy and $0.52 per task on SWE (480) against Opus 5's 94.8% and $1.05, with the vendor claiming up to 5x better cost efficiency per task.

Why it matters: The post compares Kimi K3 with Opus 5 on accuracy and cost per task, giving readers concrete figures to judge the open model against closed alternatives for their own workloads.

AIEvoCode-Bench is a multi-turn coding benchmark with 26 tasks spanning 227 sequential rounds, where agents keep a persistent workspace and must pass cumulative tests after each evolving instruction. The results show that agents perform much worse when building on their own prior work than when starting from a clean, human-completed codebase. Regressions, not failure to implement new features, are the main bottleneck, and agents that maintained a persistent requirements document more than doubled their success rates.

AITrilogy released an AI Cybersecurity Playbook built around Kimi K3, served on Fireworks through an OpenAI-compatible API. The playbook pairs deterministic tools for indexing, parsing, and deduplication with Kimi K3 for reachability, impact, and remediation judgment, followed by a separate verification stage.

AIAnthropic's Noah Zweben says a tornado-physics assignment he once TA'd for, built in Unity, is his favorite Opus 5 example so far. The quoted Atomic Chat post compares Opus 5, Fable 5, Kimi K3, and GPT 5.6 on three HTML physics scenes, with Opus 5 costing $1.40 versus Fable 5's $2.82.

AIAnthropic's Noah Zweben asked "Is this AGI?" in a post about a Rocket League clone reportedly built by Opus 5. The quoted post credits Opus 5 with building a game and 3D model that it calls the best it has seen, using 27% of a 5x Max subscription.

AICohereLabs has published North-Mini-Code-1.0-eagle, an Eagle draft model for its North-Mini-Code-1.0 target model. The three-layer draft uses dense transformer blocks and sliding window attention, and it is compatible with fp8 and w4a16 target checkpoints in vLLM.

AIMike Krieger, who is associated with Anthropic, says two games were built from prompts of about four sentences that used dynamic /workflows extensively. He contrasts this with earlier in the year, when he relied on a bespoke harness and verification system, noting that current models accomplish much more with far less instruction.

AIAnthropic co-founder Mike Krieger said he had Opus 5 build a renderer, savegame parser, and boat, plane, truck, and bus simulator overnight. The project lets him walk around the world of Transport Tycoon, an idea he had wanted since he was six years old.

AIAnthropic co-founder Mike Krieger says Claude Opus 5 has become his daily driver at work and on weekends. He reports it can work for hours on complex tasks and consistently gets to the bottom of tricky problems, and he has also built some games with it. Anthropic's announcement describes Opus 5 as close to the frontier intelligence of Fable 5 at half the price.

AIBerkeley's STAR Lab packaged multiple LLM-based "autoresearch" algorithms into a single API within the GEPA package, letting users mix and match them. The optimizers can be applied to tasks including prompt writing, agent design, and code optimization. The quoted thread adds that GEPA, AutoResearch, and Meta-Harness each win on different tasks, and that the new optimize_anything omni meta-optimizer beats every standalone optimizer at a matched budget.

AIEthan Mollick's guide says ChatGPT and Claude are the main choices for real work, since their agent modes can act on a computer. He separates agent modes that run on the company's computers from those that access the user's own computer. He recommends keeping approval settings on for sending, spending, or deleting, because of prompt injection risk. He also notes that Gemini currently lags for agentic work, though its Notebook and video tools are useful.

AICognition has signed a memorandum of understanding with the U.S. Department of Energy to join the Genesis Mission, a national AI initiative launched by executive order in November 2025. Cognition will contribute its Devin autonomous AI software engineer in four areas: software and data security, modernizing legacy scientific code, expanding scientific workforce capacity, and cloud modernization. Devin Desktop and CLI are listed as FedRAMP Class D (High) Authorized, and the company has offered in-kind code security scans for national laboratory codebases.

AIPoolside released Laguna S 2.1, an open-weight model with 118B total parameters and 8B active per token. The author says it performs strongly on agentic coding and long-horizon tasks, and it can run on a single NVIDIA DGX Spark. Weights are on Hugging Face under the OpenMDW-1.1 license, with access also available through OpenRouter and Poolside's API.

AIGemini 3.6 Flash has launched on Antigravity, according to Varun Mohan. The post also says everyone's weekly quotas were reset.

AIJetBrains Air now connects to ACP-compatible coding agents, including GitHub Copilot CLI, OpenCode, Pi, and Cline, through the Agent Client Protocol. The release also adds Beta Java and Kotlin navigation and diagnostics powered by the IntelliJ IDEA code engine, local model support through Ollama or LM Studio, and Docker-based agent tasks on Windows.

AIGoogle introduces Gemini 3.6 Flash as its workhorse model, with better coding, knowledge work, and multimodal performance while reducing token usage. It also launches Gemini 3.5 Flash-Lite, described as the fastest and most cost-effective 3.5-class model for high-throughput applications, and 3.5 Flash Cyber, a version of 3.5 Flash fine-tuned to find and fix cybersecurity vulnerabilities.

Why it matters: The post lists three distinct models, each aimed at a different job, so readers can map which one fits coding, high-volume, or security workloads.

AIJetBrains has launched JetBrains Context in early access, a repository intelligence layer that builds a semantic index so coding agents can retrieve relevant code without repeated searching. In tests on 205 SWE-bench tasks, 175 production-monorepo tasks, and 1,953 code-localization tasks, it reduced agent turns by up to 68%, latency by up to 59%, and execution cost by up to 48%. It works with Claude Code, Codex CLI, and Junie CLI at no additional cost for JetBrains AI subscribers, and it does not store source code on JetBrains Context servers.

Why it matters: The source gives benchmark figures for turns, latency, and cost, showing how repository indexing might change agent workflows on large codebases.

AISebastien Bubeck says GPT, using Codex, found a counterexample to a math problem, with its reasoning described as superb. He highlights that Codex's write-up undermines the "illusion of thinking" argument and shares the exact prompt used on internal Codex.

AICognition says its one-year-old merger with Windsurf has produced a more capable Devin, which now manages other Devins at a mid-to-senior engineering level, and new SWE-1.7 model, described as its most capable and efficient to date. The company reports growing from 44 to 350 people and revenue run rate from $73M to $500M+ since merging the brands.

AICognition found that Fable 5 led runs cost less than Opus 4.8 led runs on FrontierCode 1.1 when both used the same sidekick, $1.86 versus $2.04 per run. Fable 5 scored 60.7 against 54.6 for Opus 4.8 in those configurations, and it took fewer lead turns, delegated earlier, and rarely edited code itself. The post attributes the difference to delegation style rather than per-token price, and notes that the approach gives little benefit on short or serial debugging tasks.

Why it matters: The source compares lead-model delegation habits on a coding benchmark, showing how a pricier model can lower total agent cost through fewer turns and better handoffs.

AICognition's entire platform, including Devin Cloud, is now FedRAMP Class D (High) In-Process and listed on the FedRAMP Marketplace, extending FedRAMP High authorization beyond Devin Desktop (formerly Windsurf). Devin Desktop and CLI are already FedRAMP High Authorized for workloads with ITAR and DoW IL4, IL5, and IL6 requirements. The company says Devin Security Swarm can find and validate vulnerabilities and open remediation pull requests, and that fleets of Devins can upgrade legacy software 5-40x faster than humans alone.

AIAnthropic is extending access to Claude Fable 5 on all paid plans through July 19. Claude Code's weekly rate limits will also stay 50% higher during the same period.

AIClaude Code on desktop now includes an in-app browser that can open any website. Claude can read, click through, and interact with sites as it does with local dev servers, and the browser is sandboxed and configurable, letting users choose whether sessions persist.

AIOpenAI introduced ChatGPT Work, a new agent inside ChatGPT powered by Codex and GPT-5.6. The quoted announcement says it can take action across apps and files, stay with a project for hours if needed, and turn a goal into finished work. Fidji Simo's own post adds that the team has worked to make Chat more agentic for a while.

AIMeta Superintelligence Labs has introduced Muse Spark 1.1, a multimodal reasoning model aimed at agentic tasks, with gains in tool use, computer use, coding, and multimodal understanding. It supports a 1 million token context window and is available in Thinking mode in the Meta AI app and on meta.ai, with developers able to access it through a public preview of the Meta Model API.

Why it matters: The post specifies Muse Spark 1.1's agent, coding, and multimodal gains and its Meta Model API preview access, which helps developers judge its fit for their workflows.

AICursor's Aman Sanger says the new model is an enormous improvement over Composer 2.5 and was trained entirely from scratch with the SpaceXAI team. The quoted Cursor post identifies it as Grok 4.5, Cursor's most powerful model yet and the first built for more than software engineering.

AICursor co-founder Michael Truell announced Grok 4.5, a model trained with SpaceXAI that the post calls Opus-class, fast, and low cost. He says it is a significant step up over Composer 2.5 and has become the daily driver for many on the Cursor team. A benchmark table shows Grok 4.5 at 83.3% on Terminal-Bench 2.1 and 78.0% on SWE-Bench Multilingual, with the post saying more releases will follow.

AICognition launched SWE-1.7, which it says reaches frontier-level coding performance at lower cost, trained from a Kimi K2.7 base. The post describes RL methods including top-p sampling replay to preserve entropy, compressed weight deltas across multi-cluster training, and self-compaction for rollouts up to six hours. SWE-1.7 is available in Devin via Cerebras at 1000 TPS.

Why it matters: The post details entropy preservation, multi-cluster weight sync, and self-compaction, offering concrete RL training techniques for long-horizon coding agents to compare against one's own pipeline.