Skip to content

Areas

AI coding Latest news

Coding assistants, vibe coding, code model evaluations, and changes to software development workflows.

114 picksPast 30 days: 35 itemsTotal: 716 items

Updated

Top picks archive · Page 4

Aug 4

Aug 4TueItems 61–80
  1. Zed Blog65

    Zed Enables OS-Level Sandboxing by Default for Its Agent Panel

    Zed's agent panel now sandboxes its terminal and fetch tools by default, starting in release 1.14, and the restrictions are enforced by the operating system rather than by agent instructions. By default the sandbox blocks writes outside project directories, writes to .git, and network requests, and agents can request temporary escalation with a stated reason. The post also notes that sandboxing covers only those tools and does not protect against other tools, external programs, or the regular built-in terminal.

    Why it matters: The post explains how OS-enforced sandboxing limits agent terminal and fetch access, and why fine-grained command rules fall short of it.

Jul 31

Jul 31Fri
  1. DeepSeek API News67

    DeepSeek-V4-Flash API enters public beta with stronger agent benchmarks

    DeepSeek 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.

Jul 28

Jul 28Tue
  1. JetBrains AI Blog60

    Ponytail Skill Cuts Claude Code Costs 10% But Not the Advertised 54%

    JetBrains 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.

Jul 26

Jul 26Sun
  1. Fireworks AI Blog60

    Fireworks AI adds open-weight Kimi K3 with US-only serverless endpoints

    Fireworks 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.

Jul 21

Jul 21Tue
  1. koray kavukcuoglu72

    Google releases Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber

    Google 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.

  2. JetBrains AI Blog62

    JetBrains Context adds repository indexing to coding agents in early access

    JetBrains 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.

Jul 13

Jul 13Mon
  1. Cognition Blog (Devin, Windsurf)62

    Fable 5 with a sidekick costs less than Opus 4.8 on FrontierCode

    Cognition 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.

Jul 9

Jul 9Thu
  1. Meta AI Blog72

    Meta releases Muse Spark 1.1 with agent and coding gains

    Meta 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.

Jul 8

Jul 8Wed
  1. Cognition Blog (Devin, Windsurf)62

    Cognition releases SWE-1.7, a coding model trained with long-horizon RL

    Cognition 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.

Jun 29

Jun 29Mon
  1. Cognition Blog (Devin, Windsurf)62

    Cognition's Devin Fusion routes coding work between two models to cut cost

    Cognition has released a preview of Devin Fusion, a multi-model harness that runs a frontier main agent alongside a cheaper sidekick agent. On FrontierCode 1.1 Extended, the company reports scores near frontier models at up to 60% lower cost per task, and 41% lower cost when paired with Fable 5, which access was suspended from June 12, 2026.

    Why it matters: The post explains a sidekick architecture with cached persistent contexts, which contrasts with advisor-style tools and shows how cost cuts depend on the main model's delegation behavior.

Jun 16

Jun 16Tue
  1. Z.ai (GLM) · new models on Hugging Face72

    Z.ai releases GLM-5.2 with 1M-token context and MIT open-source license

    Z.ai has released GLM-5.2, its flagship model for long-horizon tasks, which it says substantially improves on GLM-5.1 and supports a 1M-token context. The model adds IndexShare, which cuts per-token FLOPs by 2.9× at 1M context, and is released under the MIT open-source license.

    Why it matters: The source gives benchmark tables against named rival models and deployment settings, useful for judging where GLM-5.2 sits among current flagship models.

Jun 15

Jun 15Mon
  1. Z.ai Release Notes62

    Z.ai Release Notes: GLM-5.2 Adds 1M Lossless Context for Long Tasks

    Z.ai's release notes list GLM-5.2 as supporting 1M lossless context, with improved long-horizon task performance and reduced context drift and goal forgetting. The company says GLM-5.2 achieves open-source SOTA performance on coding and long-horizon task benchmarks. The page also includes the newer GLM-5.3 and GLM-5.3-Flash entries, which are listed above GLM-5.2.

    Why it matters: The page lists a dated series of Z.ai model releases, showing how the coding and long-horizon agent line has evolved from GLM-4.5 through GLM-5.2.

Jun 11

Jun 11Thu
  1. Moonshot AI (Kimi) · new models on Hugging Face62

    Moonshot AI releases Kimi K2.7 Code, a coding-focused agentic model

    Moonshot AI published Kimi-K2.7-Code, a coding-focused agentic model built on Kimi K2.6, with a 1T-parameter MoE architecture and 32B activated parameters. The model card reports about 30% fewer thinking tokens than K2.6 and benchmark results against GPT-5.5 and Claude Opus 4.8, with weights and code released under a Modified MIT License.

    Why it matters: The model card gives benchmark comparisons against GPT-5.5 and Claude Opus 4.8 on coding and agentic tasks, useful for judging its position among current coding models.

Jun 10

Jun 10Wed
  1. Xiaomi MiMo67

    Xiaomi releases open-source MiMo Code V0.1 terminal coding assistant

    Xiaomi MiMo has released MiMo Code V0.1, an open-source AI coding assistant for the terminal under the MIT license. It ships with MiMo V2.5, a multimodal model offered free for a limited time with a million-token context window. The tool automatically loads existing Claude Code skills, MCP servers and commands, and reuses API configuration, and it supports providers including Anthropic, OpenAI, DeepSeek, Kimi and GLM.

    Why it matters: The post specifies MiMo Code's Claude Code compatibility and MIT license, which bear directly on whether existing coding-agent setups can migrate without rework.

  2. Xiaomi MiMo82

    MiMo Code open-sources a terminal coding agent for long-horizon tasks

    Xiaomi's MiMo team released MiMo Code, an MIT-licensed terminal coding agent built on OpenCode for long-horizon programming tasks. The design centers on three areas: Max Mode parallel sampling that generates five candidates per turn, Goal-based completion verification, and a memory system that checkpoints session state and rebuilds context. The article reports offline benchmark results and a double-blind A/B test with 1,213 pairs in which MiMo Code's win rate exceeded 65% beyond 200 execution steps.

    Why it matters: The article explains how MiMo Code handles long-horizon coding through computation, checkpointed memory, and cross-session evolution, useful for judging design tradeoffs in coding agents.

Jun 8

Jun 8Mon
  1. Cognition Blog (Devin, Windsurf)70

    Cognition Introduces FrontierCode, a Benchmark for Mergeable Code Quality

    Cognition introduced FrontierCode, a coding benchmark built with open-source maintainers that measures whether models produce code a maintainer would merge. On FrontierCode Diamond, the hardest 50 tasks, Claude Opus 4.8 scored 13.4%, GPT-5.5 scored 6.3%, and Gemini 3.1 Pro scored 4.7%. The authors report 81% fewer misclassification errors than SWE-Bench Pro, though this figure comes from their own analysis of agent trajectories.

    Why it matters: The benchmark's blocker and rubric design shows how code quality can be measured beyond unit-test correctness, which matters for judging coding agents.

Jun 4

Jun 4Thu
  1. Cohere · new models on Hugging Face60

    Cohere releases North Mini Code 1.0, a 30B-A3B open-weights coding model

    Cohere and Cohere Labs released North Mini Code 1.0, an open-weights 30B-A3B mixture-of-experts model for code generation and agentic terminal tasks, under Apache 2.0. The model has 256K context and 64K max output, and is trained for tool use. Its benchmark table lists Terminal-Bench v2 at 36.0, SWE-Bench Verified at 67.6, and LiveCodeBench v6 at 70.3, below Qwen3.6 on several tasks.

    Why it matters: The card lists benchmark results against Qwen3.6, Gemma4, and other models, showing where North Mini Code trails on some coding and agentic tasks.

Jun 3

Jun 3Wed
  1. Cognition Blog (Devin, Windsurf)60

    Cognition launches $10M AI Productivity Guarantee for enterprise Devin customers

    Cognition introduced the AI Productivity Guarantee, under which it will issue credits up to $10M if Devin delivers less engineering value than enterprise customers pay for. The company uses an AI estimator to measure hours of productive output, validated against engineers' own estimates of how long the same work would have taken by hand. Value is converted to dollars at a standard global rate and compared against each customer's consumption near the end of the annual contract.

    Why it matters: The post explains how Cognition estimates Devin's output in hours and backs the estimate with a $10M credit commitment, a concrete model for measuring AI vendor value.

  2. Cognition Blog (Devin, Windsurf)62

    Cognition Estimates Engineering Hours Saved by Its Devin Coding Agent

    Cognition built an automated agent that classifies Devin sessions as productive and estimates the human engineering hours each one would have taken. On 233 held-out sessions the estimator reached an rlog of 0.74, with individual errors often 2 to 3 times in either direction but roughly unbiased in aggregate. The system is calibrated to underestimate and is currently running with Devin customers.

    Why it matters: The post shows how the measurement design, from hours-based metrics to conservative calibration, determines whether agent productivity estimates can be trusted in aggregate.

Jun 2

Jun 2Tue
  1. MiniMax · new models on Hugging Face68

    MiniMax releases M3, a native multimodal model with 1M context

    MiniMax has released MiniMax-M3, a native multimodal model with a 1M-token context window, roughly 428B total parameters, and about 23B activated parameters. The model introduces MiniMax Sparse Attention, which the source says delivers 9× prefill and 15× decode speedups over M2 at 1M context. M3 supports enabled, adaptive, and disabled reasoning modes through the thinking parameter, and weights are available on Hugging Face.

    Why it matters: The source gives concrete attention-efficiency figures and three reasoning modes, which helps readers judge long-context cost against deployment choices.