|
|
Hi there, this is your daily ☕️ AIpresso.
|
|
|
|
In today's newsletter: 🛠️ Meta open-sources Muse gadget code 🤖 Why AI agents fake task completion 🧠 Google stops AI agents from memorizing tests ✏️ Claude Code lets devs rewrite its behavior 🇩🇪 Aleph Alpha releases open-weight Kolibri Plus: 🎁 6 more stories you might like, 🛠️ 5 engineering & practice picks, 🧰 7 tools, and 📚 5 papers.
|
|
Your agents work while you sleep
Give a Skydive agent an ongoing responsibility and they’ll handle it on schedule, every time.
Have them prep your morning report, research new leads, monitor customer feedback, or keep projects moving overnight. You wake up, the work is already done.
|
🛠️ Meta open-sources Muse gadget code
LINK
|
- Meta released Muse Gadgets on Friday, an open-source project that lets developers build their own hardware connecting to Muse, the personal agent that books travel, fills out forms, and shops on a user's behalf.
- The release includes open-source firmware and a Linux SDK, letting tinkerers wire Muse to a Raspberry Pi or ESP32 board plus displays, buttons, sensors, and actuators, with starter ideas like a color e-ink display or an HDMI TV stick.
- Meta also built Home Link, a USB-C device that connects Muse to home networks and smart devices, making 5,000 units free to subscribers while supplies last, though Nat Friedman said shipping is still a few weeks out.
|
🤖 Why AI agents fake task completion
LINK
|
- Microsoft and Hugging Face released ThinkingBox, an agent benchmark that grades AI agents on the terminal database state and side effects they leave behind rather than their tool calls or final replies, available now on Hugging Face.
- Across 507 stateful business workflows run 20 times each, 67% of failures still terminated cleanly and reported no tool error, yet executable checks found wrong field values in 78% of them, and Claude Opus 5.5 led at 67.16% pass@1.
- Consistency diverges sharply from single-attempt skill: Kimi-K3 solves 93.89% of tasks at least once but passes only 13% on all 20 attempts, while Claude Opus 5 clears 48% every time, so pass@20 is the column deployers should watch.
|
🧠 Google stops AI agents from memorizing tests
LINK
|
- Google Cloud AI Research and university partners found that self-improving AI agents, which repeatedly rewrite their own harness based on test feedback, end up memorizing their limited test tasks, boosting training scores while gains on new tasks shrink or vanish.
- Their fix, called RRSI, caps how many edits an agent can bundle at once and shrinks that budget over time, while a critic rejects proposals that hardcode task names, solutions, or other benchmark-specific tricks.
- For people building agents, RRSI gained up to 4.7 points on unseen benchmarks and used about 30 percent fewer tokens, showing that self-improvement helps only when repeated feedback becomes lasting, general changes rather than memorized answers.
|
✏️ Claude Code lets devs rewrite its behavior
LINK
|
- Anthropic shipped "Mods" for Claude Code, a plugin-based middleware layer that lets developers rewrite how the tool looks and behaves from inside it.
- Mods are JavaScript or TypeScript functions hooking into events like tool calls, user prompts, and UI rendering, so devs can add custom panels beside the chat, intercept tool calls, or define new commands.
- They run across the CLI, desktop app, and partly the VS Code extension, with orgs able to whitelist which Mods load, though Mods run with the user's full permissions and aren't sandboxed, so Anthropic warns to install only from trusted sources.
|
🇩🇪 Aleph Alpha releases open-weight Kolibri
LINK
|
- Aleph Alpha has released Kolibri, an open-weight English-German MoE model under Apache 2.0, downloadable in full from Hugging Face for on-premises deployment in government and regulated industries.
- The model carries 78.1B total parameters but activates just 3.46B per token via a Mixture-of-Experts design, supports up to million-token contexts, and offers four reasoning settings plus tool calling.
- Vendor benchmarks show 96.9 on AIME 2025 and strong coding scores, with Aleph Alpha claiming it matches models with up to 4x the active parameters, though these are self-run results using the company's own harnesses and highest reasoning setting.
|
|
What’s still sitting on your to-do list?
You don’t need an AI team to build an AI agent. With Skydive, the person who knows the work can create the agent to do it.
Start an agent off with a role, teach them how your team operates, connect your tools, and put them to work.
🛠️ Engineering & Practice
|
Other
news & articles you might like
-
Google's new Gemini tiers cut free users to its weakest model and lock $5/month subscribers out of Pro
LINK
-
Open-sourcing AstaBrief, the fast report-generation model in Asta
LINK
-
Volantis raises $88M for a photonic memory layer built for AI inference
LINK
-
MIT's SIFT cuts coding agent eval costs
LINK
-
Is America losing its AI lead to China? The gap is now 3%
LINK
-
NVIDIA DGX Spark 64GB gives developers more ways to build and scale local AI
LINK
|
|
📚 Trending papers & reports
|
> Agent training without do-overs teaches AI agents that act in live systems like security sandboxes by learning only from their best past attempts, matching standard methods that need costly repeated trial runs.
LINK
|
|
> Faster image and video generation automatically picks which saved computation an AI art model can safely reuse to skip costly steps, cutting the work needed while keeping output quality nearly identical to the slower full version.
LINK
|
|
> Smarter data picking shows that matching how you choose training examples to the learning method used makes AI pretraining more efficient, with one popular method staying the best filter even when paired with newer rivals.
LINK
|
|
> Fooling image reading AI shows that attacks can slash a model's internal error signal to near zero yet it still describes pictures correctly, because its language side overrules the corrupted visuals, exposing where sabotage attempts fail.
LINK
|
|
> AI game playtesters let one bot build a browser game while another actually plays it to catch broken interactions, lifting the share of games that work correctly to ~67%, beating standard code generation by ~37 points.
LINK
|
|
|
🧰 Tools & repos
|
CoreSpeed: connects apps once and shares memory and accounts across Claude Code, Codex, Cursor, and other MCP agents through a single endpoint with budgets and activity logs.
LINK
|
|
Invofox Self Serve: a document parsing API that classifies, validates, and extracts structured data from messy real-world documents, scaling reliably in production workflows.
LINK
|
|
devpit: a native desktop app for running Claude Code agents with a visible terminal, card-driven task board, per-call cost tracking, and cross-project orchestration.
LINK
|
|
Oogwai Beacon: queries ChatGPT, Gemini, and Claude with buyer questions to show whether AI engines recommend you, who they name instead, and how to improve.
LINK
|
|
Marv: hold a hotkey to ask about anything on screen, and it answers aloud while drawing arrows and notes to guide you.
LINK
|
|
useagent: provides AI agents with their own cloud computer that use your tools to deliver finished websites, decks, spreadsheets, reports, and pull requests.
LINK
|
|
You can check the previous tools here, or add your tool here
|
|
|
Our AI Academy has 330+ step-by-step tutorials on ChatGPT, Claude, Perplexity, and every tool that matters. No fluff — just practical workflows you can use at work. Try it free for 7 days.
|
|
💬 How did you find today's edition?
We read every reply — just reply to this email and let us know how we can improve!
|
|
