Fausto Albers @WonderWhyAI

My longest running consulting client @WonderWhyAI gave a talk on: "Coding Agents That Improve Their Own Harness" and it is going viral! interesting watch! youtube.com/watch?v=kic8ij… Want to think, create, and build better with AI? Explore the practical lessons, live sessions, and one-to-one guidance linked in my bio and the reply below.

Sweet irony. @Gregor Ojstersek, please allow me to share the smirk. Feeling confident you understand the Dunning-Kruger effect? Because if you do, you don’t. You’re falling for it. Given the incomplete information in your repost, you should at least have considered the opposite possibility. Instead, you seem to fill in the gaps with what is most likely confirmation bias-induced projection. The presented archetype, the “vibe coder”, may very well be under the impression that building multiple AI apps means they possess the skills and competence of a traditionally trained developer. In that case, yes, that would be illusionary competence, and therefore a plausible example of the Dunning-Kruger effect. However, one cannot rule out that the vibe coder actually has a very good understanding of their own competence. Their mistake here may not be self-overestimation. It may be an erroneous assumption, or a failing theory of mind, in regard to the hiring party’s understanding of what professional and creative qualities are important in the nearby future. And as the required-skills debate is open-ended, undecided, and not truly knowable, one also has to leave open the possibility that the Dunning-Kruger effect here actually lies with the hiring party. They think they know what they need. And who knows, they might be wrong. The reason for their bias could very well be accumulated competence in a field that is rapidly changing. Their understanding of the pressure that selects for what arbitrary features are of the winning kind may already be outdated. So yes, this may be Dunning-Kruger. But your post does not establish where. PS: It’s “its”, not “it’s”. But I can appreciate the tell that you didn’t use AI to draft ur post.

@lydiahallie Published this last wknd! github.com/Galbaz1/video-…

All we really now have to build are the tools. Agents do, and will do more before it’s 2027, understand how to use them. Almost everyone will be building code by the end of this year. And if you’re not, chances are you are missing out. I had AI build this plugin, one weekend.

@sama @thorstenball Speed!

I studied to be a sociologist, became a restaurant owner, and then transitioned to AI research. I now lead GenAI R&D at AUAS Industrial Digital Twins Lab. What I have learned contradicts much of what people assume about AI and coding. Essay -> wonderwhy.ai

@FU_joehudson Evolutionary psychology suggests our minds are modular—more like a committee of specialized drives shaped by ancestral pressures. Ideally, they integrate, but selectively accepting or rejecting parts is often key to adaptation.

@superwhisper @superwhisper is so extremely useful. I use it to convert my ideation STT as highly prompt-engineered coding instructions into @cursor_ai - My spoken thoughts are augmented with a very different type of Intelligence than mine. This will be so popular.

@sama @sama what it we consider RAG to be a closed source problem like math and coding? After all, the correct answer to a given (search)query is a function of the (correctly) retrieved chunk IDs. Wrote this paper on it last wknd. Reason to RAG: tinyurl.com/rag-linkedin-s…

@iruletheworldmo I think you’re right. RL is going to change the game. Imagine if you apply GPRO to RAG agents by framing retrieval as a closed sourced problem. The correct answer are just chunk IDs after all. I wrote on it last week. wonderwhyai.notion.site/Reason-to-RAG-…

Here's my talk with Jason Liu @jxnlco - creator of the open-source #Instructor library, a fantastic framework for structured prompting, data extraction and validation (and more). We spoke on the October AI Builders Meetup #Amsterdam. We are a community of AI Engineers that hosts monthly meetups in Amsterdam, Rotterdam and Berlin. youtu.be/G2H9jNRO6Nc #LLM #Instructor #GenAI #OpenAI #Llama #Anthropic #prompting #aiengineer

Did @OpenAI just take a swing at @cursor_ai? openai.com/index/introduc…

@ivanleomk @jxnlco @jxnlco that’s awesome! Thanks! Keen to test it out.

@jxnlco Amsterdam! You get to join the infamous AI Builders Meet-up l, and I’ll get on the list to get into the coolest restaurants and clubs. 🤘

@trussliz @elonmusk @X Free speech means nothing without the ability to say something meaningful. Freedom without constraints is just chaos. Free speech without sensible restrictions is only anarchy.

@helloiamleonie That’s why we use query understanding -> transformation -> routing

Generating interactive web components on the fly with the latest #openai model. got-4o-2024-08-06 is trained to return not only valid json objects, but also adheres with 100% accuracy to the your schema definition. loom.com/share/6914b82c… Code by @hive_echo

@shashwath19 @jxnlco After the designated field is populated I check if the value exists in the citation. If all true than pass, if false than retry kicks in. In the retry call I define a custom class to capture and analyse the validation error (so it does not get buried in context)

@shashwath19 @jxnlco I define a field to capture a citation as the source of the designated value for the next field. Than I normalize the citation and the source text of the input document. Exact match with fuzzy match fall back is used to verify the existence of the citation.