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.
Builders Unscripted: Ep. 2 - Ashe Magalhaes, Founder of Hearth AI
Watch on YouTubeChatGPT voice mode is a weaker model
I think it's non-obvious to many people that the OpenAI voice mode runs on a much older, much weaker model - it feels like the AI that you can talk to should be the smartest AI but it really isn't. If you ask ChatGPT voice mode for its knowledge cutoff date it tells you April 2024 - it's a GPT-4o era model. (Thought inspired by this Karpathy tweet about the growing gap in understanding of AI capability based on the access points and domains people are using the models with.) Tags: andrej-karpathy, generative-ai, openai, chatgpt, ai, llms
The appreciation of the useless is also why they like me so I just gotta accept it
Why do girls want the bed to be full of decorative pillows that you don't use But then at night you have to remove all those pillows Like what's the reasoning here, it's completely form over function huh
View quoted postgreat question! knowledge (system prompt, skills) and tools (apis, clis, whatnot) will always be needed, even as the best way to build agents changes i would focus on those and processes around those
@hwchase17 Harrison, what area of a harness do you think internal teams should be most opinionated about? Versus what areas do you expect to grow in abstraction as the industry matures? An example being - Ramp Inspects release post is now 88 days old, and since then we have seen the
View quoted postwhy not? what in the current harnesses are not bitter lesson-pilled? off top of head: will go away: - planning tools - compaction (or at least will matter less) not going away: - sub agents - skills - filesystem access - bash - websearch - mcps what else?
@hwchase17 I'll play devil's advocate and say that it's also much easier to accumulate bloat. current harness designs are not very bitter lesson-pilled
View quoted postSometime in the next 2-3 years agents will be using the internet more than humans We designed the whole thing for human eyes, human emotions, human attention spans Agents do not have any of that The internet as we know it was built for the wrong user The opportunity is rebuilding everything for the new user Agent-native search. Agent-native commerce. Agent-native discovery Every category is open again I can't stop thinking about it.
RT Andrew Nguonly Max volume for Max Agency 📣🗣️ Original tweet: https://x.com/andrewnguonly/status/2042621464587993429
🎙️Introducing Max Agency Max Agency is a new podcast where we go deep on how the best agents are actually being built: architecture decisions, tradeoffs, evals, and everything in between. Each episode, I sit down with engineering leaders who are doing this work in production.
View quoted postmiddleware is underrated
@hwchase17 middleware was the right abstraction for it too. way more adoptable than asking everyone to restructure their agent setup
View quoted post
I think it's non-obvious to many people that the OpenAI voice mode runs on a much older, much weaker model - it feels like the AI that you can talk to should be the smartest AI but it really isn't
Judging by my tl there is a growing gap in understanding of AI capability. The first issue I think is around recency and tier of use. I think a lot of people tried the free tier of ChatGPT somewhere last year and allowed it to inform their views on AI a little too much. This is
View quoted post