AI can save you hours.
But if you let it do everything, you may stop practicing the skills you actually want to improve.
Try this instead:
THINK → try it yourself
ASK → use AI for help
REBUILD → make the final result yourself
Same AI. Better way to use it.
Your business uses AI. Is it actually working?
Or quietly burning money, leaking data, and wasting time?
I'm giving away FREE AI Audits - 8-10 min form, personalized report on your risks, waste & opportunities.
Link in the reply below ⬇️
#AIAudit
Big graphs, meet WebGL. graphify's graph.html no longer caps at 5,000 nodes - an optional xy renderer now draws full node-level detail, offline, no CDN.
Try: graphify export html --renderer xy.
PR: https://t.co/xITzAXtc7U
@graphify
Just shipped a fix to @graperootdev 's
GrapeRoot - graph_add_memory was silently dropping every new memory entry once a store hit the 200-entry cap. Now entries write with proper kind + created_epoch, so your cross-session decisions actually persist. 🛠️ #OpenSource#MCP
This is an advocacy letter from companies with skin in the game arguing for open-weight AI. The factual claims (history of open source, role on the internet) are correct. Most of it is policy argument, not fact-reporting. Reads exactly like what it is.
For my first post, I’m sharing a letter @NVIDIA signed on why open models matter.
AI will transform every industry, power every company, and be built by every country.
Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty.
The world needs both frontier closed models and frontier open models.
https://t.co/AUKzoQ5Ikb
One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10 minutes, total mess, anything goes, full stream of consciousness. Sometimes I declare it up top, something like "switching to speech recognition sorry for any typos...". Sometimes I turn it into a small interview of a few turns. But I find that the LLMs are somehow very good at reconstructing long incoherent rambles and often their echo of your own tangle of thoughts comes out quite a bit cleaner than what you started with. The result is that you improve the mind meld and have to correct things less from that point on.