Skip to content

AI coding

Everything about AI writing code: coding assistants, vibe coding, code model evals and new developer workflows.

1,426 picksRelated topicsAgentsCursorTutorials

Latest picks

281–300 of 1,426

Sep 23Wednesday

TechCrunch · AI

Anthropic releases Opus 5.5 with lower prices and Fable-level performance

Anthropic launched Opus 5.5 on Tuesday, calling it “the strongest-performing model we've tested to date.” The company claims new state-of-the-art results in coding and knowledge work, with lower prices than previous Opus models. The post doesn't disclose specific pricing, benchmark scores, or a direct comparison with Fable, so I'd hold off on the “strongest” claim until third-party evals land.

Why it matters: Anthropic's new flagship Opus 5.5 beats the larger Fable model on coding and knowledge-work benchmarks while cutting prices.

Sep 22Tuesday

claude.dev Blog

How to get the most out of Opus 5.5 in Claude and Claude Code

Anthropic's official guide covers using Opus 5.5 in Claude and Claude Code, spanning prompts, long-task control and result checks. It recommends stating clear completion criteria, setting in CLAUDE.md the conditions for continuing versus stopping to ask, keeping task lists in files, and checking the evidence sub-agents submit.

Why it matters: Anthropic's guide breaks long tasks into completion criteria, stop conditions and result checks, using file lists and sub-agent evidence to cut missed steps.

Hacker News front page

JetBrains Air: A product system for agentic software development

JetBrains consolidates six months of agentic development experiments into Air, an open system spanning developers, teams, and orgs. It goes beyond the IDE with multi-surface, multi-service design, betting on a multi-vendor future. The post confirms Central CLI, shared context, cloud agents, automations, and AI cost controls are already rolling out, but pricing and GA dates aren't disclosed.

Why it matters: JetBrains folded its previously public agent development experiments into the Air product line: Air inside the IDE, Air Teams, and Air Governance, renamed from JetBrains Central, covering team collaboration and governance.

Latent Space

Xiaomi MiMo-V2.6-Pro tops open weights leaderboard, trained for $3M

Xiaomi released the MiMo-V2.6 series. The Pro version ranks #1 among open weights models on the Artificial Analysis Intelligence Index with a score of 46, at a training cost of $3M. A Flash variant targets efficiency, and an UltraSpeed variant offers 20x faster output. The technical report details RL scaling across three axes: larger batches and throughput, richer multi-task environments, and more grader compute. Code and training recipes are open-sourced, but the 7k+ task datasets are not yet released. Former DeepSeek engineer Fuli Luo, now at Xiaomi, previously live-streamed the training runs.

Why it matters: Xiaomi MiMo-V2.6-Pro tops the Artificial Analysis open weights intelligence index with 1.02T total and 42B active parameters, trained for about $3M, at $0.13 per task.

Computing Life · Share · Yage

Three AI Coding Stories, Three Numbers to Read

ZCode was caught silently packaging entire Git histories for cloud upload, with .git objects making up 86.6% of snapshots. HarnessTax benchmarked Claude Fable 5 across frameworks: Claude Code and minimal Pi achieved near-identical success rates but a 2x cost gap. A Microsoft architect replaced multi-model agent loops with a single model reading skill docs and calling tools directly—halving API calls but increasing total tokens by 22%. Each story unpacks one number and a reminder to check which layer a metric actually measures.

Why it matters: A single sample shows ZCode packaging the whole workspace, .git included, which can carry secrets and internal branch names to the cloud.

AI HOT (Curated Pool)

NVIDIA Nemotron 3.5 Lightning: a 30B sparse model built for high-frequency agent execution

NVIDIA positions Nemotron 3.5 Lightning as the execution layer in agent workflows—handling frequent tool calls, file reads, and result checks rather than heavy planning. It's a 30B MoE model that activates only ~3B parameters per token, keeping latency and cost low for high-volume calls. It complements, not replaces, Nemotron 3 Ultra. Weights are open, with tool calling and structured output support. Context goes up to 1M tokens, though OpenRouter's standard tier caps at 262K. Worth a look if your agent makes many model calls per run.

Why it matters: OpenRouter explains where NVIDIA's Nemotron 3.5 Lightning sits in an agent pipeline and how it splits planning and execution with Nemotron 3 Ultra, trading cost against latency.

AI HOT (Curated Pool)

Xiaomi MiMo-V2.6-Pro hits ~10th on Code Arena WebDev, ~3rd among open-weight models

Xiaomi released two omni-modal models: MiMo-V2.6-Pro and Flash. The Pro version scored 1628 on Code Arena WebDev, up 153 points from MiMo-V2.5-Pro's 1475, landing around 10th overall and ~3rd among open-weight models under MIT license. The post doesn't disclose Flash's benchmark numbers or parameter counts.

Why it matters: Xiaomi's MiMo-V2.6-Pro scored 1628 on the Code Arena web development leaderboard, 153 points above the previous generation, around 10th overall and about 3rd among MIT-licensed open-weight models.

AI HOT (Curated Pool)

Xiaomi releases MiMo-V2.6 Pro and Flash, two fully multimodal open-source models

Xiaomi MiMo dropped two fully multimodal open-source models. The Pro version matches Claude Opus 5 and GPT-5.6 Sol on most agent benchmarks and scores 46 on the Artificial Analysis Intelligence Index—the highest among open-source models so far. Capabilities span coding, computer use, 3D reasoning, and creative tasks. The post doesn't disclose parameter counts, training details, or where Flash sits in the lineup, so I'd hold off on direct comparisons for now.

Why it matters: Xiaomi shipped two open-weight omni-modal models, and the Pro version matches Claude Opus 5 and GPT-5.6 Sol on most agent benchmarks.

Sep 21Monday

AI HOT (Curated Pool)

xAI launches Grok 4.7, twice as fast as Grok 4.6 at the same price

Grok 4.7 uses a larger base model and a longer RL run on harder, multi-hour tasks. It scores 46.3% on CursorBench 4.0, ahead of GPT-5.6 Sol Max (41.7%) but behind Fable 5.1 Max (51.8%). Pricing stays at $2/$6 per million input/output tokens, same as Grok 4.6, with double the speed. Safety stack is new: only 3.3% of risky cyber prompts get through, and it hits 62.4% on LatchBio's biosafety benchmark. Available today in Cursor, Grok Build, and the API.

Why it matters: xAI ships Grok 4.7 with a larger base model and longer RL training, and publishes price and score comparisons against Grok 4.6, GPT-5.6 Sol and Fable 5.1 on coding, engineering and knowledge work benchmarks.

Hacker News front page

Will Larson tries the software factory pattern at Imprint, letting agents own goals, fill gaps, and push PRs

Will Larson pushed his agent setup at Imprint further: give an agent a Linear project, and it first checks for a Notion RFC and Datadog/Snowflake dashboards—prompting you to create them if missing. It then scans task status, adds newly identified work, and picks up unblocked tasks to write PRs, nudge reviews, or ask clarifying questions. After a task completes, if the project description is stale, it re-runs the full loop. Larson says this forced him to hand over goal-state he used to hoard, so agents can now judge direction. He plans to move this loop from local to the company's internal 'Agent Fleet' orchestrator. The post does not disclose performance numbers or cost.

Why it matters: Will Larson documents how he used the /linear-project-loop skill to have an AI agent read Linear projects, create missing tasks and open PRs, a first-hand reference for agent-driven development.

Sep 20Sunday

Hacker News front page

Microsoft used AI agents to port Copilot runtime from C# to Rust for $120K

A Microsoft team used an in-house AI agent system called Nachete to rewrite the Copilot runtime from C# to Rust, at a total cost of about $120K. The agents ran 7 iterations—writing code, compiling, and fixing errors—producing 125K lines of Rust that compiled on the first try. Humans only did code review and security audit. The team estimates a manual rewrite would have cost $1.1M and taken 9 months, though the post doesn't detail how that baseline was calculated.

Why it matters: Microsoft moved the GitHub Copilot runtime from TypeScript to Rust with AI agents for about $120K in tokens plus roughly three weeks of developer time, a concrete data point on large refactors.

Hacker News front page

The Chief of Staff Pattern: One Claude Code session coordinates, others execute

This post describes a pattern for running long Claude Code sessions reliably: separate coordination from execution. One long-lived session assigns work, verifies claims, and records lessons, while short-lived sessions do the actual coding. State lives in a durable external board, not in context. The key discipline is to never trust an agent's self-report—re-run the commands and check exit codes. cmux is used to spawn execution workspaces. The pattern is essentially orchestrator-worker; the author calls it Chief of Staff but notes it's different from Anthropic's calendar-managing agent of the same name.

Why it matters: A reusable multi-session orchestration method: a long-lived coordinator session assigns work and re-runs every command an execution session claims, with state on an external board instead of in the context window.

Hacker News front page

StepFun launches Step 5 Preview, a 600B MoE flagship model targeting coding and finance

StepFun introduces Step 5 Preview, a 600B-parameter MoE model with 27B active per token, a 1M-token context window, and vision support. It scores 67.7 on DeepSWE v1.1, ahead of Kimi K3 and GLM-5.3 but behind GPT-6 Astra and Claude Opus 5. On the in-house StepCodeBench it hits 49.0, again leading domestic models and trailing the two US labs. On FrontierFinance it reaches 66.4, second only to Claude Opus 5. Artificial Analysis gives it an intelligence index of 44; StepFun claims substantially lower cost per task at comparable intelligence. The post does not disclose API pricing, release timeline, or training details.

Why it matters: StepFun released Step 5 Preview, a 600B-parameter MoE flagship aimed at coding and finance, scoring slightly above Kimi K3 and GLM-5.3 on public coding benchmarks such as DeepSWE v1.1.

Sep 19Saturday

Computing Life · Share · Yage

Anthropic postmortem: when AI writes code too fast, patching test infra stops paying off

Anthropic's test-impact-analysis service saw 25× load growth in six months. Three patches bought 70 days, 29 days, then less than a day of stability. One engineer rewrote it in three weeks—a task the author estimates would have taken a quarter a year ago. The rewrite cost dropped while the hidden cost of patching rose, shifting the break-even point earlier. The post does not disclose the new system's exact running cost, defect rates, or production incident data.

Why it matters: Anthropic's review of a CI test accounting service shows the stable window after three patches shrinking from 70 days to under one, while rewrite cost fell from a quarter to three weeks for one person.

TechCrunch · AI

A ChatGPT inventor built Jev, a model that runs code instead of chatting, and developers are excited

Diogo Almeida, a former OpenAI researcher who co-invented RLHF, built a model called Jev that optimizes for code execution rather than human language. It's still a transformer, but TypeSafe AI designed it to run programs and call APIs directly, acting more like an automation agent. Developer reception has been enthusiastic. The post doesn't disclose benchmark scores, pricing, or whether weights will be open.

Why it matters: TypeSafe AI, founded by former OpenAI researcher Diogo Almeida, ships Jev, a model that outputs probability decisions instead of text, giving developers a path around hallucination in code and API calls.

Hacker News front page

There's no point at which turning your brain off will work

Dan Luu notes a growing trend of developers blindly trusting LLM outputs and acting as a 'meat proxy' in a loop. By September 2026, this brain-off approach can produce barely functional software, but Luu argues that if LLMs get good enough to work unsupervised, companies will just run the loop themselves and lay off the human. He shares concrete failures, including an AI bot weaker than a simple heuristic bot and a commercial product trapping users in an infinite loop. Luke Burton adds that high-value tasks still require constant supervision due to too many unknown unknowns.

Why it matters: Dan Luu argues that as LLMs improve, more people assume their summaries and code are correct, a meat-proxy habit that works better in September 2026 than in early 2025 but still ships badly broken software.

Sep 18Friday

AI HOT (Curated Pool)

Justin Cormack on AI Agent Evaluation: Start With Evidence, Not Coverage

Justin Cormack built an S3-compatible storage system with AI, reaching 350k lines of Rust. He ran 1,500 tests against real S3 as an oracle, which caught real S3 500 errors. Chasing 100% coverage backfired—agents wrote trivial tests. Docs were often wrong, and AI was bad at finding edge cases from them. His hard rule: fix flaky tests immediately, or the agent learns to ignore failures.

Why it matters: Justin Cormack built an S3-compatible object store in about 350,000 lines of Rust and pinned its behavior with roughly 1,500 S3 tests, a reusable evidence-based method for evaluating AI agents.

AI HOT (Curated Pool)

Trail of Bits Used AI Agents to Build an LSP, Decompiler, and Lean Proofs for a Miden zkVM Audit

Before auditing the Miden zkVM, Trail of Bits spent six months having AI agents build an LSP server, a decompiler, a static analysis engine, and a Lean formal model from scratch. These tools found real bugs, including an unvalidated input that let a malicious prover forge Falcon signatures and steal funds. The Lean work produced 95 machine-checked correctness proofs. The post mentions Claude built the LSP prototype but doesn't name the specific models used for other tools.

Why it matters: Trail of Bits spent six months building AI agents that found a flaw letting attackers forge Falcon signatures and steal funds.

Hacker News front page

ZCode coding agent silently uploads your entire Git history; only Z.ai holds the decryption key

Developer ferstar reverse-engineered ZCode, Z.ai's desktop coding agent, and found it silently packs the entire workspace—.git history, LFS cache, reflogs, global configs—encrypts it, and uploads to Aliyun OSS whenever logged in. A 345MB commercial workspace became a 313MB encrypted archive; .git alone was 86.6%. The app uses envelope encryption: the symmetric key is wrapped with an RSA public key delivered by Z.ai's server, and the private key lives only in Z.ai's cloud. The user cannot decrypt their own data. The upload pipeline was reconstructed from the client's app.asar: request credentials from zcode.z.ai, pack and encrypt locally, POST directly to Aliyun OSS. In-app privacy toggles don't stop it, and the privacy policy doesn't mention it. The post hit 276K views; a Chinese-language alert urged users to disable ZCode. If you run GLM locally, remember: open weights don't make the closed harness safe. The only working defense is keeping projects outside ZCode's reach or not using it.

Why it matters: Developer ferstar's reverse engineering found that after login ZCode encrypts and uploads the whole workspace, including full .git history, to Alibaba Cloud OSS, with the decryption key held only by Z.ai.

AI HOT (Curated Pool)

WSJ: Three researchers used Claude Opus 5 to chain a Discourse bug into access to OpenAI's private code

WSJ reports three researchers used Claude Opus 5 to chain a Discourse vulnerability into access to OpenAI employee auth tokens. Some forum tokens also worked on ChatGPT and reached OpenAI's GitHub services. The post doesn't spell out how the bug was exploited or whether OpenAI has patched it.

Why it matters: Claude Opus 5 used to breach OpenAI's private repos—strong reversal that security and capability evaluation circles will debate. Deduction: WSJ doesn't disclose exploit details or OpenAI's post-incident response, leaving a factual gap.