koushik

[koushik @imkoushik]

@naval @grok why is that?

[Naval @naval]

AI lets you search by concepts instead of by keywords.

[Comet @comet]

Clean up your inbox.

Ask Comet to unsubscribe you from spam and unwanted emails.

[The Learning Logbook @Tharuns_Journal]

Most older, successful people will tell you that their life was best when they lived it unapologetically, on their own terms. - @naval

[Navalism @NavalismHQ]

"You want to spend all your time either learning, earning, or relaxing."

@naval

[Demis Hassabis @demishassabis]

Chess is a much more intense game than people realise… I feel for Magnus here (he was winning earlier), but congrats also to Gukesh!

[Nassim Nicholas Taleb @nntaleb]

1 - No cost-benefit analyses for applications entailing sustainability. (Absorbing barrier)
2- Nothing that includes a parameter works for risky decisions.
2- Ethics is the result of intransigence by a minority, not by governmental efforts to "save the planet".

[Cassie Kozyrkov @decisionleader]

LLM coding assistants can't guarantee 100% reliable results. The 'generative' in GenAI means the output is randomly sampled from a distribution of likely responses based on your prompts. So you can get endless answers to the same question—some helpful, others far off the mark. Commercial #LLMs have some error-checking under the hood, but it's not bulletproof.

[koushik @imkoushik]

@AravSrinivas would be great if you can add the feature to tag perplexity within chat similar to @AskPerplexity on X, instead of forward

[Demis Hassabis @demishassabis]

Soon with AI we will be communicating with dolphins and realistically simulating fruit flies…

[Demis Hassabis @demishassabis]

Really enjoyed this wide-ranging in-depth chat with Reid and Aria, thanks for hosting me!

[Naval @naval]

“Work in isolation, collaborate in person.”

- @maximecperoumal

[James @james1ach]

@ChrisWillx @naval being in love > being loved

[Naval @naval]

Currently my favorite account on YouTube…

Be Free From a Chaotic Mind (Ascendor):
https://t.co/1teeVYap77

[Prajwal Tomar @PrajwalTomar_]

I invented a new technique for Cursor.

Using this, I reduced AI hallucinations and assumptions by 85%.

I am calling it “knowledge base” technique.

Here’s how it works: ↓

[Cursor @cursor_ai]

Feedback is much appreciated! Much more to come.

[Andrej Karpathy @karpathy]

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 👇

[Naval @naval]

I went All In…

[Andrej Karpathy @karpathy]

New 3h31m video on YouTube:
"Deep Dive into LLMs like ChatGPT"

This is a general audience deep dive into the Large Language Model (LLM) AI technology that powers ChatGPT and related products. It is covers the full training stack of how the models are developed, along with mental models of how to think about their "psychology", and how to get the best use them in practical applications.

We cover all the major stages:
1. pretraining: data, tokenization, Transformer neural network I/O and internals, inference, GPT-2 training example, Llama 3.1 base inference examples
2. supervised finetuning: conversations data, "LLM Psychology": hallucinations, tool use, knowledge/working memory, knowledge of self, models need tokens to think, spelling, jagged intelligence
3. reinforcement learning: practice makes perfect, DeepSeek-R1, AlphaGo, RLHF.

I designed this video for the "general audience" track of my videos, which I believe are accessible to most people, even without technical background. It should give you an intuitive understanding of the full training pipeline of LLMs like ChatGPT, with many examples along the way, and maybe some ways of thinking around current capabilities, where we are, and what's coming.

(Also, I have one "Intro to LLMs" video already from ~year ago, but that is just a re-recording of a random talk, so I wanted to loop around and do a lot more comprehensive version of this topic. They can still be combined, as the talk goes a lot deeper into other topics, e.g. LLM OS and LLM Security)

Hope it's fun & useful!
https://t.co/75mXcUBI8L