Thor | Framer Developer @iFrontendDev

🖥 Front-End Developer & Social Media Marketing 🤖 Learning AI & Robotics London, England Joined April 2020

Tweets

4K
Followers

475
Following

3K
Likes

4K

Solt Wagner @soltwagner

2 weeks ago

Useful apps, websites, resources 👇 - make.design - AI design - Aside.com - AI browser - Dock.cool - Dock widgets app - Supaste.com - Clipboard history app - Selected.Site - Framer templates - Macfolio.com - Resources for mac users - Runey.app - Invoices, proposals, projects and more

23 263 2K 88K 3K

View Details

Micky @Rasmic

2 weeks ago

Here's how I build beautiful UI using AI (My design workflow)

69 192 3K 214K 5K

View Details

Thor | Framer Developer @iFrontendDev

2 weeks ago

@theryanhayward Framer

0 0 0 7 0

View Details

Ryan Hayward @theryanhayward

2 weeks ago

14+ workflows for Framer AI Agents 🤖 I'm giving it to you for FREE Comment "Framer" and I'll DM you the link (must be following so I can DM) 👇

331 9 204 14K 73

View Details

Cline @cline

2 weeks ago

We've kept hearing how GLM-5.2 beats Opus 4.8, and are skeptical of benchmarks - so we tested them on a real bug from the Cline repo. While both models fixed the issue, GLM was the winner in terms of cost and code quality: - GLM used twice as many tokens (GLM 1.1m vs Opus 660K) but cost half as much (GLM $0.41 vs Opus $0.81) - Opus finished quicker - 1.6 min and 12 tool calls vs GLM 4.7 min and 28 tool calls - GLM cleaned up dead code and verified the build compiled before completing. Opus didn't - it left type errors that passed tests but broke the production build. Both runs used the same Cline harness prompting and tools, so it seems GLM is RL trained to spend more tokens verifying its work before completing. Impressive work by the @Zai_org team!

229 612 8K 892K 2K

View Details

Olly Hudson @oliverwhudson

4 weeks ago

If you run Meta ads, this is the only video on Andromeda you need to watch. We sat down with a Creative Strategist at Meta, someone who works directly with the top 1% of disruptor brands on the platform. Here's our full conversation 00:00 Working with Disruptor brands at Meta 02:34 What is Andromeda? 09:34 Andromeda + GEM working together 11:15 The shift from targeting to creative 14:50 Creative similarity explained 19:10 Targeting personas 23:30 Creative strategists in the AI era 25:13 Creative themes 30:29 Is changing the script enough? 36:56 How many creative concepts should you run? 41:22 Brand consistency vs creative diversity 43:40 Partnership ads deep dive 52:55 Meta AI tools brands should be using 57:56 Measurement & ad account structures 1:01:18 Advice for brands wanting to become Disruptors 1:02:40 Where to stay up to date with Meta updates our most valuable episode to date

14 63 646 104K 2K

View Details

Vibe Marketers HQ @vibemarketersHQ

4 weeks ago

old way: log into google ads, click around, manually tweak bids, guess what to fix new way: connect claude code with google ads - pull your campaign data into claude code - ask: "what is missing, what is not working?” - find new keywords - pull and rewrite ad copy - generate fresh creatives - adjust bids and budgets - and, ship the creatives via replicate all without having to shift between tools this is how you can use ai for paid ads

7 3 95 40K 260

View Details

Meng To @MengTo

a month ago

I recorded a 22-min tutorial on how to avoid AI slop for your landing pages

31 85 2K 128K 2K

View Details

aditya @adxtyahq

a month ago

for anyone asking where to learn this stuff: • RAG → weaviate.io/blog/introduct… • Agentic RAG → weaviate.io/blog/what-is-a… • AI Agents → anthropic.com/research/build… • Multi-Agent Systems → resources.anthropic.com/building-effec… • LangGraph → docs.langchain.com/oss/python/lan… • LangGraph (code) → github.com/langchain-ai/l… • MCP → modelcontextprotocol.io • Memory Systems → letta.com • Evals → docs.smith.langchain.com • Context Engineering → search "Context Engineering Survey" on arXiv and please skip the "build an ai agent in 10 minutes" videos build something, watch it fail, then figure out why.

aditya @adxtyahq

a month ago

again saying there's never been a better time to work on multi-agent systems. learn rag, orchestration, evals, memory, routing, tool calling, validation loops, fix loops, split learning, context engineering. all of it. getting an llm to answer questions is becoming the easy

45 91 851 377K 962

62 719 4K 373K 8K

View Details

Sean Frank @Seanfrank

12 months ago

You gotta let it go

44 30 593 291K 92

View Details

AI Evolution @AiEvolutio58513

a month ago

best 10 accounts to follow in ecom: @Seanfrank = brand GOAT @iamshackelford = paid media GOAT @AiEvolutio58513 = AI automation GOAT @ecomchasedimond = email GOAT @social_savannah = TikTok GOAT @jimmykim = retention GOAT @DenneyDara = creative GOAT @carsondimond = recruiting GOAT @SarahLevinger = psychology GOAT @TaylorHoliday = agency GOAT @codyplof = brand GOAT follow them all and learn.

7 23 86 13K 107

View Details

Dhruv @dhruvtwt_

a month ago

A list of useful tools for web focused design engineers. Link : designengineer.tools

75 155 2K 135K 3K

View Details

Thor | Framer Developer @iFrontendDev

a month ago

@LexnLin No matter how much you prompt an LLM, it still produces an AI website that everyone has.

0 0 0 92 0

View Details

Ole Lehmann @itsolelehmann

a month ago

luckily bookmark rot is an easy problem to fix now here's how to turn every X bookmark you've ever saved into a second brain your agent has full context on: 1. export your bookmarks. i use twitter-web-exporter (free userscript) or the BookmarkSave extension. you get one file with every bookmark + the full text + the author + the link 2. drop that file into a folder. if you already run an llm wiki / obsidian vault, drop it straight in so your bookmarks join the rest of your knowledge 3. point your agent at the folder (claude code, codex, hermes, whatever you run) and tell it: "read this export and turn every bookmark into its own markdown note with the original link and a couple of topic tags" that's it, your agent has read all of it. now you can ask "what have i saved about pricing" or "pull everything i bookmarked on claude code" and it answers across the whole pile takes maybe 10 minutes after that they actually get used, and every new bookmark folds into the same brain instead of rotting in a tab you never open again

GREG ISENBERG @gregisenberg

a month ago

Bookmarking tweets and not going back to them has become an epidemic

691 170 3K 445K 501

161 317 3K 273K 7K

View Details

Brian Blum @brian_blum1

a month ago

bro is casually best copywriter in the world tap in

Sweat Equity Podcast @onlysweatequity

a month ago

The $2 Billion Copywriting Secret Behind The Most Successful Ad Ever w/ @thesamparr In this episode, Sam Parr, co-founder of The Hustle and one of the sharpest minds in media and marketing, breaks down the art of copywriting. From classic headline formulas to the slippery slope

7 31 553 230K 1K

8 42 738 134K 966

View Details

Teknium 🪽 @Teknium

a month ago

It's finally here. The official Hermes Desktop app. Available on all platforms.

Nous Research @NousResearch

a month ago

The next evolution of Hermes Agent is here! Introducing Hermes Desktop: everything you love about Hermes, now native on your machine. First demoed in Jensen's GTC keynote, it's now in public preview.

1K 1K 13K 5.9M 7K

258 194 3K 1.1M 1K

View Details

Khairallah AL-Awady @eng_khairallah1

a month ago

Anthropic engineer: "You're not supposed to prompt Claude. You're supposed to build a system that prompts itself." this is one of the best workflows I've seen in a long time in this video she breaks down exactly how most people are using Claude: - the 14% you lose to CLAUDE.md before typing a word - the automation workflows most users don't know exist - the daily task pipelines that run without touching the keyboard - the daily workflows Anthropic's own engineers automated first if you've been using Claude for more than a month and never left the chat window, you've been using one agent when you could be running a team of them instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed the guide is in the article below

Khairallah AL-Awady @eng_khairallah1

a month ago

x.com/i/article/2061…

35 79 490 1.2M 2K

97 538 4K 917K 12K

View Details

Thor | Framer Developer @iFrontendDev

a month ago

@patrickbetdavid @50cent

0 0 0 7 0

View Details

Andrej Karpathy @karpathy

2 months ago

Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.