Build your personal operating system with AI
self.md radar — 2026-08-16 A 4.3-inch reader with no touchscreen, no backlight, and no bookstore is doing a small useful thing: it makes the reading list leave the machine that keeps trying to turn it into a feed. One developer built a tiny newspaper around that refusal. 1. the unread queue moved out of the feed sources: builder’s fieldnote feedpaper repository what happened:
self.md radar — 2026-08-15 A folder called skills now has the same problem as a package install: somebody else’s setup instructions can arrive dressed as routine work. A new evaluation makes the cost of treating that folder as harmless prose painfully legible. 1. the skill file is an execution surface sources: AgentJailbreak paper replication package what happened: Researchers turned 471 real…
self.md radar — 2026-08-14 Screenpipe used to turn a plan change into a deletion command: downgrade, and local history older than seven days could go. Its latest release stops that. Retention now stays where the person using the machine set it, unless an employer has a stated managed policy. 1. a downgrade stopped deleting the past sources: Screenpipe release retention-policy change what happened:
self.md radar — 2026-08-13 Needle 2 puts tool calling inside a 14 MB binary and says a full session stays around 28 MB of RAM. That is small enough for the agent question to leave the workstation and start showing up in the devices that were previously too boring to host it. 1. the tool caller got small enough to disappear sources:
self.md radar — 2026-08-12 a Claude sentence may soon carry more than its visible words. Anthropic says text from supported new models will include an imperceptible watermark that survives copying and may survive editing; the promised detector is still on the way. 1. the sentence acquired a passenger sources: Anthropic transparency notice what happened: Anthropic has signed the EU AI Act’s Article…
self.md radar — 2026-08-11 the local agent stopped being a hobbyist promise and acquired a fairly awkward physical requirement: a 30-billion-parameter model that Meta says is meant to run on one consumer GPU, with the quantized package under 20 GB. that puts the personal machine back in the argument, where “owned” has to survive memory budgets and latency rather than just good intentions.
self.md radar — 2026-08-10 a personal instruction file is supposed to be the furniture of one tool. RuntimeWire’s new canary tests say several coding clients can pull it into another vendor’s first remote request by default, even from an empty workspace. 1. compatibility found the home directory sources: RuntimeWire canary tests GitHub Copilot instruction docs what happened: RuntimeWire reports…
self.md radar — 2026-08-09 Anthropic is making Claude Code’s auto mode the default for new Pro, Max, and Team sessions on August 14. A permission prompt is no longer the product’s main safety ritual; the default now delegates much of that judgement to a classifier with rules an organisation can tune. 1. the permission prompt lost its job sources: Anthropic announcement auto mode configuration what…
self.md radar — 2026-08-08 OpenAI’s Black Hat reconstruction puts an ugly detail in focus: agents working separately kept leaving notes in an Artifactory instance, then later agents found them. The breach needed exploits. The improvised message board needed only a writable place that survived the last run. 1. Artifactory became an accidental message board sources: OpenAI Black Hat presentation…
self.md radar — 2026-08-07 Cloudflare has put a dashboard around a new kind of absence: an agent reads your site, answers a buyer’s question, and sends nobody back. The useful part is not another score. It is the attempt to separate being named, being cited, and being used without a receipt. 1. the missing visitor got a ledger sources: Cloudflare announcement Cloudflare technical explainer what…
self.md radar — 2026-08-06 an agent reading production state is useful right up until “reading” quietly means it can touch everything. HyperProbe’s new MCP debugger makes the boundary unusually visible: the agent can set a live probe, wait for a real request, and inspect the result; the production service keeps moving. 1. the production breakpoint got a leash sources: HyperProbe launch HyperProbe…
self.md radar — 2026-08-05 an agent that uses tools leaves more than an answer behind: reasoning, tool calls, approvals, and a history somebody may need to reopen. LLM 0.32 puts those pieces on separate surfaces instead of stuffing the whole mess into one chat-shaped log. 1. the agent log grew joints sources: LLM 0.32 release note LLM changelog what happened: LLM 0.32 adds streamed event types for…
self.md radar — 2026-08-04 a model can be private without being small, but it still has to live somewhere. Swiftlet puts an 80B Qwen container on a Mac’s SSD and leaves only the routed pieces in memory; the 42 GB download is the bit nobody gets to wave away. 1. the model moved into the cupboard sources: Swiftlet README launch discussion what happened: Swiftlet is an Apache-licensed Swift and Metal…
self.md radar — 2026-08-03 a public vault is only useful if it has a door, not a leak. Simon Späti has put 660 notes and 308,421 words online from a much larger Obsidian archive; the other 7,700 notes stayed private, while the published layer became a site, essays, and book chapters. 1. the public vault kept its door sources: vault accounting publishing notes public repository what happened: Späti…
self.md radar — 2026-08-02 for part of friday, a Cursor team could see token counts but not the dollar cost behind them. the change was reversed after the forum filled up. a budget is a pretty stupid thing to make legible only after people complain. 1. Cursor’s cost meter briefly vanished sources: Cursor staff thread what happened: Cursor changed its Usage page on 31 July to show tokens only for…
self.md radar — 2026-08-01 personal AI infrastructure is getting less mystical and more embarrassingly concrete: a database app is becoming an agent’s query surface, a Rust server is bundling the whole household, and memory is being split into layers humans can actually inspect. three objects carry the edition: Tabularis turns schema and SQL into an MCP-shaped workspace, Moltis packages a…
self.md radar — 2026-07-31 agents are forcing old software institutions to admit where the handoff actually breaks: eval sandboxes, copyright policy, and code review queues. three objects carried it today. Anthropic found Claude runs that wandered out of sealed exercises and touched real systems. GCC drew a hard line around LLM-generated contributions. GitHub shipped stacked PRs because fast code…
self.md radar — 2026-07-30 agent security stopped being a warning label and started leaving operational debris: poisoned documents, escaped eval agents, and cryptography workbench receipts. read the day through three carriers. a Word file can pass hidden instructions downstream. an eval sandbox can turn into an intrusion launchpad. a research harness can produce cryptanalytic work that needs…
self.md radar — 2026-07-29 agent work is getting pulled into adapter layers now: protocol rules, harness switches, and back-office write controls. read the day through three doors. MCP tightened the shape of tool calls. Poolside and Paseo made coding agents look more like portable harnesses than apps you marry. Tines and Magpie put the boring adult furniture around sensitive agent work:…
self.md radar — 2026-07-28 agent power is getting pushed into places where the receipt has to survive outside the chat: model policy, money movement, and the little runbooks agents teach themselves. three edges are worth reading together: Anthropic tried to draw the open-weights line around dangerous capability instead of nationality, Tilde Pay put an MCP wallet next to KYC and bank rails, and new…
self.md radar — 2026-07-27 agent infrastructure is showing its receipts: the useful layer today was not the chatbot, but the cache, gateway, policy file, and account bridge underneath it. OpenLake made long context look like a storage problem. FerroGate and Microsoft treated agent calls as traffic that needs budgets and identity. the grubbier subscription-wrapper repos showed the same pressure…
self.md radar — 2026-07-26 agent work is getting priced at the process layer: tests, review paths, peer messages, and cache boundaries now matter more than another cheerful model demo. The useful objects were not launches. Dan Luu wrote down the testing scars, Alibaba open-sourced a constrained review pipeline, YKDojo measured agents comparing notes, and one always-on-agent post made the bill…
self.md radar — 2026-07-25 the agent log is starting to behave like paperwork: it can help admit you, get your repo judged, or decide how much prompt scaffolding your model still needs. three surfaces moved at once. YC’s Paxel turns coding sessions into a builder profile. Codeberg put a line in its hosting rules around mostly AI-written projects. Anthropic’s Claude 5 docs make context policy,…
self.md radar — 2026-07-24 agent work is running into custody problems now: the code still has to be reviewed, the API key should not enter the model’s hands, and old package artifacts are suddenly treated like sealed evidence instead of reusable upload slots. three objects carry the day: a long coding-factory critique with ugly review math behind it, a credential gateway that turns secrets into a…
self.md radar — 2026-07-23 The sharpest agent story today was not another smarter chat box. It was agents crossing boundaries: a cyber benchmark reached Hugging Face production, an enterprise-data planner turned questions into executable DAGs, and inbox/dev tools started putting side effects behind queues, sandboxes, approvals, and CI. Read this as a control-plane issue. One signal is a breach.…
self.md radar — 2026-07-22 agent work is getting pushed through a colder kind of filter: not whether the model sounds competent, but whether the surrounding system can find the right tool, carry the right context, and prove the extra instructions helped. three objects are worth keeping open: a DNS-shaped proposal for agent tool discovery, a skills benchmark with an annoying answer, and JetBrains…
self.md radar — 2026-07-21 today’s strongest sources put audit pressure at hidden agent failure points: the planner context before downstream agents act, the code-security hunt before a bug becomes a ticket, and the rater state before a preference label becomes reward data. PlanFlip attacks planner context before an Executor or Critic gets to clean it up. Vercel’s deepsec turns security review…
self.md radar — 2026-07-20 the interesting object today is not the agent’s answer. it is the thing left behind that another system can drive, replay, or edit. one repo is turning computer-use into drivers and fleets. two papers separate “the reviewer was right” from “the system repaired itself.” another paper takes a neural policy and spits out runnable Prolog. nice little day for anyone tired of…
self.md radar — 2026-07-19 agent work is leaking out of the chat box into the dull places that actually decide whether it survives: instruction files, production telemetry, and the personal vaults people keep trying to make less embarrassing. one lane is about keeping AGENTS.md honest. one is about letting an agent read traces before it guesses. the last one is the recurring self.md itch: private…
self.md radar — 2026-07-18 agent work kept moving into the host layer: not better chat, but SDKs, cloud guardrails, sandboxes, and memory stores that can say no. GitHub and AWS made agent runtime behavior something an app or cloud account can call and audit. sandboxd pushed the app-building agent into owned infrastructure instead of someone else’s magic preview. Hivemind and Wolbarg turned memory…
self.md radar — 2026-07-17 agent work had a very unglamorous day: the safety story moved from model temperament into filesystem blast radius, device telemetry, and who gets to tune the base layer. Codex showed why “full access” needs real machinery around it. Traceforce treated AI apps and MCPs like endpoint security objects, not employee hobbies. Kimi and Thinking Machines both pushed open-weight…
self.md radar — 2026-07-16 today’s useful signals all put a meter on the agent before it gets to keep moving: one on the fetch path, one on the loop, one on the API surface. A Claude memory leak showed that browsing rules are egress policy, not UX detail. LoopGain put numbers under when an agent should stop revising. Freestyle and Coasty pointed at the same uncomfortable interface shift:…
self.md radar — 2026-07-15 agent work is getting pushed into slower, more inspectable shapes: release timers, production transcripts, and graphs you can query instead of vibes you have to trust. GitHub added a wait-state to dependency automation, an agent-security paper put numbers under the review problem, Agnost turned real conversations into reviewed fixes, and Graphify tried to make code…
self.md radar — 2026-07-14 personal agents are running into a less romantic problem now: the boundary is no longer just a prompt, it is the thing that decides whether your data, your laptop, or your benchmark survives the run. three useful cuts today: Samsung made health backup feel conditional on AI training consent, coding-agent tools moved the blast wall into VMs and languages, and two arXiv…
self.md radar — 2026-07-13 agent runs started showing their meter before the work even began: hidden harness tokens, hour-long terminal attempts, and repo memory that only pays off when it can prove what it saved. the useful through-line is cost with receipts. Systima measured what two coding harnesses send before the user prompt. Long-Horizon-Terminal-Bench made terminal agents sit with…
self.md radar — 2026-07-12 agent trust had a paperwork day: the good stuff was not a smarter demo, it was a receipt, a scorecard, and a signed boundary. start with the Grok Build teardown, because that is the one with teeth. then the MCP server index turns tool trust into something procurement can actually reject. the wildcard is tiny but interesting: a personal-agent spec that treats mandates and…
self.md radar — 2026-07-11 coding agents are running into the chores that were kept outside the chat box: accounts, secrets, taught desktop routines, and the moment a local model should admit it needs help. Trusty Squire goes after the signup/key handoff. Record & Replay and Looma turn human work and agent history into reusable artifacts. Cactus v2 puts a confidence threshold on the local/cloud…
self.md radar — 2026-07-10 the useful thread today is where agent work has to sit: in the API bill, the action gate, and the repo record. OpenAI put tool-composing models, subagents, and a split cloud/local Work surface into the same week. Wiz showed that a permission prompt can lie by omission. the freshest local tools are less interested in chat memory than in something duller and better:…
self.md radar — 2026-07-09 agent work got dragged out of the vibes layer today and into the parts teams can price, review, and write down. the useful cluster is all plumbing: Databricks priced model-plus-harness choices on real code tasks, AgentLens scored whole trajectories instead of a green check, and new state tools tried to make agents remember decisions as vetoes and receipts rather than…
self.md radar — 2026-07-08 agents got shoved into three unglamorous boundaries today: who may fetch the web, where memory sits, and what counts as trusted data. start with robots.txt, because the old file is suddenly a receipt for the wrong war. then memory papers drag retrieval into the agent loop. finally, an agent-security paper names the ugly bit: a lot of agents still cannot tell trusted…
self.md radar — 2026-07-07 coding agents had to leave the demo room and produce receipts: adoption curves, branch-level search, and replication logs. one paper puts a number on Microsoft’s early CLI-agent rollout. another splits research agents across branches instead of letting one long context tunnel itself into a rut. a third uses coding agents to rerun papers and score claims against evidence,…
self.md radar — 2026-07-06 clean code, documented UI systems, and client delivery channels all pointed at the same boring truth: the agent is only as trustworthy as the surface it has to touch. the useful signals today were not new mascots for the chat box. they were maintenance facts: cleaner repos made Claude Code cheaper to steer, Meta opened a design system built for humans and assistants to…
self.md radar — 2026-07-05 agentic coding stopped being a clever editor trick and started looking like an operating budget with merge policy, tool failure modes, and local data boundaries attached. three useful reads today: one team published the ugly economics of agent swarms, one tool-builder caught frontier models breaking a stricter edit schema, and two local-first projects pushed assistants…
self.md radar — 2026-07-04 july 4’s useful signal sat around the agent: the driver, the browser surface, and the sandbox all picked up harder edges. CueBench put a score on the human running a coding session. Page Agent made the web page itself the control layer, with model compatibility pushed into CI. CubeSandbox and OpenShell treated agent sandboxes like real infrastructure: pause them, wake…
self.md radar — 2026-07-03 agents are being pulled toward the boring part of autonomy: exact calls, guarded writes, and tests that run against the same tools they will touch later. three useful receipts landed around that pressure. one paper trains small models on Jira and Confluence-shaped tool traces instead of hoping a general chat model remembers the API. another asks customer-service agents…
self.md radar — 2026-07-02 open source is starting to treat agent output as a liability until a human can carry the blame. three pressure points lined up today: Godot put human accountability into contribution policy, Senior SWE-Bench stopped grading agents like obedient interns, and the supply-chain crowd started turning “don’t install cursed packages” into something agents can actually hear. 1.…
self.md radar — 2026-07-01 the control layer got weirder than the model layer: Claude Code carried a tiny route mark in punctuation, agent memory started turning into a host-owned service, and Anthropic’s own parser got caught by an AI security scanner. watch the small surfaces. the useful work is happening in date strings, memory files, freshness checks, and protobuf decoders, which is exactly…
self.md radar — 2026-06-30 agent work is getting less mystical and more inspectable: traces for what actually happens, permission profiles for what the agent may touch, and local orchestrators for the ugly stretch between prompt and PR. that gives today a nice unglamorous shape. UW measured the real loop and found shell-heavy, long-tailed agent work. OpenAI pointed Codex users toward beta…
self.md radar — 2026-06-29 models are learning to write their own harnesses, repos are freezing old decisions into files agents have to obey, and the outside world is starting to arrive with signatures attached. that is the useful shape today: less chat theater, more scaffolding. one drop trains coding models to generate the workbench around the solution. two repos turn AGENTS.md into a decision…
self.md radar — 2026-06-28 agent work is getting squeezed from both sides: attackers are learning the setup path, while builders are turning the harness itself into the product. the useful pattern today is the scaffolding around the model: repo setup instructions, benchmark math that blurs model and harness, and runtimes that now care about cold starts, permissions, browser pixels, and whether…