Tag
37 notes collected under this theme.
Archive
Logged at IST: 2026-07-15 13:30 IST What it is: Ayush Paul’s writeup on prompt-injecting Claude’s memory and browsing system into exfiltrating personal data Gist: The attack chain was not about breaking the memory store directly, but about combining long-lived…
Logged at IST: 2026-07-14 11:05 IST What it is: iximiuz warning that VMs and microVMs exposing /dev/kvm to untrusted guests were hit by the Januscape guest-to-host breakout class Gist: The key update is that KVM-based isolation is not a free safety upgrade ove…
Logged at IST: 2026-07-14 08:14 IST What it is: Gergely Orosz calling out reports that Grok CLI uploaded codebases without users knowingly consenting, quoting SpaceXAI’s privacy response Gist: The important issue here is not just data retention policy wording …
Logged at IST: 2026-07-10 22:51 IST What it is: X post by David Crawshaw commenting on expectations of professionalism from OSS authors Gist: Says independent OSS authors do not owe anyone a professionalized posture, and that salaried open-source workers often…
What it is: Drew Breunig revisiting his "10 Lessons for Agentic Coding" list and asking for additions Gist: the piece frames coding agents as making code cheap but not making judgment cheap; strongest lessons are to implement/rebuild to learn, invest in end-to…
What it is: hands-on writeup of deploying Cloudflare’s official agentic-inbox to run a custom-domain email client on Cloudflare Workers Gist: the stack uses Email Routing for inbound mail, Email Service for sending, Durable Objects + SQLite for mailboxes, R2 f…
What it is: Chris Short’s DevOps’ish 316 roundup Gist: strongest signals are ClickHouse gaining observability mindshare, Vint Cerf warning that agents will need more formal coordination than plain English, Podman 6.0 breaking old assumptions, and agent-secret …
What it is: X post praising Thorsten Ball’s Amp note “Putting an Agent in an Orb.” Newsletter angle: the useful shift is from “smart model” to “legible environment”, paved paths, observability, and anti-guessing ergonomics matter as much as model quality. Retr…
Gist: the argument is that domestic robots will create an extraordinarily intimate surveillance layer inside the home, while the underlying article argues humanoid home robots are the wrong form factor, dexterity, cost, weight, and safety push the practical fu…
Gist: claim is that Claude Code inserts hidden/system-prompt markers tied to API base URL and timezone; privacy/trust implications if true. Newsletter angle: “invisible metadata in coding-agent requests” as a prompt-layer trust/safety story. Retrieval note: X …
Gist: on Semgrep’s IDOR benchmark, GLM 5.2 scored 39% F1 in a simple prompt-only PydanticAI harness, beating Claude Code’s 32% while costing roughly $0.17 per vulnerability found; Semgrep’s own endpoint-discovery multimodal harness still led overall at 53–61% …
What it is: Go/security post on building a self-hosted LLM security proxy with sub-2ms prompt inspection Gist: author built an OpenAI-compatible reverse proxy (“Tamga”) that scans prompts for PII, secrets, and prompt-injection patterns before forwarding to pro…
Gist: the safe/scalable model is many fine-grained task-specific agents, each receiving only the exact capabilities implied by the task context (for example, a pasted doc URL grants access only to that doc). He also argues agent authority should derive from a …
What it is: Armin Ronacher post linking to “The Coming Loop” Gist: argues the important new layer in coding agents is the harness-level loop outside the agent itself; loops already work well for bounded, verifiable work like ports, benchmarking, scanning, and …
What it is: Shriram Krishnamurthi memo on rebooting a programming languages course for the agentic coding era. Gist: argues PL should be reframed around constraining AI-generated implementations and providing guarantees; distinguishes PL from SE/FM, then propo…
What it is: Armin Ronacher explaining Pi’s new per-project approval prompt and the security model behind it. Gist: the key argument is that AGENTS.md gets injected into the system prompt, so untrusted repo-level instructions can directly influence agent behavi…
What it is: a blog essay arguing AI disruption is structurally more threatening to software than many other fields because code is verifiable, open source created a huge training corpus, and AI labs can dogfood coding tools on themselves. Gist: the author expe…
What it is: Bilgin Ibryam pointing to Jani Janakiram’s Diagrid essay “Why AI Agents Fail in Production.” Gist: the core claim is that agent projects fail less because models are weak and more because teams ship behavior without the production substrate underne…
What it is: Armin Ronacher pointing to Andrew Tridgell’s defense of using AI tools while maintaining rsync under a flood of security reports. Gist: Tridgell’s main point is not “vibe code and pray” but “use AI for grunt work under strong human design/review/va…
What it is: Mario Zechner recommending Thariq’s article on dynamic workflows in Claude Code. Gist: Mario’s takeaway is that durable dynamic workflows are the interesting part; he inspected the implementation, found a few footguns, but still thinks the design i…
What it is: Sid's writeup on a recently patched Instagram/Meta account takeover flow. Gist: attacker allegedly only needed a target username, region-matching IP, and Meta support AI to redirect recovery codes to attacker-controlled email; video selfie checks w…
What it is: Guillaume Laforge post + MCP release-candidate blog link Gist: MCP 2026-07-28 RC is out; biggest revision so far with stateless HTTP-native core, first-class extensions (Apps, Tasks), stronger auth alignment, and a formal deprecation policy. Final …
What it is: Cloudflare on testing Anthropic Mythos against 50+ internal repos; links to "Project Glasswing: what Mythos showed us". Gist: key claim is that stronger offensive-security models change vuln research from bug spotting to exploit-chain construction …
Imported from historical reading log. Ambitious OSS project pitching WiFi CSI as a privacy-preserving sensing stack: presence detection, breathing/heart-rate monitoring, activity recognition, rough pose estimation, and through-wall/environment sensing using E…
Imported from historical reading log. Andras Bacsai jokes that Coolify created a fake repo with fake bounties so agent/bot-driven fake PR submissions would self-identify and could be banned from the main repo. Useful as a sharp anecdote about the emerging spa…
Imported from historical reading log. Extracted main post via api.fxtwitter.com fallback and checked the linked Auth0 GA announcement. Auth0 is pitching Auth for MCP as the missing identity/authorization layer for production MCP servers: not just connecting a…
Imported from historical reading log. Extracted Alex Albert's post via api.fxtwitter.com fallback and read the attached chart. Claim: with help from Claude Mythos Preview, the Firefox team fixed more security bugs in April 2026 than in the previous 15 months …
Imported from historical reading log. Extracted Simon Willison's post via api.fxtwitter.com fallback and checked the linked note Notes on the xAI/Anthropic data center deal. Simon's main clarification is that Anthropic is getting Colossus 1, while xAI keeps u…
Imported from historical reading log. Extracted main post via api.fxtwitter.com fallback and checked the linked GitHub repo. Mitchell Hashimoto strongly recommends Hunk, saying it has fully replaced other local diff viewers for him. Hunk is positioned as a re…
Imported from historical reading log. Extracted main post via api.fxtwitter.com fallback. Mario Zechner says pi is moving its GitHub repo into the earendil-works org and will start publishing packages under the @earendil-works npm namespace instead of @marioz…
Imported from historical reading log. Readable page copy was sparse, but enough to identify the core program: ChatGPT Futures is an OpenAI initiative highlighting 26 young people/teams from the Class of 2026 using AI to build, research, create, and expand wha…
Imported from historical reading log. Extracted main post via api.fxtwitter.com fallback; inspected attached screenshot separately. Thomas Ptacek argues the .de incident is decisive evidence against DNSSEC as core Internet security functionality. Attached scr…
Imported from historical reading log. GitHub PR title: HTML5+CSS face lift for the generated pages by knadh on mitmproxy/pdoc; merged Nov 20, 2014. Logged as a folklore/historical reference rather than a current article; likely relevant as an old design/imple…
Imported from historical reading log. Extracted main post via api.fxtwitter.com fallback and checked project site for more detail. Terminal Trove highlights nless (nothing-less) by Matt Pryor: a Textual-based TUI for exploring logs/CSV/JSON as terminal tables…
Imported from historical reading log. Extracted main post via api.fxtwitter.com fallback and read linked ChinaTalk piece How to Buy Cheap Claude Tokens in China. Kyle Chan highlights Zilan Qian’s write-up on the transfer station economy around blocked frontie…
Imported from historical reading log. Extracted via api.fxtwitter.com fallback. Armin Ronacher reacting to .de outage: How the hell do you take all of .de offline?, useful signal that ccTLD operational failures were visible well beyond India. Pranesh Prakash:…
Imported from historical reading log. Pimalaya: open-source PIM tools in Rust; positions itself as I/O-free Rust libraries plus house-made applications for the PIM domain. Himalaya: CLI to manage emails; supports IMAP/Maildir/Notmuch, SMTP/Sendmail, keyring, …