💬 Community — 1 item

💬 Show HN: Llmspeed – feel how fast a local LLM runs before you buy the hardware — Show HN tool for gauging local LLM inference speed before buying hardware; 204 points, 66 comments on HN.

📚 Read — 1 item

📚 More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning — Large-scale systematic evaluation of self-distillation in agentic reinforcement learning, framed as a reality check on whether more methods actually produce better agents.

💬 Community — 3 items

💬 OpenCode Hacked: User credentials leaked — 696 points / 120 comments. Top reply says the leak was for 'OpenCode Console', which it says the OpenCode team has done a bad job of clarifying as distinct and separate from the rest of the product.

💬 Anthropic assigned highest junk credit rating in June — 283 points / 86 comments on the FT report; the top reply quotes the article's line that Anthropic's disclosure to KBRA excluded certain details.

💬 Scalzi: vibe-coder traded one 'capitalist yoke' for another with Claude Code — John Scalzi: the vibe-coder 'took aim at a multi-billion dollar company with infamous subscription practices using a tool (Claude Code) provided by a multi-billion dollar company with infamous subscription practices' — 'trading one capitalist yoke for another.' 122 likes / 13 reposts.

⚙️ Ship — 3 items

📦 Kimi K3 now available in Kiro — Moonshot AI's open-weight Kimi K3 is now available with experimental support across the Kiro IDE, CLI, Crew, and Web for Pro, Pro+, Pro Max, and Power customers using Kiro's US geography — accepts text and images.

📦 Kiro — Switch to V3 at Chat Start and Model Fallback Notices — Kiro switches to V3 at chat start and adds model fallback notices — you now get a notice when the harness falls back to a different model.

📦 Codex 0.163.0 — Codex 0.163.0 is out — the new version of OpenAI's coding agent CLI; this release's notes are at the linked changelog entry.

Both Kiro changelog moves touch model selection: chats switch to V3 at chat start, Kimi K3 joins with experimental support, and the new fallback notices flag when a different model gets used.

🚨 Watch — 1 item

🚨 MCP Python SDK: Unbounded Session Accumulation in StreamableHTTP Transport Enables Resource Exhaustion — Unbounded session accumulation in the StreamableHTTP transport enables resource exhaustion against MCP Python SDK servers — CVE-2026-59951, GHSA-84m7-p3x7-pcfv, medium severity. Anyone running that transport should check the advisory for affected and fixed versions.

📚 Read — 1 item

📚 3DCodeVerse: Exploring 3D Worlds as Code — Generates 3D worlds as code only — no image, video, or 3D diffusion models — and ships datasets plus automated verification harnesses for evaluating the output.

⚙️ Ship — 2 items

📦 Amp: See Your Runner's Desktop — You can now see and control your macOS or Linux runner's desktop — useful for trying native apps Amp builds for you, like iOS apps. Turn on Share This Mac's Display under Settings › Runner in the macOS app, or start your runner with amp --no-tui --desktop; the Amp client connects directly to the runner.

📦 OMP 18.12.0 — Breaking: PI_CODEX_ZSTD is replaced by PI_REQUEST_COMPRESSION — set PI_REQUEST_COMPRESSION=0 to send Codex (and every other) request body uncompressed. Also fixes Cursor turns failing with PROVIDER_ERROR when a follow-up arrived while the previous turn was still streaming, and adds ThinkingContent.narration for Anthropic/Bedrock between-tool narration blocks.

💬 Community — 3 items

💬 DeepSeek search and fetch – $0.75 per 1000 successful requests — DeepSeek search and fetch at $0.75 per 1000 successful requests — 443 points and 214 comments on HN, a concrete pricing point for anyone wiring web search into an agent stack.

💬 Codex Desktop continuously generates Crashpad pending dumps — Codex Desktop continuously generates Crashpad pending dumps — 161 points and 80 comments on HN, where operators trace disk pressure from running agents to causes including their git worktree approach.

💬 Trying to get jev to drive Claude Code — Trying to get jev to drive Claude Code — 92 likes / 15 reposts on Bluesky.

Both HN threads are about what agents cost to run: $0.75 per 1000 successful requests for DeepSeek's search and fetch on the API side, and disk pressure from Codex Desktop's Crashpad dumps and agent git worktrees on the local side.

📚 Read — 1 item

📚 GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement Learning — GroundGUI pairs the ScreenRef data with a distillation-to-reinforcement-learning pipeline to train GUI grounding models — the instruction-to-screen-element mapping GUI agents run on.

💬 Community — 3 items

💬 Llama.cpp on a jailbroken PS5: run any GGUF model natively on the console — HN thread at 372 points / 85 comments on running any GGUF model natively on a jailbroken PS5; the top comment argues the project's primary site should not be GitHub.

💬 Designing more efficient quantum circuits with Claude — Anthropic's post drew 172 points / 37 comments on HN; the thread notes it builds on Google's Kickmix, an assembly language for classically simulatable quantum circuits.

💬 cuck coding: 'you just sit in a chair and watch, no touching' — Bluesky meme (70♥ / 15🔁) on the sit-back-and-watch school of coding with agents: 'you just sit in a chair and watch, no touching.'

⚙️ Ship — 2 items

📦 Pi 1.3.0 — Prompt-cache fixes lead: changing the thinking level mid-session on OpenAI GPT-6 (API key) now keeps the cache, and tools added mid-conversation on Kimi Code no longer invalidate it — but models.json base URL overrides must now include /v1. Also new: sessionShareDestination picks the /share upload target (auto, gist, or radius), model switching drops the previous model's thinking instead of showing it to the new model as text, and resumed sessions keep their active tools with --tools +name/-name stacking on top.

📦 Anthropic prepares to release Claude Fable 5.5 next week — Claude Fable 5.5 has reportedly reached Anthropic's partners ahead of a release next week; six early access codenames spotted in Devin CLI, plus one in a GitHub model picker, suggest it may not be the only model on the way.

📚 Read — 2 items

📚 CLASHarness: Benchmarking Multi-Agent Conflict in Computer Use via a Controllable and Verifiable Generation Pipeline — Benchmark paper introducing a controllable, verifiable pipeline for generating multi-agent conflict scenarios in computer-use tasks — the read for anyone orchestrating more than one computer-use agent.

📚 OmniVerifier-C1: Decomposed Graded Verifier for Rule-Governed Generative World Modeling — A graded visual verifier that decomposes complex multimodal rules into pointwise scores and uses decoupled reinforcement learning to improve rule-governed generative world modeling.

Both papers are verification work: CLASHarness generates multi-agent conflict scenarios in computer use via a controllable, verifiable pipeline, while OmniVerifier-C1 decomposes rule-following in generative world models into pointwise graded scores.