01Log
Archive
The full log, newest first.
GPT-6 Luna
Fast, cost-efficient GPT-6 tier for high-volume and latency-sensitive workloads.
RiftX Pentest Tool
RiftX is a local workbench for authorized web security testing that combines agent conversations, controlled local tools, a Playwright browser, multi-agent collaboration, and evidence capture. It aims to reduce manual context switching across terminals, browsers, proxies, and notes.
Netlogon RCE PoC
A proof-of-concept for CVE-2026-41089 Netlogon remote code execution, intended for security research, vulnerability validation, and defensive testing. The README text appears copied from an unrelated AI security tool.
AI Security Tool
Free open-source AI-powered security terminal and vulnerability scanner with CVE/SBOM support, SSH/SFTP/RDP/VNC/serial connections, and 12+ AI agents. It unifies security audit, Red Team, pentest, and CTF workflows in desktop and web interfaces.
Cybersecurity Daily
Automated daily Chinese cybersecurity briefing that aggregates CVE, vulnerability notices, security incidents, and threat intelligence; AI-generated, human-verified, published to GitHub Pages. It selects 5-10 items with analysis and source links.
AITIR Framework
AITIR 2.0 is a vendor-neutral reference architecture for adaptive identity threat intelligence and response, converting identity telemetry into provenance-linked evidence, policy decisions, authorized responses, and reviewable assurance. It separates analytics evidence from enforcement authority.
BugScanner Web Scanner
BugScanner is an advanced web vulnerability scanner with recon, subdomain/port scanning, fingerprinting, endpoint discovery, and checks for XSS, SQLi, CORS, SSRF, open redirects. It includes false-positive reduction, WAF evasion, and HTML reports.
Cyber Resume Reviewer
An agent skill for evidence-led cybersecurity resume reviews, tailoring to job descriptions, exact edits, scoring, and rewrites; produces Markdown report and styled PDF. It does not rank candidates or invent achievements.
Birdview AI Mapper
Birdview is a skill for AI coding agents that maps architecture and constraints into one reviewable view before changes; the agent shows the map and plan, waits for confirmation, then implements and records verification.
Grok Keysmith
Preview-first installer for Grok Build that writes custom instructions only after showing a plan and receiving confirmation, then supports verification and layered uninstall. It does not modify Grok or read account credentials.
DSH TUI Plugin
Interactive terminal UI plugin for DeepSeek Harness with whale header, live status, streaming thinking, double-Esc rewind, context progress bar, and TPS gauge. It is a pure plugin requiring no core changes and installs via npm.
Dashi Taskboard
Local-first issue board that runs in the browser and can be embedded in Codex via a CDP launcher or injection script; one HTTP API powers the React UI and taskctl CLI. It supports Codex and DeepSeek Harness.
Jev Align
Experimental CLI from Sutro for building calibrated AI Functions with TypeSafe's Jev. It finds uncertain examples, asks you to label them, and uses GEPA to improve the function, then lets you share portable functions through ai-functions.dev.
Gooey Pi
Desktop workspace that gives Pi, OMP, and Prime Agent the same cross-platform interface on macOS, Linux, and Windows, while leaving each harness's own models, logins, and saved sessions in charge.
DeepSeek Balance Widget
Bottom-right widget for DeepSeek Harness web UI showing API balance, today's usage, and per-conversation cost with customizable whale bubble content. It installs via dsh plugin without a session token and also has a For-Codex branch.
On-Device AI Agents
Build AI agents that run 100% on-device. Sub-100ms latency on Qualcomm NPU. Zero cloud dependency.
Octatrack DSP Effects
Custom DSP effects for the Elektron Octatrack MKII — original DSP56300 algorithms (ChonVerb reverb, BongDelay) on a cross-core send bus, delivered by patching the stock OS image
SquachWatch CYD Firmware
SquachWatch is a firmware for the Cheap Yellow Display that gamifies detecting things like Flock Cameras, Trackers, Meta Glasses and so much more!
MSPM0 Agent Skill
MSPM0 + SysConfig Agent Skill for Electronics Design Contests
CrumBLE E-Reader Firmware
Xteink X4 e-reader firmware, fork of CrossInk
Echo Show Firmware
Open firmware for the Echo Show 5, 1st and 2nd gen: Alpine Linux instead of Android, no Alexa. A local Home Assistant voice satellite with its own touch screen, on-device wake word, SSH and A/B over-the-air updates.
FlightPortrait Frame Firmware
Firmware, device protocol, and reference BYOS server for the FlightPortrait e-ink frame
Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna, and a new price war
Simon Willison on the day's model drops — Claude Opus 5.5, GPT-6 Sol/Luna, Grok 4.7, MiMo v2.6 — and the price war they're triggering. Worth reading for how the cost curve shifts for agent workloads.
DeepSeek Elastic Compute (DSec)
A paper proposing sandbox infrastructure to scale agentic training.
Codex 0.156.0
Codex 0.156 adds a fullscreen TUI with transcript search, voice by default, a /usage analytics dashboard, and worktree sessions on by default.
Antigravity Google — Windows Subsystem for Linux, Office attachments, and live subagent cards
Antigravity adds Windows Subsystem for Linux support, Office attachments, and live subagent cards.
Claude Opus 5.5
Claude Opus 5.5 launches with 1M context, 128k output, always-on adaptive thinking, and $4/$20 pricing — a direct upgrade for long-running agentic coding.
JetBrains Air: A System of Products for Agentic Software Development
JetBrains Air — a system of products for agentic software development. 66 points, 104 comments on HN; JetBrains is leveraging its IDE moat to enter agentic dev as a product line.
ACLArena: Agent Continue Learning in Multi-stage Post-training
ACLArena — a benchmark for agent continual learning across multi-stage post-training, targeting how agents acquire new capabilities without catastrophic forgetting.
Show HN: JevBench, a reproducible benchmark for typed decision models
Show HN: JevBench — a reproducible benchmark for typed decision models, built to separate serious open-source implementations from lookalikes. 54 points.
Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL
Supervising observations, not just actions, measurably changes how agents explore under RL — a counterintuitive lever for anyone tuning agent reinforcement learning.
Qwen3.8 Max Prime
Higher-throughput SKU of Qwen3.8 Max accepting text, image, and video at a premium price point.
Space Bunny Alpha
Anonymous large model with fast inference, strong coding, and native multimodal input — currently free.
GLM 5.3 Prime
High-throughput variant of GLM-5.3 with 1.5–2× faster output via inference acceleration, same 1M context.
Recognition, Simulation, and Refusal: A Contamination-Aware Study of Classic Psychological Effects in LLM Agents
Contamination-aware study of classic psychological effects in LLM agents — checks whether agents actually exhibit effects or just parrot contaminated benchmarks. Useful for anyone evaluating agent behavior.
Memory That Looks Forward: A Zero-Inference Prospective Term for Personal Memory Retrieval
Proposes a zero-inference prospective term for personal memory retrieval — memory that anticipates future queries without extra inference cost. Relevant to agent memory design.
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
RRSI formalizes regularized recursive self-improvement for agent harnesses — adds a regularization term to keep self-modifying loops from drifting. Directly relevant to anyone running agents that rewrite their own prompts or tools.
onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction
Open-sourced onPanda — token-level correction for on-policy alignment data, aimed at cheaper RLHF/RLVR annotation for LLMs and agents. Useful if you're building agent-specific alignment pipelines.
Gun Protocol
GUN is an open source protocol and ecosystem for syncing decentralized graph data, enabling encrypted, realtime peer-to-peer applications. It is notable as a novel p2p data store with CRDT-based synchronization, used in production by many apps.
Apache Cassandra
Apache Cassandra is an open source transactional distributed database with linear scalability and proven fault-tolerance on commodity hardware or cloud infrastructure. It is notable as a proven distributed wide-column database with exceptional scalability and fault tolerance.