Coding

AITinker has cut prices up to 70% on long-context prefill and sampling, which now cost the same as short context. The cut lowers the cost of agentic RL rollouts, which spend most of their tokens re-reading growing context, and of evaluating trained models on long inputs. Tinker also added GLM-5.3-Flash and DeepSeek-v4.1-Flash for cost-efficient long-context work.

AISherwin Wu, who owns OpenAI's account context here, says he has been tab-accepting about 40-50% of Codex's next-message suggestions after a week of use. OpenAI Devs says composer predictions, which suggest a user's next message from the conversation and their style, are in beta for Pro users.

AIOpenAI's Codex now suggests the user's next message based on the conversation and how the user talks to it, available in beta for Pro users. Lewis Tunstall of Hugging Face jokes that meat proxies will love the feature.

AILinus Torvalds says he uses AI to do things he is bad at, such as building a user interface for a guitar pedal project he wrote in C. He says AI is a wonderful tool for beginners, but warns that maintainers are stressed by AI-generated Linux kernel patches and bug reports. Torvalds says AI review tools like Sashiko are now appearing on the Linux Kernel Mailing List, with some subsystem maintainers expecting patches to be reviewed before acceptance.

AIJAN3 CTO Jan Ceuleers says he rebuilt the AQUA wallet from Flutter into React Native, using Claude Code for most of the coding. He started by binding GDK to a React Native app and showing a wallet balance in about half an hour, then ported the Aqua UI component library from Flutter over roughly a year of prior work.

AIDex Horthy says the share of tasks that can be one-shot without strict process has grown, but alignment, grilling, and planning workflows still matter. He argues that heavy planning on small tasks makes developers feel slower, and predicts tools will add escape hatches so humans or models can decide to ship directly. He adds that as model capabilities improve, the "smart zone" has grown to roughly 200k–400k tokens, and HumanLayer is prototyping research-to-implement and research-to-short-design-to-implement workflows.

AIA CTO hiring new graduates at a larger company reports they are generally unfamiliar with AI coding tools and have little hands-on use of them. Many of those who did internships worked at traditional companies that also did not use these tools, so they are more fluent in pre-AI software development methods than the "AI-native" label suggests.

AIThe article explains how a software factory combines agents, tools, and engineering practices to take work from intent to verified output. It argues that teams should enforce domain rules, workflow gates, and tool permissions independently, version shared guidance and checks, and review lessons before reuse.

AIA Chinese podcast transcript argues that Opus 5.5 makes code generation, game modding, and language migration much faster and cheaper. It cites examples such as game remakes, Photoshop clones, and ESP32 firmware projects, and says legal and open-source barriers are struggling to keep pace.

AILauren Tan argues that with frontier AI agents, anyone can produce code at machine speed, so PR volume now signals productivity alongside impact. She says the bottleneck is trust in agent output, and that higher token costs are worth it compared with hiring many engineers. She frames the engineer's job as building the software-producing machine rather than writing code directly.

AITessl argues AI code review is slow because generated code outpaces trust, and proposes executable specs that let agents check preview environments against product intent. Its spec reviewer splits work between a planner agent that extracts requirements and parallel verifier agents that test each one against the code and base branch.

AISoftware developer Gergely Orosz questions why he is working more despite AI tools, quoting Sam Newman's view that AI was meant to free developers from drudgery. Newman says most developers are doing more work, with more context switching and a loss of the big picture. The quoted post adds that AI assistants are not human partners and that pairing with them fragments the shared mental model of a program.

AILucas Beyer says he learned Python around 2004 as Blender's scripting language, long before deep learning. He calls it a full-circle moment, as the linked post shows LLMs writing Blender Python code to generate 3D scenes.

AIThe author argues that in agent workflows, the real bottleneck is whether users can precisely express requirements, not the model or agent capability. When people work outside their expertise, they lack the precision needed for prompts and plans, forcing many imprecise iterations that waste time and tokens. The suggested fix is to have the model first teach the unfamiliar domain knowledge before acting.

AIBlock's AI capabilities lead describes using Claude Fable to plan large code migrations and direct smaller models like Opus and Sonnet on individual tasks. He says Block routes frontier and smaller models by task and keeps merges and production deploys behind human dual approval.

Why it matters: Block's engineering lead describes how frontier models orchestrate large migrations and how access, effort levels, and safeguards are managed across an organization.

AIThariq, of Anthropic, says the most common failure in AI coding is users working outside their domain who cannot write precise prompts and plans. As a result, they spend many turns iterating imprecisely. The quoted post contrasts this with programmers' advantage in vibe coding.

AIThis Next Token episode discusses Personal Agents, including Dots in Codex, memory and cloud computer permissions, and whether agents should act as assistants or digital twins. The hosts also cover Instinct's booking and business-travel model, hands-on projects built with Opus 5.5, and whether software, games, and hardware could become open source as AI makes rewriting easier.

AIA solo founder writes that after a rocky first trial, they gave Devin Max a second chance and now favor Devin Cloud for shipping real projects. The post praises Cognition and Devin Max's model access and pricing, and covers SWE-1.7 Lightning's speed and its tendency to consume limits quickly. It also compares GPT 6 Astra and Fable 5.1, finding Fable more efficient for bug fixes and features.

AILauren Tan (@poteto) proposes "time to (fully automated, hands-off) rewrite" (TTR) as a rough thought-experiment heuristic for how well a codebase is set up for agents. She suggests asking how long a single engineer would need to rewrite the code in another language, framework, or architecture, since the answer surfaces gaps like missing verification that agents can use to confirm user-visible behavior matches. The post also raises questions about whether a rewrite would improve, maintain, or regress performance and maintainability over time.

AIAnthropic's Lydia Hallie says Claude Haiku 5.5 suits mostly reading, small edits, and tool calls that need little reasoning. The quoted @claudeai post introduces Haiku 5.5 as Anthropic's cheapest, fastest, and most capable small model, costing around 75% less to run than Claude Haiku 4.5.

AIA startup's founders report that a single engineer built polished, reliable web, desktop, iOS, and Android apps in six months using AI. The post argues AI is turning 10x engineers into 100x engineers, a capability it says was not possible last year.

AIThe newsletter argues that AI competition is shifting toward completed workflows, citing OpenAI's September 29 DevDay announcements on cost and infrastructure and Google's September 30 introduction of Gemini 4 Argon for longer, more demanding reasoning tasks. It says coding agents must inspect repositories, edit code, run tests, and deliver reviewable work, so cost, context, and supervision matter alongside model intelligence.

AITibo of OpenAI advises users to switch from full-access to auto-review mode. He says the change is no longer a trade-off and offers greater peace of mind.

AIHarrison Chase, founder of LangChain, endorsed a post on harnesses with the brief comment "Good take on harnesses." The post, from @zeeg, argues that general coding harnesses like Codex will be superseded by specialized ones and that local models will handle most daily tasks within five years.

AIVercel completed migrating Turborepo from Go to Rust, which Rauch says was chosen for better low-level OS access despite controversial returns on human migration costs. He argues that what is best for humans is no longer necessarily best for business now that agents are writing code, and suggests Rust may not be the final toolchain.

AIJerry Liu says ChatGPT/Codex currently has the best agent interface for deep work, unifying coding and knowledge work in one place with forking support that Claude's app lacks. He still prefers Claude Code CLI as close to the best a CLI can be, and uses Opus 5.5 mainly through it for product demos, while noting a GUI is sometimes nicer.

AIThe post argues that in the agent era, AI-driven PR review has become a tool for malicious office politics. Because AI reviews can be used to wear down targets' tokens and positive sentiment, malicious intent is harder to detect than in human review.

AIYuchen Jin argues that terminals, built around files, commands, and processes, are giving way to AI agents where users state intent and the agent operates the machine. He says understanding Linux and systems fundamentals remains valuable as a moat. In a follow-up, he calls the terminal era over for coding agents, saying persistent context matters more than tabs, and names the Codex desktop app as the best agentic UI for now.

AIYuchen Jin argues that the terminal is the wrong interface for coding agents, since managing many tabs creates cognitive overhead while context should persist. He says he rarely needs an IDE like Cursor because he seldom navigates the whole codebase now, calling the agent rather than the file the new primitive. He names the Codex desktop app as the best agentic UI for now, while noting the space is still early.

AIHamel Husain says he cannot understand a demo video for a new Claude Code modding feature, calling it visual slop. He suggests the feature may be cool but argues demos should be understandable to humans. The background post says Claude Code can now be modded to change behavior, customize the UI, or add features via TypeScript or Claude-built mods installed through /plugin.

AIOpus does the math before it writes the game. In a free kick game it works out exactly how hard to kick the ball to land on target. It also drafts code in its thinking in 91% of summaries. Astra does that in about 1 in 5.

AIOpus does the math before it writes the game. In a free kick game it works out exactly how hard to kick the ball to land on target. It also drafts code in its thinking in 91% of summaries. Astra does that in about 1 in 5.

AIAI is changing developer work, and the article recommends three skills: directing AI agents, reviewing AI output instead of trusting the first answer, and using saved time for judgment-heavy problems such as customer needs and tradeoffs. It cites GitHub Copilot's built-in Rubber Duck agent, which uses a second model to critique plans, code, and tests. The author argues that developers remain responsible for outcomes while AI handles more implementation.