amitunix retweeted
AI coding agents can waste time and tokens relearning the same lessons. TokenEconomizer builds on past sessions to cut costs while maintaining task success. It’s a path toward coding agents that learn not only how to solve tasks, but also how to spend computation more effectively.
The open-source plugin is available now on @github. msft.it/6017xDtyc
Microsoft just made Claude Code and Codex cheaper without touching the agent.
TokenEconomizer is a free, open-source plugin that learns from the sessions your agent already ran in a repo:
- Remembers the repo facts your agent keeps rediscovering
- Stops loading tools that never get used, since every tool definition is sent with every request
- Works with Claude Code, Codex, Copilot CLI and Pi
- 18.4% to 30.9% lower cost across 5 agent-model setups on SWE-Bench
If you hit your usage limits every week, this is free money.
Save your tokens.
github.com/microsoft/TokenEc…
amitunix retweeted
Anthropic just published an engineering guide on how to build always-on agents.
The biggest misconception: an always-on agent does NOT run 24/7. It sleeps almost all day, wakes up for short runs, saves state, and goes back to sleep.
The 5 core pieces I distilled:
1. Event Inbox
Put a database table between webhooks and your agent. Acknowledge webhooks fast, run only one active worker per user so runs never collide, and batch rapid messages together.
2. Timers
Keep timers in a separate table from the inbox. Split them into one-off follow-ups and recurring schedules. A background poller drops due timers into the inbox.
3. Lean Memory + Dreaming
Only store what cannot be looked up again: user instructions, user notes, past messages, and task progress. Load a small index at wakeup, not every file. Run periodic dreaming passes to clean out stale facts.
4. Unattended Permissions
Never put raw API keys inside the agent sandbox — inject them through an outside proxy. Use Deferred Tool Calls to pause risky actions for approval without blocking the worker.
5. Outbox
Queue outgoing replies so your agent paces notifications instead of spamming users at 3 AM.
claude.com/resources/article…
amitunix retweeted
New LangChain Academy course: Building and Deploying Managed Agents 🚀
An agent can take weeks to ship to real users because of all the infrastructure that has to run alongside it.
Led by @ishaan_lal1, learn to close that runtime gap
Enroll free: academy.langchain.com/course…
amitunix retweeted
Introducing Gemini Decision 1, our new frontier decision model in the Gemini API.
It is $0.10 per 1M input tokens with no additional cost. With support for image, audio, video, and PDF natively, 256K context window, & 1K questions.
You can try it for free in the API!
amitunix retweeted
Today we’re launching the Gemini Decisions API, powered by our new Gemini Decision 1 model in @GoogleAIStudio.
Instead of generating text token by token, it’s built for closed-set choices scoring up to 1,000 questions across text, images, audio, video + PDFs in a single pass. A few details:
- 3 decision types: yes/no, multiple choice (up to 255 options) + rubric scoring
- $0.10 / 1M input tokens with $0 billed for output tokens (~5x cheaper than Flash-Lite)
- leads on several benchmark evals with lowest calibration error
Google teams are already building with it, below is a look at Stitch Rapid designing a full product flow in seconds (1x speed)
amitunix retweeted
What happens when you combine embedding models with System 1 decision models? You get the intersection, which is VENN —> Vector Decision Models, a very cool OSS research project from Mark Russinovich that I was fortunate to review early and am excited to support.
How are Decision Models Trained?
Today, we are publishing the Drex Technical Report for the developer community! 🚀
Discover details on how the State-of-the-art Open-Source decision models are trained with RLAF.
Build more at: console.nace.ai/ (try for free)
P.S. Drex Max 1.1 and Drex for Finance are closed sourced and designed for enterprise use-cases
amitunix retweeted
this week at langchain:
- async subagents in deep agents - your agent keeps talking to you while subagents work in the background
- how we tuned browser use in MDA (7 toolsets tested, stagehand won)
- LangSmith BYOC on AWS, Azure + GCP
- Interrupt is back, March 24-25 in SF
amitunix retweeted
Memory is what allows Claude to learn from experience. In a new Engineering Blog post, we share how “dreaming” helps Claude organize what it’s learned, correct its mistakes, and find what it needs more easily the next time. anthropic.com/research/compo…
amitunix retweeted
first classifiers (jev) and now embedding models (ERNIE) ... is classical NLP making a comeback?
ernie.baidu.com/release/erni…
amitunix retweeted
Everyone’s excited about decision models. When should you buy one, or train your own?
We fine-tuned a 2B model for a production classifier: frontier-level quality, 35ms, ~1% of the cost.
We’re sharing when we think it’s worth it, and when it isn’t: airbnb.tech/ai-ml/frontier-q…
amitunix retweeted
NVIDIA Open-Sources Auto Ontology, a Semantic Layer for AI Agents
Your boss asks the AI agent: "What was revenue last quarter?"
It answers in 3 seconds. Clean number. Nice chart.
But it used the wrong "revenue" column. 𝗡𝗼𝗯𝗼𝗱𝘆 𝗻𝗼𝘁𝗶𝗰𝗲𝘀.
That's the problem NVIDIA's new open-source library, Auto Ontology, goes after. Its README puts it plainly:
"…𝘢 𝘳𝘦𝘷𝘦𝘯𝘶𝘦 𝘮𝘦𝘵𝘳𝘪𝘤 𝘢𝘯𝘴𝘸𝘦𝘳𝘦𝘥 𝘧𝘢𝘴𝘵𝘦𝘳 𝘪𝘴 𝘸𝘰𝘳𝘵𝘩 𝘯𝘰𝘵𝘩𝘪𝘯𝘨 𝘪𝘧 𝘵𝘩𝘦 𝘯𝘶𝘮𝘣𝘦𝘳 𝘪𝘴 𝘸𝘳𝘰𝘯𝘨."
𝗪𝗵𝗮𝘁 𝗶𝘁 𝗶𝘀:
A "context layer" that sits between an AI agent and your database. It tells the agent where the data lives, what each field means, and whether to use it.
𝗛𝗼𝘄 𝗶𝘁 𝘄𝗼𝗿𝗸𝘀, 𝘀𝘁𝗲𝗽 𝗯𝘆 𝘀𝘁𝗲𝗽:
• 𝗗𝗶𝘀𝗰𝗼𝘃𝗲𝗿: it reads your database metadata and drafts an ontology, a map of business terms like "active customer"
• 𝗚𝗿𝗼𝘂𝗻𝗱: agents use those terms instead of guessing from raw table names
• 𝗩𝗮𝗹𝗶𝗱𝗮𝘁𝗲: it checks generated SQL against certified definitions
• 𝗘𝘅𝗽𝗼𝘀𝗲: agents reach it through MCP, a CLI or an API
• 𝗟𝗲𝗮𝗿𝗻: certified corrections go back into the map
𝗙𝗼𝗿 𝘂𝘀𝗲𝗿𝘀:
Ask a question, get 𝘁𝗵𝗲 𝗮𝗻𝘀𝘄𝗲𝗿, 𝘁𝗵𝗲 𝗦𝗤𝗟 𝗶𝘁 𝗿𝗮𝗻, 𝗮𝗻𝗱 𝘁𝗵𝗲 𝗿𝗼𝘄𝘀. You can check the work, not just trust it.
𝗙𝗼𝗿 𝗯𝘂𝗶𝗹𝗱𝗲𝗿𝘀:
• Apache 2.0, runs with Docker Compose or Helm
• Works with Databricks, Postgres, Snowflake and DuckDB
• Defaults to NVIDIA's Nemotron models, but 𝗮𝗻𝘆 𝗢𝗽𝗲𝗻𝗔𝗜-𝗰𝗼𝗺𝗽𝗮𝘁𝗶𝗯𝗹𝗲 𝗲𝗻𝗱𝗽𝗼𝗶𝗻𝘁 𝘄𝗼𝗿𝗸𝘀
• The MCP server has 𝟵 𝗿𝗲𝗮𝗱-𝗼𝗻𝗹𝘆 𝘁𝗼𝗼𝗹𝘀. There is deliberately no tool to browse raw tables, so agents must go through the business terms
𝗜𝘁 𝗯𝘂𝗶𝗹𝗱𝘀 𝗼𝗻 𝗲𝗮𝗿𝗹𝗶𝗲𝗿 𝘄𝗼𝗿𝗸:
• Cube and dbt MetricFlow: semantic layers you write by hand in code
• Wren AI: an open semantic layer for AI agents, with a context layer built partly by agents
• Snowflake's Semantic View Autopilot: also drafts semantic models with AI, but only for Snowflake
What's different here: 𝗼𝗽𝗲𝗻 𝘀𝗼𝘂𝗿𝗰𝗲, 𝘄𝗼𝗿𝗸𝘀 𝗮𝗰𝗿𝗼𝘀𝘀 𝗳𝗼𝘂𝗿 𝗱𝗮𝘁𝗮𝗯𝗮𝘀𝗲𝘀, 𝗮𝗻𝗱 𝗯𝘂𝗶𝗹𝘁 𝗳𝗼𝗿 𝗮𝗴𝗲𝗻𝘁𝘀 𝘁𝗵𝗿𝗼𝘂𝗴𝗵 𝗠𝗖𝗣.
𝗧𝗵𝗲 𝗵𝗼𝗻𝗲𝘀𝘁 𝗽𝗮𝗿𝘁:
• 𝗧𝗵𝗲 "𝟵𝟬% 𝗳𝗮𝘀𝘁𝗲𝗿" 𝗰𝗹𝗮𝗶𝗺 𝗶𝘀 𝗡𝗩𝗜𝗗𝗜𝗔'𝘀 𝗼𝘄𝗻 𝘁𝗲𝘀𝘁𝗶𝗻𝗴, with no baseline published
• 𝗡𝗼 𝗮𝗰𝗰𝘂𝗿𝗮𝗰𝘆 𝘀𝗰𝗼𝗿𝗲𝘀 𝗮𝗿𝗲 𝗽𝘂𝗯𝗹𝗶𝘀𝗵𝗲𝗱. NVIDIA ships an eval harness (BIRD, 1,534 questions) but no results
• That harness was tested with 𝗖𝗹𝗮𝘂𝗱𝗲 𝗢𝗽𝘂𝘀 𝟰.𝟴, 𝗻𝗼𝘁 𝗡𝗲𝗺𝗼𝘁𝗿𝗼𝗻
• 𝗪𝗶𝘁𝗵𝗼𝘂𝘁 𝗛𝗮𝘀𝗵𝗶𝗖𝗼𝗿𝗽 𝗩𝗮𝘂𝗹𝘁, 𝗱𝗮𝘁𝗮𝗯𝗮𝘀𝗲 𝗽𝗮𝘀𝘀𝘄𝗼𝗿𝗱𝘀 𝗮𝗿𝗲 𝘀𝘁𝗼𝗿𝗲𝗱 𝘂𝗻𝗲𝗻𝗰𝗿𝘆𝗽𝘁𝗲𝗱 in Postgres (per the README)
• It's young: 𝗮𝗯𝗼𝘂𝘁 𝟳𝟱𝟬 𝗚𝗶𝘁𝗛𝘂𝗯 𝘀𝘁𝗮𝗿𝘀, and NVIDIA isn't accepting outside contributions
𝗧𝗵𝗲 𝗯𝗶𝗴𝗴𝗲𝗿 𝗽𝗼𝗶𝗻𝘁: the hard part of AI analytics isn't writing SQL. 𝗜𝘁'𝘀 𝗮𝗴𝗿𝗲𝗲𝗶𝗻𝗴 𝗼𝗻 𝘄𝗵𝗮𝘁 𝘁𝗵𝗲 𝘄𝗼𝗿𝗱𝘀 𝗺𝗲𝗮𝗻.
GitHub: github.com/NVIDIA/auto-ontol…
Links in reply 👇
amitunix retweeted
A lot of content engineering challenges have pretty standard solutions, which has lead to some engineers saying agent engineering is solved/boring
True to some extent, but there are a bunch of (fun) new ones emerging as agents evolve!
amitunix retweeted
If you saw Jev and you're wondering how decision models work, this should be helpful! In it I try to explain how Perplexity Decider works, plus some considerations around when and how to use decision models.
Lots of fun excalidraw figures!
amitunix retweeted
how do you fine-tune a decision model on your own data?
in these two notebooks, you'll learn:
• how to prepare the training data
• how to fine-tune our d1-3B decision model
• using @UnslothAI and @huggingface TRL
all within 30 minutes on a free-tier GPU.
unsloth: github.com/Liquid4All/cookbo…
TRL: github.com/Liquid4All/cookbo…
ps: how adorable are these halloween kitties? 👻
amitunix retweeted
typesafe.ai/blog/jev-1-14
Image inputs!
New output Type!
Longer Context!
Highway to... the Danger Zone





























