Seven NeurIPS Papers Explore Self‑Improving Agents
found 7 neurips papers on "self-improving agents"! https://t.co/GEA5krNUVb
Edge Computing Accelerates AI Inference Deployment
lots of talk about inference moving to edge today here’s a nice intro thread from someone who’s been working on this:
Edge Inference Flips Economics—Try Mobile SDKs Now
the economics change rapidly when inference moves to the edge a perfect time to start playing around w mobile inference sdks like @RunAnywhereAI
Self‑learning Agents Gaining Traction in Research
finally seeing an increasing number of projects and research under the “self-learning” agents bucket :)
AI‑Native CRMs Shine: Attio Leads, Others Follow
ai native crms. @attio is great (we switched to it recently). @newitemco also looks solid/agentic. i havent played with it yet but @lightfld also seems similar.
Superhuman's Agentic Writing Pulls Emails and Web Context
just tried superhuman's agentic writing - you can ask it to look up relevant emails/web info as context!
Looking for Your Favorite New AI Tools
any new ai tools that you’ve started using recently and love?
Future AI Memory Needs Concepts, Tags, and Clustering
good intro to a couple of concepts/approaches to memory. not sure i agree agents need to forget, but I agree some sort of strategy is required to make sure you’re efficiently pulling only data you need into the context. i think current...
ChatGPT Now Includes Interactive Finance Widget
just noticed this interactive "finance-widget" in chatgpt for the first time https://t.co/DAk0SqRcC2
Ditto Powers New Functional Vibe Coding App
okay fine this is fun someone built a working vibe coding app on top of my earlier project called ditto (self-building coding agent w ~500 lines of code) https://t.co/VK2yyTzUnS https://t.co/GOoqgreIgr
Embeddings Beat LLMs for Fast, Cheap Classification
totally forgot about this experiment where i found it was faster and cheaper to do classification via embeddings vs using the fastest/cheapest llm (at the time)
Embedding Classification Beats Fastest Model on Speed, Cost
@jasonth0 did an experiment a bit back, and found that embedding based classification seemed consistently faster and cheaper than using the cheapest/fastest model (at the time) https://t.co/uuEPwu88cg
LLM
kinda like this, but instead of using vec2text - i found grabbing a few samples from each cluster and feeding into an llm came up with better names (not surprisingly) https://t.co/K8phyyDFdR
Clustering Embeddings Drives Dynamic Ontology Exploration
last weekend i went down the rabbit hole of how to build dynamic ontologies, and kept coming back to clustering of embeddings curious if anyone has cool experiments i could look at around this
Visualizing Karpathy’s Key Idea
i liked this @karpathy post from a few months back, and put together a quick slide to show this visually https://t.co/cQCkYxmQsB
Master One AI Tool, Skip the Noise
most people would be further along ignoring all ai discourse and just mastering one ai tool
AI-Powered Tool Turns Research Into Ready-Made Listicles
started working on a deep research agent to build nice lists for me and one thing led to another... introducing researchoor dot com an ai powered social listicle builder https://t.co/RoAEj1jDYE
AI Needs Onboarding and Scaffolding, Not Just Raw Models
this is an interesting experiment I love but it seems like they did little to no onboarding for the ai, where they didn’t even have the ai review the tools data schema and learn from it before trying to use...
AI Builders Clone Games, Only Rename—Ethical Question
not sure how i feel about ai app builders cloning existing games and just letting users change the name… (maybe this is okay cuz it was a tutorial meant to be cloned/learned from?) https://t.co/dYWJZ0E2Dk
Offload Model Inference to Devices, Slash Cloud Costs
if you're already starting to fine-tune open source models for smaller tasks, using something like the @runanywhereai sdk can let you offload some of the inference to user devices, lowering cloud inference costs and latency but there's probably more fun/unique applications...
Ollama Goes Mobile, Attracts Growing Interest
ollama for mobile, picking up attention https://t.co/sBa5luBHLh
AI Email Client Auto‑Tags, Scores, and Drafts Replies
this weekend, i vibe coded a prototype email client that i want... - for each email, looks up contacts details + notes in attio, then org details, looks at lists to determine if portfolio, LP, etc. - summarizes this context and creates...
AI Drafts Legal Docs, Lawyers Still Essential
ai can draft legal docs but you still want a lawyer to review it. i’m a fan (and investor) of services like @DocDraftai that combines the best of both into a single elegant service :)
Add AI to Any Site with a Tiny Widget
[tiny project] ai-share-widget the easiest way to add* ai capability to a site with a front-end widget where you can customize the prompt and allow the user to pass that into their AI tool of choice github (102 lines of code) in...