This might surprise many new to AI. The best agentic systems I have built and seen other top engineers build involve lots of boring deterministic steps.
You can't just throw more LLM agents at every problem and expect reliability to improve. Every error will compound into more errors.
You still need good classifiers, verifiers, and evaluators for agentic workflows to truly compound in the right direction. This is key to your "software factory."
BREAKING: @Zelle just sent $1.25M in its first confidential transfer using ZelleUSD ($ZLUSD) on Solana, live on stage at Breakpoint.
The network that moved $1.2T this year is going global.
Private AI, verified onchain.
Introducing Solana Confidential Compute, open-source tools for building private AI, with hardware attestations verified onchain.
Built with @TryNitoAI. Now in beta on Solana devnet.
Start building: https://t.co/YsA2Q8jYgH
prophetic prophetabilitiy - the changing nature of data ownership and privacy in the wake of the US midterm elections
read more post: link in thread below
computer science 1950--2022: eliminate all non-determinism
computer science 2026: set temperature=0.8 and see if bug vibes mellow, if not ask computer to try something random
computer science 1950--2022: eliminate all non-determinism
computer science 2026: set temperature=0.8 and see if bug vibes mellow, if not ask computer to try something random
There is still no substitute for caring. Every piece of software getting rapidly better is happening because a human cares. And happens to be using AI to move really fast.
There are 3 types of people in the world right now:
1. People who actually understand what AI is.
2. Idiots who have no clue how AI works.
3. The people taking advantage of those idiots for profit.