Follow AI Builders — Not Influencers
Discover real AI creators shaping the future. Track their latest blogs, X posts, YouTube videos, WeChat Official Account posts, and GitHub commits — all in one place.
RT Colin Francis say it with me, "memory systems are only as good as their ability to forget" the most overlooked part of building memory is building resilient memory that can forget and self-correct. a new functionality of openwiki is its ability to validate links, flag any as broken, and self-correct. thanks to @DecentralizedJM for adding this important functionality to openwiki!
Love that the “template” of an agent is just a folder of Markdown text and a few .𝚝𝚜 tools. Agent is the last class of software, and it’s the easiest kind to make with http://eve.dev
Let eve help your marketing team manage social. The Marketing team template makes it simple to collaborate on drafts, receive weekly Typefully analytics, and require human approval before posts are scheduled or published. https://eve.dev/templates/marketing-team-eve-template
View quoted postRT Denis Timonin Introducing Serverless Agents on the FlyMy Harness Cloud. For startups shipping agent-powered features: stop building agent infra. Describe the worker your product needs - ~90 seconds later it's live: its own API endpoint 1,000+ tools and integrations built in persistent state scheduled and background runs, laptop closed full execution history Your product calls the API. We run the agent loop, infra and compute. You build the product. We run the agents.
PSA: Slop infographics do NOT help make your slop post clearer
Activity on simonw/llm-anthropic
simonw commented on an issue in llm-anthropic
simonw commented on an issue in llm-anthropic
View on GitHubActivity on simonw/llm-anthropic
simonw labeled an issue in llm-anthropic
simonw labeled an issue in llm-anthropic
View on GitHubPipeNetwork/minimax-h3-mlx
PipeNetwork/minimax-h3-mlx MiniMax released MiniMax-H3 two days ago - they describe it as a "a general-purpose, omni-modal generative system", which in practice means it accepts text, images, audio and video and can use them to generate up to 15 second video clips with audio included. This Python package ports it to MLX for running on Apple Silicon. I got it running on my M5 Max MacBook Pro. I cloned the repo and ran the model like this: # First download the models uvx --from huggingface_hub hf download MiniMaxAI/MiniMax-H3 \ --include 'FL2VA/*' --exclude 'FL2VA/transformer/*' uvx --from huggingface_hub hf download pipenetwork/MiniMax-H3-MLX-8bit # Now run the prompt uv run --with mlx-vlm \ --with-requirements requirements.txt python scripts/generate.py \ "a rainbow colored skunk leaps over a mossy log in a supermarket" \ -o skunk.mp4 \ -c ~/.cache/huggingface/hub/models--MiniMaxAI--MiniMax-H3/snapshots/fa9c8ab1eaa21c8ae25e7e40b83b2e6002f340af/FL2VA \ -t ~/.cache/...
amplifying and following along. wishing @Drift0r the best of luck. Help him find help.
After 100+ doctors & thousands of tests, nobody can diagnose my complex medical issue. So, I decided to make all of my records public and beg the internet for help. Can you diagnose me? Plz share 4 help Medical records: https://drive.google.com/drive/u/1/folders/1z_juK9yVdhbzaGJafzzZYZWe3U1cs37e Full video: https://youtu.be/krP9EGyLCRE
View quoted post
