Top all-time · #4635
François Chollet
Personal blog · fchollet.substack.comaiphilosophy
François Chollet writes Sparks in the Wind, a personal blog at fchollet.substack.com about ai and philosophy. Since 2022, 17 different Hacker News readers have linked it 20 times, most often “I think about LLM prompt engineering”. The last post was in 2023, but the archive is still widely read.
Too few sampled comments (5) to say how often HN recommends it.?
Why HN links it
HN readers link François Chollet's Substack posts on how LLMs work, including prompt engineering and LLMs as program databases. Commenters cite them to explain how models handle unfamiliar words.
Summarised by Claude from a sample of 5 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Ideas on AI, technology, and society. Mostly ephemeral, but carries a small chance of starting a fire.
Most-linked posts?
- I think about LLM prompt engineering8 people · 10 mentions · first linked 2023-10-09
- AI is cognitive automation, not cognitive autonomy6 people · 6 mentions · first linked 2022-11-28
What Hacker News says?
Actually it's way easier to search for the information in an LLM compared to an 8 tb harddisk. The search is vague, and the result is nondeterministic, but in a lot of cases it's still the better method. https://fchollet.substack.com/i/137628402/llms-as-program-da... I like the way this article puts it. "LLM is a continuous, interpolative kind of database"
Comment linking /i/137628402/llms-as-program-databases
on “Spaced repetition can allow for infinite recall (2022)”Submitted Education as civilization-building as a story · 69 points
HN discussionThis seems to have similar ideas to an post from a year ago by François Chollet: https://fchollet.substack.com/p/how-i-think-about-llm-prompt...
Comment linking /p/how-i-think-about-llm-prompt-engineering
on “Prompts are Programs”Submitted The machine that makes the thing is more valuable than the thing as a story · 5 points
HN discussionI would read Francois Chollet's explanation of this. It's very good: https://fchollet.substack.com/p/how-i-think-about-llm-prompt... For words that are not in the model's vocabulary, like 'fluftable', the model uses a subword tokenization strategy. It breaks down the word into smaller known subunits (subwords or characters) and represents each subunit with its own vector. By understanding the context in which 'fluft…
Comment linking /p/how-i-think-about-llm-prompt-engineering
on “Orca 2: Teaching Small Language Models How to Reason”Submitted I think about LLM prompt engineering as a story · 3 points
HN discussionThe original article [0] is from 2023 and was already posted on HN multiple times. Anyway, while there's something interesting in this mental model, I find this attitude below and particularly the word "rather" to be overly reductive, seeing how you could argue that intelligence in general consists of searching in an abstract database of Platonic ideas. > Viewing LLMs as vector program databases rather than intellig…
Comment linking /p/how-i-think-about-llm-prompt-engineering
on “LLMs as Vector Program Databases: A New Mental Model”Submitted The Loop of Progress as a story · 2 points
HN discussion> We are tens of months into what looks like the AI age. The modern AI era started in 2017 with the "Attention Is All You Need" paper ( https://arxiv.org/abs/1706.03762 ). ChatGPT is a popular manifestation of something that has been making huge and significant progress (image recognition, language translation, image generation, etc.) since then. This blog post has helped me the most in trying to understand what LLM…
Comment linking /p/how-i-think-about-llm-prompt-engineering
on “Ask HN: What are the most interesting takes on Generative AI you've come across?”Submitted I think about LLM prompt engineering as a story · 2 points
HN discussionSubmitted AI is cognitive automation, not cognitive autonomy as a story · 2 points
HN discussionSubmitted AI is cognitive automation, not cognitive autonomy as a story · 2 points
HN discussionSubmitted I think about LLM prompt engineering as a story · 1 points
HN discussionSubmitted LLMs as Program Databases as a story · 1 points
HN discussionSubmitted Prompting As Searching Through A Space Of Vector Programs as a story · 1 points
HN discussionSubmitted How I think about LLM prompt engineering as a story · 1 points
HN discussionSubmitted AI is cognitive automation, not cognitive autonomy as a story · 1 points
HN discussionSubmitted AI is cognitive automation, not cognitive autonomy as a story · 1 points
HN discussionSubmitted AI is cognitive automation, not cognitive autonomy as a story · 1 points
HN discussionSubmitted AI is cognitive automation, not cognitive autonomy as a story · 1 points
HN discussion
