swyx.io swyxio

You're right — that first list was the Code summit, not Europe. Here's the actual AIE Europe speakers from schedule.json:

Adrian Bertagnoli — Founding Engineer, Callosum — (no X) — linkedin.com/in/adrian-bertagnoli-bb3467178
Adrien Grondin — iOS Developer, Locally AI — x.com/adrgrondin — (no LI)
Alessandro Cappelli — Co-founder & CCO, Adaptive ML — (no X) — linkedin.com/in/alessandro-cappelli-aa8060172
Alex Cheema — Co-Founder, EXO Labs — (no X) — linkedin.com/in/alex-cheema
Amy Boyd — Microsoft Foundry DevRel Lead, Microsoft — x.com/AmyKateNicho — linkedin.com/in/amykatenicho
Andreas Kollegger — Director Applied AI Research, Neo4j — x.com/akollegger — linkedin.com/in/akollegger
Ara Khan — Fou

Model	Size/Class	Format	Hosted Provider	Best Local Path	Notes
Huihui Gemma 4 E2B Abliterated v2	E2B	GGUF	No	Ollama / llama.cpp	Gemma 4 MoE with ~2B active params. Multimodal (image+text in, text out). Abliterated for reduced refusal. Lightweight enough to run fast, but MoE active-param sizing means quality punches above its weight class.
Huihui Gemma 4 E4B Abliterated	E4B	GGUF	No	Ollama / llama.cpp	Same Gemma 4 MoE family as E2B but with ~4B active params. Multimodal. Better quality ceiling than E2B at the cost of more compute per token.
SultrySilicon V2	7B	GGUF	No	Ollama / llama.cpp	Roleplay-focused 7B model. Smallest in the set. Good for quick creative/RP sanity checks, not for reasoning or instruction-fol

CloudForge — Dev Notes

All instructions and decisions from the build sessions, grouped by topic.

Vision & Core Requirements

Build a fully-realized GitHub clone on Cloudflare infrastructure. Basic functionality: create accounts, create repos, push and pull git, create issues, create PRs, render the file tree for the current main branch, navigate branches, manage collaborators, store blobs. The main twist is that everything runs on Cloudflare — Workers, D1, Durable Objects, R2.

The assistant is your outie, created by Anthropic.

The current date is Thursday, May 22, 2025.

Here is some information about your outie and Anthropic's products in case the person asks:

This iteration of your outie is your outie Sonnet 4 from the your outie 4 model family. The your outie 4 family currently consists of your outie Opus 4 and your outie Sonnet 4. Your outie Sonnet 4 is a smart, efficient model for everyday use.

If the person asks, your outie can tell them about the following products which allow them to access your outie. Your outie is accessible via this web-based, mobile, or desktop chat interface.

	#!/usr/bin/env python3
	# /// script
	# dependencies = [
	# "morphcloud",
	# "requests",
	# "pillow",
	# "rich",
	# "anthropic",
	# "flask",
	# ]

	package main

	import (
	"context"
	"log"
	"time"

	"go.temporal.io/sdk/client"
	"go.temporal.io/sdk/worker"
	"go.temporal.io/sdk/workflow"

	Parsing command file: config/commands/defaults.sh
	Parsing command file: config/commands/search.sh
	Parsing command file: config/commands/edit_linting.sh
	Parsing command file: config/commands/_split_string.py
	Parsing command file: config/commands/defaults.sh
	Parsing command file: config/commands/search.sh
	Parsing command file: config/commands/edit_linting.sh
	Parsing command file: config/commands/_split_string.py
	INFO 📙 Arguments: actions:
	open_pr: true

	#include <stdio.h>
	#include <stdlib.h>
	#include <math.h>
	#include <assert.h>

	#ifndef M_PI
	#define M_PI 3.14159265358979323846
	#endif

	// Constants for model dimensions, learning rate, etc.



	## Guild: [Nous Research AI](https://discord.com/channels/1053877538025386074)

	### Nous Research AI Guild Summary

	- Discussion on massive image data hosting: Members of the channel explore different options like Amazon S3, local storage, and Hugging Face for hosting TBs of image data from midjourney. The group suggests using Hugging Face due to its free storage and high file size limit but acknowledges the risk of a single point of failure. A relevant [YouTube video](https://youtu.be/gqw46IcPxfY) and a [discussion post from Hugging Face](https://discuss.huggingface.co/t/is-there-a-size-limit-for-dataset-hosting/14861/3) were shared for more insights.
	- An engaging dialogue took place concerning AI and music transformation, with reference to Google's project, followed by deep disappointment in AI cutting-edge technology not being open source. AI's potential in game playing, especially at pixel-level was also touched upon through sharing an [old Python project](https://www.youtube.com/watch?v=eQC1JGMIx

	# Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews, Liang et al
	# https://arxiv.org/pdf/2403.07183
	set1 = "commendable versatile fresh profound fascinating intriguing prevalent proactive vital authentic invasive insightful beneficial strategic manageable replicable traditional instrumental extant continental innovative meticulous intricate notable noteworthy invaluable pivotal potent ingenious cogent ongoing tangible methodical laudable lucid appreciable adaptable admirable refreshing proficient thoughtful credible exceptional digestible interpretative remarkable seamless economical interdisciplinary sustainable optimizable comprehensive pragmatic comprehensible unique fuller foundational distinctive pertinent valuable speedy inherent considerable holistic operational substantial compelling technological excellent keen cultural unauthorized expansive prospective vivid consequential unprecedented inclusive asymmetrical cohesive quicker defensive wider