#Agent

AIMatt Pocock's /wayfinder skill is designed for "fog of war" situations where the end state of a project is unclear. It orchestrates research and other grill sessions to help users discover what they don't yet know, building on his popular /grill-me skill. Latent Space is featuring the skill in an exclusive interview as the first in a series of Skills coverage.

AIDean Ball, writing in his first OpenAI-hosted post on the new AI Futures blog, argues that concentration of power is the largest long-run AI risk. He says states could project force and collect revenue without the human labor and cooperation that have historically constrained them.

AIMistral has released Agentic Search, a multi-step retrieval layer available through its Search Toolkit and Libraries. On FinanceBench, the company reports accuracy rising from 26.7% to 86% over one-shot RAG, and on OfficeQA Pro a gain from 6.3% to 51.9%. The system also reports up to 39.6% lower p90 latency and up to one-third lower token use from fewer repeated searches.

AIThe 甲子光年 "激流——2026甲子引力X科技产业投资大会" held in Beijing on August 20 released an AI trend report from its founder and CEO Zhang Yijia. Her report says H1 2026 showed investment amounts rising 91.6% year on year, with AI capturing over 70% of global venture funding.

AIZhang Yijia, founder and CEO of Chinese tech think tank 甲子光年, presented a 2026 AI trend report at a Beijing investment conference, arguing China's venture capital has entered a new cycle as financing, investment, and exits rebounded in H1 2026. He said AI absorbed over 70% of global venture investment in H1 2026, with OpenAI and Anthropic together raising $217 billion, and that global AI-related capex is expected to exceed $1 trillion in 2026.

AIAdd @𝚟𝚎𝚛𝚌𝚎𝚕 to any thread ▪︎ Create plans and PRs ▪︎ Roll back deploys and update configs

AIAir's latest release lets users open several projects in one window and run agents across them in parallel, with tasks grouped by project in the sidebar. Markdown files now render as formatted text while editing, with syntax shown only when editing, and Chinese, Japanese, Korean, and other IMEs now work on Windows. The release also adds a Customize screen for keymap, theme, and accent color, and lets users choose the agent and model for Agent Review.

AI…Update financial models in spreadsheet - Process and generate reports in batch Stay tuned for more Kimi Work workflows!

AICursor's update lets cloud agents subscribe to PRs, Slack threads, and scheduled tasks, and wake when something happens. It also adds custom modes that pin a skill in chat, subagents that run on their own virtual machines, and a /goal command for long-lived objectives. Users can also send steering messages while an agent works, with follow-ups applied at the next tool call.

Why it matters: The release lists concrete agent controls such as event subscriptions, custom modes, subagent VMs, and /goal, showing how cloud agents may run longer tasks with less manual steering.

AISee how Gemini 3.7 Flash, combined with Nano Banana and Omni, builds interactive websites in one shot. Under the hood, 3.7 Flash calls the right tools to generate the copy, image references, and render parallax-ready Omni videos.

AI…Available via the official API and partner model gateways Get started:

AIGoogle Labs has opened a waitlist for CC, its experimental AI productivity agent in Gmail, in Australia and New Zealand, and is expanding availability in the US and Canada. CC now helps manage calendars by connecting to Gmail and automatically creating events in a dedicated Google Calendar that update as plans change. Invitations to waitlisted users in the US and Canada begin rolling out today.

AICheck out the video and congrats to the winning teams from Stanford, UMass Amherst and Yale! Blog on winning ideas:

AI1,000,000 hacker challenge for Vercel Sandbox: • Escape the Firecracker microVM • Defeat the host-side network boundary • Up to $50k/report via @Hacker0x01

AIZ.ai's release notes announce GLM-5.3, which the company says delivers a 50% gain over GLM-5.2 on Z.ai Code Bench and reaches open-source SOTA on public benchmarks including Terminal Bench 3.0. The company also reports that GLM-5.3 matches Mythos 5 in white-box code review and vulnerability discovery, identifying 2,436 vulnerabilities in real-world targets, 1,097 of them medium- or high-severity. A separate GLM-5.3-Flash entry describes native visual capabilities and a hybrid architecture with 320B total and 18B activated parameters.

Why it matters: The release notes show GLM-5.3's coding and cybersecurity gains, with a vulnerability count, letting readers compare it against Z.ai's prior GLM-5.x line and other coding models.

AIi'm sick of telling my agent orchestrator things like: "for Claude, use model X, for OpenAI, use model Y, etc." i want to be able to tell my orchestrator: "use models tier ..." for this kind of task

AIMicrosoft Foundry now offers structured outputs, web search, web fetch, MCP connector, and tool search for Claude models on Azure-hosted deployments. Prompts and completions remain within Azure for these deployments, while only usage metadata and safety-flagged content egress to Anthropic. The features were previously available only on Hosted on Anthropic deployments, which required choosing between capability and data-handling commitments.

Why it matters: The post shows which agent scaffolding now runs on Azure-hosted Claude deployments, which matters for teams needing data residency without rebuilding search, fetch, or tool routing.

AIJason Wei now believes a small 1B-parameter "cognitive core" relying on tools is insufficient, because fast, natural recall without tool use matters. He cites speed, knowledge better learned through backpropagation than retrieved from search, and the greater reliability of already-known facts over repeated lookups. Since a 1B model has an information limit, he argues that demanding AI will still need larger models, not just tool access.

AIGive it a URL or describe where to find the skill. Make sure to only install skills from sources you trust!

AIReplit now offers black-box pen tests that scan deployed apps over the network and browser, with no access to source code. A Level 3 scan runs them alongside the existing white-box code scan, and the source notes the two catch different kinds of flaws.

Why it matters: The post explains how black-box scans test an app like an outside attacker, showing why source-code review alone misses some exposed doors.

AIDiG-bench, a 70-game benchmark for discovering hidden rules through interaction, shows Opus 5 and Fable 5 with Claude Code performing best overall, with GPT-5.5 next. Only Opus 5 and Fable 5 beat any Tier 7 tasks, at a 0.2 success rate, while humans reached 100% on the same tests. The authors say the benchmark's games are mostly kept private to avoid training contamination.

AIYou can force the model to take an action when it thinks for too long by injecting a thought after a specified reasoning budget. Helps dealing with underspecified tasks which make the model reason for way too long.

AIThe author built a Python agent that uses Gemini 3.7 Flash to control an Android emulator from raw screenshots, returning normalized 0–999 coordinates that are scaled to 1080x1920 pixels over ADB. In a test, the agent opened Chrome, closed popups, and solved one round of Wordle in two guesses without accessibility IDs or DOM access. The article presents the loop as usable for UI testing and task automation across native apps, webviews, and canvas interfaces, with code in an open-source quickstart repository.

AIPrime Intellect ran 153 autonomous runs on the nanoGPT optimizer speedrun across 18 frontier models, with runs lasting up to eight days on 8xH200s. The results show a large gap between models at every stage of the research process, though none of the runs produced a fundamentally new method.

Why it matters: The experiment measures how frontier models conduct autonomous research, showing large gaps between models in experiment choice, execution, and result interpretation.

AIAugment rebuilt the Auggie CLI harness as v2, forking the open-source Pi coding harness and moving its context engine into Pi's extension system. On SWE-bench Pro at the same pass rate, Auggie v2 completes a task for $1.27 versus $2.70 for Claude Code, which is 53% cheaper. The gains come mainly from a narrower tool surface, one bash tool plus read, edit, and write, and from codebase retrieval that reduces exploration turns.

Why it matters: The post traces the design trade-offs behind each harness choice and ties them to measured token and cost differences, useful for anyone weighing agent tool surfaces.

AIEpoch AI outlines nine open questions about AI capabilities, including whether AI can take over full jobs and whether benchmark scores are correlated. The author says Epoch's benchmarking work is built to help answer them, citing examples such as MirrorCode, Remote Labor Index, and the Epoch Capabilities Index (ECI). The post notes that benchmark scores are highly correlated across domains, and that ECI growth trends can help detect whether AI capability progress has accelerated.

AIAndrew Ng's team released an AI Engineering Skills Map, built from analysis of over 10,000 job postings and expert interviews, identifying four priority skills. The skills are building and deploying AI applications, software engineering fundamentals, using coding agents, and shaping the build. Ng says these skills matter for all developers, not only those with the AI Engineer title.

AIAli Ghodsi attributes Databricks' 80% growth at $7B to enterprise AI agents becoming usable, now that Genie Ontology automates the capture of organizational context. He says over 70% of queries on the platform are now generated by Genie agents, and that this usage drives consumption and revenue.

AIRead how we built it to make it task-aware and preserve good cache hit rates. With so many frontier models coming out every week, this can really improve both cost and quality.

AIOur data is showing unprompted messages are down ~45% -- Claude Tag is both more context-aware across your work and more attuned on when to keep quiet. Best part - you don't pay for Monitoring either!

AIGoogle has made Gemini 3.7 Flash available in Google Antigravity, described as its most intelligent workhorse model yet for coding and agents. Users can download or upgrade Antigravity to try the model. The author, Varun Mohan, says the model brings a big capability improvement at half the API cost.

AIAugment Code describes an expanded AI-native review system in which specialized agents handle review, repair, and verification from pull request to merge. Humans still make judgment calls and the final merge decision, with the company claiming a 3× increase in code output in its earlier review system.

AIGoogle AI Developers announced Gemini 3.7 Flash as its most intelligent workhorse model yet for coding and agents, citing higher instruction adherence, first-pass code accuracy, and high-quality agentic execution. The post shows the model building a complex 3D web game in Antigravity, covering Three.js engine logic, asset orchestration with PBR textures and Nano Banana sprite sheets, and procedural sound effects.

Why it matters: The post shows a concrete build workflow across engine logic, assets, and audio, which helps readers judge how the model handles multi-step agentic coding.

AIGoogle launches Gemini 3.7 Flash, its latest Flash model for coding and agentic workflows, with an introductory price at half the original cost of 3.6 Flash. The post reports gains from 3.5 to 3.7 Flash, including DeepSWE v1.1 rising from 37.0% to 65.3%, Code Arena Elo from 1506 to 1588, and AutomationBench from 13.4% to 30.4%.

Why it matters: The post pairs a launch with specific before-and-after benchmark gains and an introductory price, letting readers weigh capability against cost for coding and agent work.

AIKoray Kavukcuoglu announced Gemini 3.7 Flash, saying it brings a large jump in agentic performance and coding accuracy. To demonstrate, a three-agent team was set up to autonomously train a robotics control model from scratch. The full introduction is linked on the Google blog.

AIAugment Code's Solutions Architecture lead used the Cosmos agentic orchestration platform to build a live pilot-health view that combines product usage, GitHub and PR activity, Salesforce deal data, and customer call transcripts. Each account's health and board-level one-liner was checked against the customer's own stated success criteria, such as a 30% PR merge-time reduction. The article says the view refreshed from current Salesforce data and was designed to avoid inflating usage numbers through session lineage reconciliation.