Artur Klajnerok retweeted
Switching brain state costs energy
"Stable" brain states exist in local energy minima, so there is an energy barrier to overcome to switch from one state to another
Nice summary of relevant papers and work by @DaniSBassett here:
helper.ipam.ucla.edu/publica…
Artur Klajnerok retweeted
📢 New @auth0 product: Auth for GenAI 🤖 our new product for devs building apps with GenAI
It helps devs secure their GenAI apps, with the dev experience @auth0 is known for
You can start using Auth for GenAI today: auth0 dot ai
What's in the box?
This developer preview supports 4 use cases:
1️⃣ User Authentication
2️⃣ Calling APIs on the users' behalf
3️⃣ Async User Confirmation
4️⃣ Authorization for RAG
1️⃣ User Authentication
GenAI agents or apps still need to know who the user is. e.g. a chatbot might need to display chat history, or know the user age/country to customize replies This requires authentication, and Auth for GenAI makes it easy to implement in GenAI apps
2️⃣ Calling APIs on the users' behalf
GenAI apps interact with other apps, e.g. to read emails or send a pull-request And they don't need a UI Agents need to call APIs with credentials that are for a single user, with narrow permissions
3️⃣ Async User Confirmation
Many GenAI workflows are async, take "longer" to reply @OpenAI's o family of models is a good example of it. Users won't wait in front of a chat window. GenAI agents need to support async confirmation securely
4️⃣ Authorization for RAG
GenAI apps use RAG to make relevant data available to LLMs for replies To avoid disclosing sensitive information, it is paramount to ensure that the content used to generate answers is content each user can access
How do we make all of this easy?
We have SDKs, docs and sample apps for many of the popular GenAI app frameworks: @aisdk @langchain @llama_index @Firebase Genkit and others like @CloudflareDev AI and @crewAIInc are coming soon
And we really want your feedback (my DMs are open, we have a Discord community). If you have issues, want other features, frameworks, or want to collaborate on making Auth for GenAI easy to integrate into your platform, I'd love to chat
I am very excited about how this product will enable all of us devs to make prod ready AI apps a reality. Looking forward to learning how you are using it!
Artur Klajnerok retweeted
Introducing the Evals API.
You can now programmatically define tests, automate evaluation runs, and quickly iterate on prompts.
Evals are still available in the dashboard—and now through the API, so you can integrate them anywhere in your workflow.
Artur Klajnerok retweeted
The reality of building web apps in 2025 is that it's a bit like assembling IKEA furniture. There's no "full-stack" product with batteries included, you have to piece together and configure many individual services:
- frontend / backend (e.g. React, Next.js, APIs)
- hosting (cdn, https, domains, autoscaling)
- database
- authentication (custom, social logins)
- blob storage (file uploads, urls, cdn-backed)
- email
- payments
- background jobs
- analytics
- monitoring
- dev tools (CI/CD, staging)
- secrets
- ...
I'm relatively new to modern web dev and find the above a bit overwhelming, e.g. I'm embarrassed to share it took me ~3 hours the other day to create and configure a supabase with a vercel app and resolve a few errors. The second you stray just slightly from the "getting started" tutorial in the docs you're suddenly in the wilderness. It's not even code, it's... configurations, plumbing, orchestration, workflows, best practices. A lot of glory will go to whoever figures out how to make it accessible and "just work" out of the box, for both humans and, increasingly and especially, AIs.
Artur Klajnerok retweeted
A deindustrialized America simply does not produce enough to pay for what it consumes.
It prints money instead. And exchanges these pieces of paper for valuable goods.
But if the world stops using that money, the US has a real problem. So, alienating allies is not a good idea.
This is as dumb as it gets.
The rest of the world holds $27 trillion in US securities, that is, the rest of the world finances the US, which overspends & undersaves.
Good luck when Trump drives foreign financial investments away!
Start thinking!
Artur Klajnerok retweeted
What happens if high quality AI models become free, ubiquitous, and inexpensive to run on even low-spec hardware?
(1) First, you can rebuild every productivity app AI-first. That starts with Microsoft Word, Google Sheets, and Apple Keynote. But it extends to wholly new kinds of productivity apps.
(2) Second, every “smart” device becomes truly smart. Your fridge can double as your nutritionist. Your alarm clock is your sleep therapist. And so on. Just like your car is already your driver.
(3) Third, moats move to the app layer. As others have remarked, the GPT wrappers may end up more defensible than the GPT model itself.
(4) Fourth, physicality becomes relatively more valuable. The hardware, the secure real estate, the in-person community — these are all things digital AI can’t deliver.
(5) Fifth, high human IQ actually becomes increasingly valuable. Because AI is really amplified intelligence rather than truly agentic intelligence, since it requires the creative prompt to get started.
(6) Sixth, prompt engineering is here to stay, because prompting is programming — just in a higher-level language.
(7) Seventh, the most common form of AI doomerism is proven false, because we are getting decentralized ubiquitous AI rather than centralized monotheistic AI. More like a garden of smart things than a vengeful Old Testament God that’ll turn you into paperclips.
(8) Eighth, the combination of cuts to US “industrialized” academic research at the same time AI models accelerate discovery will mean a return to individual gentleman scientists and the advance of desci (decentralized science).
(9) Ninth, the complement to probabilistic AI is deterministic crypto. For captchas, for identity, for money, for all these things — crypto is the digital scarcity that AI can’t fake.
(10) Tenth, the main cost of software development may reduce to reducing the costs of the physical environment. That is: to providing society-as-a-service, to simply giving engineers time to type and experiment in peace. This was already so, but may become even more so.
Several of these points have been made by others, but I think that collectively they help define the second mover era.
AI will move into a window (later this year) that I would call "second mover's advantage." That is, the first obvious moves that could be big are played out given the technology/funding cycle. The rest of us get to watch how it worked out, take stock of the pace, understand how users use it, and better consider where it will be vs where it was--without baggage.
Much of mobile and web had second movers that became dominant.
Artur Klajnerok retweeted
building AI agents with python 🐍 and need to do RAG ? everyone does 😅
@langchain LangGraph 🤝@auth0 FGA make it easy and secure
@bajcmartinez explains how 👇
auth0.com/blog/building-a-se…
Artur Klajnerok retweeted
France has already achieved the level of electricity decarbonization the world aims for by 2050.
Yet environmentalists still claim we’re behind.
Artur Klajnerok retweeted
Pretty sure I’m typing more into AI models windows than into email or company slack these days. Work has shifted dramatically already
Artur Klajnerok retweeted
New 2h11m YouTube video: How I Use LLMs
This video continues my general audience series. The last one focused on how LLMs are trained, so I wanted to follow up with a more practical guide of the entire LLM ecosystem, including lots of examples of use in my own life.
Chapters give a sense of content:
00:00:00 Intro into the growing LLM ecosystem
00:02:54 ChatGPT interaction under the hood
00:13:12 Basic LLM interactions examples
00:18:03 Be aware of the model you're using, pricing tiers
00:22:54 Thinking models and when to use them
00:31:00 Tool use: internet search
00:42:04 Tool use: deep research
00:50:57 File uploads, adding documents to context
00:59:00 Tool use: python interpreter, messiness of the ecosystem
01:04:35 ChatGPT Advanced Data Analysis, figures, plots
01:09:00 Claude Artifacts, apps, diagrams
01:14:02 Cursor: Composer, writing code
01:22:28 Audio (Speech) Input/Output
01:27:37 Advanced Voice Mode aka true audio inside the model
01:37:09 NotebookLM, podcast generation
01:40:20 Image input, OCR
01:47:02 Image output, DALL-E, Ideogram, etc.
01:49:14 Video input, point and talk on app
01:52:23 Video output, Sora, Veo 2, etc etc.
01:53:29 ChatGPT memory, custom instructions
01:58:38 Custom GPTs
02:06:30 Summary
Link in the reply post 👇
Artur Klajnerok retweeted
What we've learned from LLM is that when your sample is monstrously large, induction can fool you as it becomes nearly indistinguishable from deduction.
Artur Klajnerok retweeted
The EU is healing: A Majority Now Supports Nuclear Energy 💙
The top 5 most pro-nuclear countries:
1️⃣ Czechia (77%)
2️⃣ Finland (71%)
3️⃣ Poland (69%)
4️⃣ Denmark (66%)
5️⃣ France (66%)
I illustrated results from a brand new survey by @EurobarometerEU, which asked EU Citizens the following question:
“Do you think nuclear energy will have a positive, negative, or no effect on our way of life in the next 20 years?”
Compared to the same survey in 2021, the positive attitude toward nuclear has increased by 10 percentage points across the EU.
A majority of EU Countries (16 out of 27) saw an increase in the proportion that thinks nuclear energy will have a positive effect on our way of life compared to 2021.
The largest increases can be observed in Denmark (66%, +22 pp), France (66%, +21 pp) and Germany (44%, +19 pp).
One of the biggest surprises? Denmark in the top 5! A country that has banned nuclear power for electricity production since 1999 and kept it out of national energy planning since 1985.
One thing is clear: EU Citizens increasingly support nuclear energy, and the trend is only growing.
Artur Klajnerok retweeted
Agency > Intelligence
I had this intuitively wrong for decades, I think due to a pervasive cultural veneration of intelligence, various entertainment/media, obsession with IQ etc. Agency is significantly more powerful and significantly more scarce. Are you hiring for agency? Are we educating for agency? Are you acting as if you had 10X agency?
Grok explanation is ~close:
“Agency, as a personality trait, refers to an individual's capacity to take initiative, make decisions, and exert control over their actions and environment. It’s about being proactive rather than reactive—someone with high agency doesn’t just let life happen to them; they shape it. Think of it as a blend of self-efficacy, determination, and a sense of ownership over one’s path.
People with strong agency tend to set goals and pursue them with confidence, even in the face of obstacles. They’re the type to say, “I’ll figure it out,” and then actually do it. On the flip side, someone low in agency might feel more like a passenger in their own life, waiting for external forces—like luck, other people, or circumstances—to dictate what happens next.
It’s not quite the same as assertiveness or ambition, though it can overlap. Agency is quieter, more internal—it’s the belief that you *can* act, paired with the will to follow through. Psychologists often tie it to concepts like locus of control: high-agency folks lean toward an internal locus, feeling they steer their fate, while low-agency folks might lean external, seeing life as something that happens *to* them.”
Artur Klajnerok retweeted
This is the AI graph that big companies (and many startups) haven’t yet absorbed. Models are getting both better and cheaper at very fast rate.
You either need to skate towards where the puck is going, or else make a bet on when AI will hit a wall. Don’t assume a static world.
Artur Klajnerok retweeted
our educational system is extremely unfun. you're forced in a classroom metabolizing lifespan for 8 hours a day, cramming homework, memorizing lists...
we want creative project-based learning. 1:1 tutoring. personalized, self-paced lesson plans. joy and mastery drive discipline!
Magnus Carlsen gives a great explanation of the extraordinary power of what @DavidDeutschOxf has coined the 'fun criterion'... and the perils of its negation.