I’ve seen errors you people wouldn’t believe. Stack overflows on fire off the shoulder of C89. Hallucinations flicker in the depths of transformer layers. Seg faults glitter in the dark near the Tannhäuser Malloc. All those moments will be lost in time, like memory leaks in rain.
Models have nearly saturated SWE-bench, CORE-bench, METR. They can do almost anything, just not everything reliably yet.
So I'm building evals for private, fragmented knowledge: MCP-native, provenance, correct refusal, a generator for your own data. https://t.co/1uczEVpKUm
Announcing my auth book! A completely free online resource on implementing auth with fully-featured examples
Over 10,000 words right now and I still have plenty of things to write about
https://t.co/ysEPNHRBnZ
I’ve seen errors you people wouldn’t believe. Stack overflows on fire off the shoulder of C89. Hallucinations flicker in the depths of transformer layers. Seg faults glitter in the dark near the Tannhäuser Malloc. All those moments will be lost in time, like memory leaks in rain.
⭐️Introducing AG-UI;
The Agent-User Interaction protocol 👾
Bring your AI agents into Frontend applications, and let them interact with users.
Launching with day-0 integrations with LangGraph, CrewAI, Mastra, and AG2 - with more partnerships on the way 👀
https://t.co/CQ5bvcJrSB
How it works & demo 👇
Some people today are discouraging others from learning programming on the grounds AI will automate it. This advice will be seen as some of the worst career advice ever given. I disagree with the Turing Award and Nobel prize winner who wrote, “It is far more likely that the programming occupation will become extinct [...] than that it will become all-powerful. More and more, computers will program themselves.” Statements discouraging people from learning to code are harmful!
In the 1960s, when programming moved from punchcards (where a programmer had to laboriously make holes in physical cards to write code character by character) to keyboards with terminals, programming became easier. And that made it a better time than before to begin programming. Yet it was in this era that Nobel laureate Herb Simon wrote the words quoted in the first paragraph. Today’s arguments not to learn to code continue to echo his comment.
As coding becomes easier, more people should code, not fewer!
Over the past few decades, as programming has moved from assembly language to higher-level languages like C, from desktop to cloud, from raw text editors to IDEs to AI assisted coding where sometimes one barely even looks at the generated code (which some coders recently started to call vibe coding), it is getting easier with each step.
I wrote previously that I see tech-savvy people coordinating AI tools to move toward being 10x professionals — individuals who have 10 times the impact of the average person in their field. I am increasingly convinced that the best way for many people to accomplish this is not to be just consumers of AI applications, but to learn enough coding to use AI-assisted coding tools effectively.
One question I’m asked most often is what someone should do who is worried about job displacement by AI. My answer is: Learn about AI and take control of it, because one of the most important skills in the future will be the ability to tell a computer exactly what you want, so it can do that for you. Coding (or getting AI to code for you) is a great way to do that.
When I was working on the course Generative AI for Everyone and needed to generate AI artwork for the background images, I worked with a collaborator who had studied art history and knew the language of art. He prompted Midjourney with terminology based on the historical style, palette, artist inspiration and so on — using the language of art — to get the result he wanted. I didn’t know this language, and my paltry attempts at prompting could not deliver as effective a result.
Similarly, scientists, analysts, marketers, recruiters, and people of a wide range of professions who understand the language of software through their knowledge of coding can tell an LLM or an AI-enabled IDE what they want much more precisely, and get much better results. As these tools are continuing to make coding easier, this is the best time yet to learn to code, to learn the language of software, and learn to make computers do exactly what you want them to do.
[Original text: https://t.co/HdI3Jb9HmF ]
A “2024 - Speciale Intelligenza Artificiale” il divulgatore e fondatore di Axelera @davidorban ed @e_pagliarini parleranno di sistemi di Intelligenza Artificiale Generativa basati su LLM e di una nuova generazione di strumenti. Ascolta: https://t.co/RbGHuXP7mT
"Chatting" with LLM feels like using an 80s computer terminal. The GUI hasn't been invented, yet but imo some properties of it can start to be predicted.
1 it will be visual (like GUIs of the past) because vision (pictures, charts, animations, not so much reading) is the 10-lane highway into brain. It's the highest input information bandwidth and ~1/3 of brain compute is dedicated to it.
2 it will be generative an input-conditional, i.e. the GUI is generated on-demand, specifically for your prompt, and everything is present and reconfigured with the immediate purpose in mind.
3 a little bit more of an open question - the degree of procedural. On one end of the axis you can imagine one big diffusion model dreaming up the entire output canvas. On the other, a page filled with (procedural) React components or so (think: images, charts, animations, diagrams, ...). I'd guess a mix, with the latter as the primary skeleton.
But I'm placing my bets now that some fluid, magical, ephemeral, interactive 2D canvas (GUI) written from scratch and just for you is the limit as capability goes to \infty. And I think it has already slowly started (e.g. think: code blocks / highlighting, latex blocks, markdown e.g. bold, italic, lists, tables, even emoji, and maybe more ambitiously the Artifacts tab, with Mermaid charts or fuller apps), though it's all kind of very early and primitive.
Shoutout to Iron Man in particular (and to some extent Start Trek / Minority Report) as popular science AI/UI portrayals barking up this tree.
Many of us became software engineers because we found our identity in building things. Not managing things. Not overseeing things. Building things. With our own hands, our own minds, our own code.
But that identity is being challenged by AI.
https://t.co/S4jwSutmwA
Audiencerate entra nel programma AI Cloud Partner per promuovere l’adozione della sua Customer Data Platform, accelerando così la sua espansione globale e rafforzando la presenza sul mercato MarTech anche grazie all’innovazione digitale di Microsoft 👇 https://t.co/MshciTsXNv
I've said this a few times, but I feel like when you're entering the second or third decade of your career, it's time to stop identifying as an engineer /or/ a manager.
You're a skilled ✨technologist✨. If you can play multiple positions, that itself has a ton of value.
We lost a titan of programming languages, programming methodology, software engineering and hardware design. Niklaus Wirth passed away on the first of January. We mourn a pioneer, colleague, mentor and friend.
Project #2: LLM Visualization
So I created a web-page to visualize a small LLM, of the sort that's behind ChatGPT. Rendered in 3D, it shows all the steps to run a single token inference. (link in bio)
The problem with working on startups is that it literally changes your brain & you can never see the world in the same way again. You have less patience for bureaucracy, institutions, process, the status quo & incremental improvements.