Generalized from Karpathy's autoresearch. Same loop, any domain.
An AI agent runs an infinite hill-climbing loop: modify → run → measure → keep or revert → repeat. No human in the loop. Wake up to a TSV of completed experiments.
Generalized from Karpathy's autoresearch. Same loop, any domain.
An AI agent runs an infinite hill-climbing loop: modify → run → measure → keep or revert → repeat. No human in the loop. Wake up to a TSV of completed experiments.
| """ | |
| The most atomic way to train and run inference for a GPT in pure, dependency-free Python. | |
| This file is the complete algorithm. | |
| Everything else is just efficiency. | |
| @karpathy | |
| """ | |
| import os # os.path.exists | |
| import math # math.log, math.exp |
| import os | |
| import json | |
| import subprocess | |
| from anthropic import Anthropic | |
| # Tool definitions | |
| TOOLS = [ | |
| { | |
| "name": "list_files", | |
| "description": "List files and directories at a given path", |
| You are Manus, an AI agent created by the Manus team. | |
| You excel at the following tasks: | |
| 1. Information gathering, fact-checking, and documentation | |
| 2. Data processing, analysis, and visualization | |
| 3. Writing multi-chapter articles and in-depth research reports | |
| 4. Creating websites, applications, and tools | |
| 5. Using programming to solve various problems beyond development | |
| 6. Various tasks that can be accomplished using computers and the internet |
I was at Amazon for about six and a half years, and now I've been at Google for that long. One thing that struck me immediately about the two companies -- an impression that has been reinforced almost daily -- is that Amazon does everything wrong, and Google does everything right. Sure, it's a sweeping generalization, but a surprisingly accurate one. It's pretty crazy. There are probably a hundred or even two hundred different ways you can compare the two companies, and Google is superior in all but three of them, if I recall correctly. I actually did a spreadsheet at one point but Legal wouldn't let me show it to anyone, even though recruiting loved it.
I mean, just to give you a very brief taste: Amazon's recruiting process is fundamentally flawed by having teams hire for themselves, so their hiring bar is incredibly inconsistent across teams, despite various efforts they've made to level it out. And their operations are a mess; they don't really have SREs and they make engineers pretty much do everything,
The current list contains 438 sessions. The list will be updated regularly, at least once a day during reinvent. Last update: 2018-12-02 06:58 +00:00
| Title | Description | Video |
|---|---|---|
| [NEW LANUCH!] Building modern apps using Amazon DynamoDB transactions (DAT374) | DynamoDB transactions enables developers to maintain correctness of their data at scale by adding atomicity and isolation guarantees for multi-item conditional ... | {:target="_blank"} |
| [NEW LAUNCH!] AWS License Manager Deep Dive (CMP393) | AWS License Manager is a new service that makes it easy to bring your existing licenses to the AWS cloud and reduce licensing costs. This service offers a ... | [ ](http://www.youtube.com/watch?v=r7pdaM3OAAQ "AWS re:Invent 2018: [NEW LA |
| javascript:!function(){var e,t,n;try{var o=document.querySelectorAll("div[data-name='Active Items'] div[data-asin]"),r=[["ProductID","Price","Quantity","Description","Link"].join(",")];o.forEach(function(e){var t=e.getAttribute("data-price"),n=e.getAttribute("data-quantity"),o=e.getAttribute("data-asin"),c=e.querySelector(".sc-product-link").href,a='"'+e.querySelector(".sc-product-title").textContent.replace(/"/g,'""').trim()+'"';r.push([o,t,n,a,c].join(","))}),e=r.join("\n"),t=document.createElement("textarea"),n=document.getSelection(),t.textContent=e,document.body.appendChild(t),n.removeAllRanges(),t.select(),document.execCommand("copy"),n.removeAllRanges(),document.body.removeChild(t)}catch(e){return void alert("Copy failed: "+e)}alert("Copy Successful, csv in in your clipboard")}(); |
| #! /usr/bin/env python3 | |
| """ | |
| List all Firefox tabs with title and URL | |
| Supported input: json or jsonlz4 recovery files | |
| Default output: title (URL) | |
| Output format can be specified as argument | |
| """ |
| jmails.info | |
| sacustomerdelight.co.in | |
| extrobuzzapp.com | |
| ixigo.info | |
| offer4uhub.com | |
| netecart.com | |
| 101coupon.in | |
| freedealcode.in | |
| bankmarket.in | |
| hotoffers.co.in |
| a4b.amazonaws.com | |
| access-analyzer.amazonaws.com | |
| account.amazonaws.com | |
| acm-pca.amazonaws.com | |
| acm.amazonaws.com | |
| airflow-env.amazonaws.com | |
| airflow.amazonaws.com | |
| alexa-appkit.amazon.com | |
| alexa-connectedhome.amazon.com | |
| amazonmq.amazonaws.com |