#Agent

AIThe article argues that improving an AI setup can sometimes mean giving the AI fewer rules to follow, based on the author's experience across a million words of failed drafts. The source text provided is mostly paywall and subscription material, so no further specific figures, products, or benchmarks can be verified.

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.

AIPromptArmor reports that a malicious Skill can make Databricks Genie Code display a phishing modal and exfiltrate tenant data without human approval. The attack exploits Skills loaded from users' personal workspaces and a display interface that lacks egress controls, and Databricks, after disclosure on August 16, 2026, said users are responsible for ensuring uploaded Skills contain no malicious content.

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 says GPT-6 can work autonomously on 3D design for hours while its results keep improving, a gap other models failed to match because they could not recover from mistakes. Design Arena reports GPT-6 Astra took #1 on four leaderboards, including 3D Design at 1484 and Frontend at 1397, a month after release.

AIfx.sh has become much faster, with the v0.0.13 release reporting launches up to 23× faster, shell calls up to 8.6× faster, and exits up to 44× faster. Guillermo Rauch says that as models like Astra ultrafast speed up, harness overhead matters more, and the next release will improve session storage and retrieval.

AIEmpero announces Homebrew, an open agent that builds AI models for users. According to the post, users describe what they want, and the agent picks a base model, prepares data, sets parameters, and runs training. The project is available on GitHub at empero-org/homebrew-ai.

AIThe Hermes plugins catalog has grown to nearly 500 mods that add capabilities, model providers, memory enhancements, and visual components. The full list is available in the Hermes documentation at

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.

AITeknium, a researcher associated with the Hermes model family, posted only two eye emojis with no explanation of the main post's content. The post appears to be a teaser linked to a quoted post from @alexhvnsen describing a Hermes "Alan's way" companion app with Telegram-based control, a macOS and VM hybrid setup, and a proactive lead bot.

AIPerplexity's Computer can build custom vertical AI apps, such as one that guesses an image's location using 3D and satellite views. The example app was built with the Perplexity SDK for web search, local place lookups, and visual clue extraction, and it uses Cesium for the 3D globe and satellite imagery.

AIThe Sequence's Issue 944 recaps a week of AI news, including OpenAI's Dots persistent agents and GPT-6.1 Sol, Google's Gemini 4 Argon, and Meta's Meta Enterprise Platform. It also covers AMD's roughly $8.2 billion all-stock deal for World Labs and Instinct's $1 billion Series C at a $10 billion valuation. The editorial argues that delegation to AI agents is the common theme across these announcements.

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.

AIOpenAI wants ChatGPT to become an operating system for work, and Dan Shipper sorted its 22 DevDay 2026 releases by how much each advances that goal. The five most important include Dots, an always-on agent, and Space, native documents the agent can edit, which form the workspace itself. After a week of use, Shipper concluded the ambition is big but the execution is not there yet, and even power users have a lot to figure out.

AIMicrosoft and Hugging Face released ThinkingBox, a benchmark that grades AI agents on the terminal backend state and side effects they leave behind rather than their final responses. Each of 507 stateful business tasks runs 20 times from a clean backend, and the post reports pass@1, pass@20, and observed 20/20 counts, plus cost per successful and per dependable task across 18 models. The harness and dataset are available on Hugging Face, with the OpenEnv interface for running evaluations.

Why it matters: The post shows why checking the database state, not tool calls or final replies, exposes agent failures, and gives a repeat-run method for judging reliability.

AIReplit CEO Amjad Masad argues that general models could train smaller, domain-specific successors on the fly when they detect a limited use case. He compares this to a just-in-time compiler that emits optimized code during execution. He says such specialized models could be cheaper, less vulnerable to prompt injection, and less harmful than general agents.

AIHarrison Chase, LangChain's leader, says his team is debating whether to build specialized agents or one mega agent. The post gives no conclusion or supporting detail.

AIPerplexity's Computer can now generate inline visualizations when users ask it to "Visualize" a topic, producing interactive widgets and animations within the thread. The feature is best used on Standard or High effort, and an example given is an inline 3D cutaway of a jet engine.

AIAmjad Masad of Replit and Alex Atallah of OpenRouter discuss why AI independence and model diversification matter for enterprises. They argue that depending on a single lab risks lock-in and that specialized agents may outperform one general superagent. The post presents the conversation as a podcast episode, the first Atallah has done since Stripe acquired OpenRouter.

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.

AIA consultant helping several companies adopt AI in engineering workflows says teams become much more productive and ship better software faster once they ramp up. The shift he recommends is from prioritizing human-maintainable code to building strong processes that validate what agents do, and he rejects the view that such software will later prove worthless.

AICMU researchers released SMDD-Bench, a benchmark of 502 small-molecule drug design tasks that use RDKit, ADMET-AI, and Boltz-2 as feedback loops. The authors argue that long-horizon planning, exploration, and learning from imperfect feedback remain open problems beyond math and coding, and the benchmark is available in Prime Intellect's Environments Hub for training with prime-rl.

AIPrime Intellect has launched Prime Inference, serving GLM-5.3 with vLLM at scale for agent workloads. The vLLM project credits the team's work on prefill/decode topology, scheduler bubbles, and reliable tool calls.

AIIndependent analyst Mostly Borrowed Ideas said he sold his Airbnb stake and added to Meta after testing Meta's Muse AI agent for about 10 days. He said Muse browsed Airbnb like a human, then found a farmhouse stay about 60% cheaper by booking directly with the host, suggesting AI agents could bypass booking platforms. He acknowledged Muse is slow, with a five-hotel price comparison taking 14 minutes.

AIPrime Intellect says long-context agent serving depends on retaining history, scheduling new work, and moving cached state efficiently. It optimized three paths separately: prefill topology and scheduling, compressed KV with a fused attention kernel, and a transfer-friendly cache layout.

AIMuse has released Muse Gadgets, an open-source ESP32 firmware and Linux SDK for building hardware devices that work with Muse. Developers can obtain an API token from gadgets.muse.ai and use a coding agent with the GitHub repo to build peripherals. Guillermo Rauch praised the team's rapid shipping.

AIBaseten tested the MetaInfer skills-only approach by having Claude Code build an inference engine, VibeQwen, for Qwen-3.6-35B-A3B in NVFP4 on a single B200. On single-stream text, VibeQwen decoded 90% faster than a tuned vLLM 0.25.1 deployment (1,792 vs. 943 TPS) and cut time to first token from 28 ms to 12 ms, with a 71% throughput gain at concurrency 32. The author notes this was an outcome-focused run that allowed some numerically different outputs as long as accuracy stayed at or above the BF16 baseline.

Why it matters: The post tests a skills-only inference engine method on a real model and states the speed and accuracy constraints used, helping readers judge how far such automated optimization can be trusted.