AMD is using Cline as their coding agent for local models.
After testing 20+ models, they found what actually works:
> 32GB RAM: Qwen3-Coder 30B (4-bit)
> 64GB RAM: Qwen3-Coder 30B (8-bit)
> 128GB+ RAM: GLM-4.5-Air
10-minute setup with @lmstudio + Cline, linked below
AMD is using Cline as their coding agent for local models.
After testing 20+ models, they found what actually works:
> 32GB RAM: Qwen3-Coder 30B (4-bit)
> 64GB RAM: Qwen3-Coder 30B (8-bit)
> 128GB+ RAM: GLM-4.5-Air
10-minute setup with @lmstudio + Cline, linked below
Say hi to OK Computer, Kimi's agent mode 🤖🎸
Your AI product & engineering team, all in one.
✨ From chat → multi-page websites, mobile first designs, editable slides
✨ From up to 1 million rows of data → interactive dashboards
✨ Agency: self-scopes, surveys & designs
✨…
Prompt optimization is becoming a powerful technique for improving AI that can even beat SFT! Here are some of our research results with GEPA at Databricks, in difficult Agent Bricks info extraction tasks. We can match the best models at 90x lower cost, or improve them by ~6%.
My napkin math says @OpenAI should be charging around $300 in monthly sub if they have 30M paying users with 25% profit margin with 10 PE at $300B valuation. Hm.
🚀 We're thrilled to unveil Qwen3-VL — the most powerful vision-language model in the Qwen series yet!
🔥 The flagship model Qwen3-VL-235B-A22B is now open-sourced and available in both Instruct and Thinking versions:
✅ Instruct outperforms Gemini 2.5 Pro on key vision…
In most development environments, your codebase connects to databases, integrates with APIs, and adheres to coding standards.
These form an invisible framework that experienced team members navigate instinctively.
.clinerules make this framework explicit. 🧵
For todays morning coffee I'm reviewing @calebwrites0101 video on energy consumption for Ai.
Noticed he only has about 40 followers on here despite having 17,000 subscribers on youtube
His videos are fantastic. Going to binge a few today.
More people should follow him here.…
97 Followers 403 FollowingBuilding https://t.co/zoAVYnDqbC. We enable traders automate their trading algorithms with any brokers and cross platform. NO APIs, NO Webhooks, No hassle
2K Followers 606 FollowingFormerly @GiannisWorld got suspended at 10k💔 PARODY AND FAN ACCOUNT | NOT AFFILIATED WITH GIANNIS OR THE MILWAUKEE BUCKS OR ANYBODY
15K Followers 787 Followingslightly less attractive cofounder @AskEureka: we’re replacing all doctors with AI. prev @Harvard @Google @BCG tweeting wrong thoughts only, dm to say hi :)
9K Followers 713 FollowingI make youtube vids on cool AI research /// AI papers newsletter https://t.co/Xn7GMDbQSd /// paper recap @TheAITimeline /// building @findmypapersAI
45K Followers 3K FollowingWe're in a race. It's not USA vs China but humans and AGIs vs ape power centralization.
@deepseek_ai stan #1, 2023–Deep Time
«C’est la guerre.» ®1
96K Followers 1K FollowingCEO @HyperWriteAI, @OthersideAI, creator of https://t.co/PSUlubx5bb (Github for prompts), investor in @GroqInc @Etched @Rork_App @OpenRouterAI + many more
14.9M Followers 70 FollowingApple CEO Auburn 🏀 🏈 Duke 🏀 National Parks 🏞️ “Life's most persistent and urgent question is, 'What are you doing for others?'” - MLK. he/him
57K Followers 858 FollowingFiguring out AI @allen_ai, open models, RLHF, fine-tuning, etc
Contact via email.
Writes @interconnectsai
Wrote The RLHF Book
Mountain runner
62K Followers 12K FollowingAI policy researcher, wife guy in training, fan of cute animals and sci-fi, Substack writer, stealth-ish non-profit co-founder
1.4M Followers 1K FollowingBuilding @EurekaLabsAI. Previously Director of AI @ Tesla, founding team @ OpenAI, CS231n/PhD @ Stanford. I like to train large deep neural nets.
1.3M Followers 1K FollowingCo-Founder of Coursera; Stanford CS adjunct faculty. Former head of Baidu AI Group/Google Brain. #ai #machinelearning, #deeplearning #MOOCs
4.4M Followers 3 FollowingOpenAI’s mission is to ensure that artificial general intelligence benefits all of humanity. We’re hiring: https://t.co/dJGr6Lg202