#Coding

AIReflection AI, an Nvidia-backed startup, released Beam, its first open-weight large model, aimed at coding and agent tasks. The company says Beam is comparable to Z.ai's GLM-5.2 and is approaching Qwen3.8-Max on coding and agent work. Beam has 501 billion total parameters, with 23 billion activated per task in a sparse architecture.

AIDex Horthy says a new Claude Code skill resembles the outline skill HumanLayer bundles, which mixes a /show-me command with planning language. He praises its HTML-based questions, interactive diagrams, and a pipeline that sends questions to the clipboard.

AIPuck users can now run several separate conversations at once, with each getting its own Puck, by pressing + to start one and clicking a conversation's name to switch. Conversations untouched for three days move into an Inactive list to keep the main list short.

AIThe author says Beam, a 501B-parameter open model from Reflection AI, comes close to GLM 5.2 in capability but trails GLM 5.3, Kimi K3, and DeepSeek V4.1 Flash in several areas. The author attributes Beam's competitiveness mainly to inference efficiency, with inference compute at roughly one-third to one-quarter of GLM 5.2's.

AINVIDIA has published Nemotron-Labs-3-Competitive-Coding on Hugging Face, a competitive-programming specialist model built on Nemotron-3-Ultra. The model is available in the NVIDIA-Nemotron-Labs-3-Competitive-Coding-550B-A55B-NVFP4 repository, indicating a 550B-parameter total size with 55B active parameters in NVFP4 format.

AIThariq (@trq212) says he particularly likes the call stacks feature and the ability to annotate code snippets. He credits the call stacks idea to @dillon_mulroy. The post does not specify the product or tool in which these features appear.

AIOllama says it is excited about a new open model from Reflection AI and that more US models are coming to Ollama. Reflection AI's Beam is described as an agentic open model with 501B total parameters and 23B active, with full weights due this month.

AIAlexander Doria argues that sandboxes are the new tokens, a claim presented without elaboration. The post quotes Reflection AI's introduction of Beam, an agentic open model with 501B total parameters and 23B active, with full weights to be released this month.

AIThariq, who works at Anthropic, is developing a skill for Claude Code that produces HTML plans using simple language, code snippets, surfaced questions, and mockups. Linting is used to reduce common failure cases Claude encounters, and he is seeking feedback before a broader release.

AIReflection AI has introduced Beam, an open agentic model with 501B total parameters and 23B active, trained end-to-end from scratch. The company says Beam advances the Western open frontier on coding and agentic tasks, with full weights set for release this month.

AICognition published a blog post about memory and dreaming, linking readers to the full article at devin.ai. The post itself gives no further details, so its specific claims cannot be summarized from this source alone.

AIAdo Kukic, an Anthropic-affiliated account, posted an enthusiastic one-line message saying Go plus Opus 5.5 means "shipping." The post gives no details on features, benchmarks, or specific use cases.

AILewis Tunstall reports that when Claude and Codex review each other's PRs, Claude's reviews are packed with blockers and nitpicks, while Codex usually approves with LGTM. He suggests this could mean Opus 5.5 is the strongest coder right now, or that GPT 6.1 Sol is simply more lenient.

AIDex Horthy argues there will always be an advantage in reviewing AI output, since unreviewed work tends toward generic "AI slop." He adds that the reviewed object may not always be code, and speculates that once models far surpass humans, human interference could make results worse.

AICursor's SDK now supports steering and system prompts for local TypeScript agents. Background subagent results are returned locally in TypeScript and Python.

AICursor is enabling an option to replace its built-in system prompt with a custom one, while rules, skills, and tool schemas still load. The feature is being rolled out account by account rather than to all users at once.

AIBackground subagents now return their results to the parent as a follow-up turn on the same run. The stream() and wait() calls carry through until every subagent finishes.

AITogether AI has announced Together Link, which lets developers run frontier open models inside their favorite coding harness. The product includes spending tracking and an Auto router that selects low-cost models for quick fixes and more capable models for harder tasks.

AIGitHub has released ReviewBench, an open benchmark for evaluating AI code review agents on 219 public pull requests across 19 languages. The benchmark reports grounded and augmented precision, recall, and F1 metrics, and its dataset, rubric, and judge are publicly available. GitHub says ReviewBench predicted the direction of a Copilot code review ensemble experiment's production results before A/B testing.

Why it matters: The post explains how ReviewBench was built and validated, and reports an offline-to-production comparison that shows how well a benchmark predicts real experiment outcomes.

AIFireworks AI has made DeepSeek V4.1 Flash available for training on its Dedicated Training API and Managed Training surfaces. The post positions the model as a strong base for agentic coding, terminal automation, and tool use, and notes it is cost-efficient to serve.

AIReplit shipped a weekly update letting users build with GPT-6.1 Sol and Claude Sonnet 5.5, along with an Ask agent integration with Jev. The release also includes an updated Settings UI and enterprise Workplace controls for company-wide rules and controlled exceptions. Full details are in the Replit changelog.

AIHugging Face says a capture proxy lets reinforcement learning train open models inside unmodified coding harnesses such as Claude Code, Codex, and OpenCode. The proxy records the exact token IDs and logprobs vLLM samples and hands them to TRL for training. On LFM2.5-2.6B, training in four harnesses at once raised OpenCode results from 34% to 58%, while SFT on 3,189 Qwen3.8-27B rollouts plateaued at 47.5%.

AIGuillermo Rauch introduced gdp-ts, a library, linter, and AI skill that uses "proofs" to enforce that sensitive functions are called only after an authorization check. The TypeScript typechecker verifies these proofs at compile time, aiming to stop security bugs from shipping, including those written by AI agents. The README models a Vercel API constraint requiring a role and entitlement proof to change a Project's password.

AICloudflare announced 46 products and updates during Birthday Week 2026, including the cf CLI for the entire Cloudflare API and EmDash, an open-source Astro-based serverless CMS whose plugins run in isolated Worker sandboxes. The company also said it plans to become a public certificate authority that issues free Merkle Tree Certificates for post-quantum authentication.

AIThe /break-ui Skill, added to the Skills For Designers and Engineers repo with 43K stars and 1.9M installs, plays the most annoying real user to stress UI components with worst-case but realistic data. It targets bugs manual testing misses, such as "1 members" pluralization errors, zero-value "0 seconds ago" rendering, cross-timezone date shifts, and emoji or CJK names breaking initials logic. The skill reports issues before fixing them, and only changes the data, never the component.

AITogether Link connects coding agents such as Claude Code, Codex, OpenCode, and Pi to open models on Together AI, which the company says cuts spend by over 50%. Setup takes one command, and its "Auto" mode routes each session's first task to a fast low-cost model or a frontier model, with a per-session tracker comparing costs against Opus 5.5.

AIOpenAI researchers' daily coding-agent usage, valued at API prices, rose from under $1 in January 2026 to $601 for the median researcher by mid-August. The 90th-percentile researcher reached over $7,000 per day, and both groups show doubling times of roughly one month. Epoch notes these are API-list values, not OpenAI's internal costs.

Why it matters: The figures show internal coding-agent usage growing fast enough to matter for research cost, though they measure API-list value rather than OpenAI's actual spending.

AIBoris Power, who is linked to OpenAI, posted "Time to 🚢 🚢 🚢!" to signal an imminent round of shipments. Quoted background from @thsottiaux says that over the next 28 days the team will ship one clear improvement relevant to most Codex and work users each day, or a full reset.

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 poster calls GPT-6.1-Sol their go-to model for both work and personal use, saying it is "all you need." Citing Arena's real-usage cost-per-task data, they claim users should get about 5x more usage from GPT-6.1-Sol than from Astra.

AIThe author tracked token usage over three days and estimated that a $200 Claude plan delivers about $3,400 of API-equivalent value per week, versus about $1,700 for a $200 Codex plan. With cache hit rates of 98.94% for Claude Code and 98.34% for Codex, the author says GPT-6 Astra costs roughly five times more than Claude Opus 5.5, making the Claude weekly quota last about ten times longer.

AIThe author spent over half an hour using Claude to produce a company logo animation that is now roughly usable. The post reflects surprise that motion graphics and video work can now be generated directly through code by AI.

AILangChain says its coding agent costs fell significantly for a second straight month after adopting three steps. The steps are cost visibility through LangSmith tracing, per-user cost caps via its LLM gateway, and harness optimization such as model routing in its open-source OpenSWE cloud agent harness.

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.

AIA post from Anthropic's Ado Kukic says Opus 5.5 at medium and high effort has never hit the 5-hour limit, with the closest single session reaching about 74%. He says this has significantly changed his workflows and asks others about their experience.

AIYuchen Jin says AI coding was at its peak earlier this year, reflecting a shift in his own tool use. He has stopped using Claude Code and Codex CLI, arguing the terminal is the wrong interface for coding agents.

AIThe GitHub Copilot app places the diff, terminal, and browser in one view so users can review agent code without switching tabs. It lets them check, run, and preview changes side by side. The post links to a GitHub blog guide for beginners.

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.