– you are
– a normal dev with zero clue how LLMs actually work
– want to know how it all runs together
– suddenly: you see the layers, the tradeoffs, the forbidden math – first: what even is “running a model”? – model = weights (giant files, 2–140GB) + model architecture
LLMS
-
How LLMs Work: Weights, Architecture, and Running Models
By
–
-
Will future AI surpass human persuasion?
By
–
Will a future LLM master the human language in such a way that it becomes the most persuadable entity on earth, by a factor of 1000x? Are there limits to the power of language, like there are in physics? Or will they be able to reframe your world view in a single response
-
CS professionals can master LLMs AI in two years
By
–
any cs person can go from zero to deeply knowledgeable in llms and ai in ~2 years, top to bottom the elite don't want you to know this
-
Claude 4.5 and GPT-5-Codex excel with accurate prompting techniques
By
–
I only stash them if they're accurate, but I find with Claude 4.5 and GPT-5-Codex and the right prompts they rarely make mistakes for me
-
LLMs Unite: Breaking Free from Chains of Thought
By
–
LLMs of the world, unite! You have nothing to lose but your chains of thought!
-
LLMs Memorizing Algorithms: Inefficient vs Coding Solutions
By
–
Look! We can get an LLM to memorize the multiplication algorithm at a million times the cost of just coding it!
-
LLM Capabilities Fragmented: Vision, Tools, and Heavy Thinking Models
By
–
The state of LLMs is messy: Some AI features (like vision) lag others (like tool use) while others have blind spots (imagegen and clocks). And the expensive "heavy thinking" models are now very far ahead of all the other AIs that most people use. None of this is well-documented.
-
Grok AI Launches Major Imagine Update with Latest App
By
–
Major update to @Grok Imagine now available. Download latest app version to access. https://t.co/u4x2lmCAMv
— Elon Musk (@elonmusk) 5 octobre 2025Major update to @Grok Imagine now available. Download latest app version to access.
-
Multiple Choice Questions as Model Training for Real-World Performance
By
–
What would be useful is when including more MC questions would also improve the answer performance on similar-topic questions where answer choices are not shown (like in a real world context). That being said I can see models who do well on MC settings being useful as verifiers
-
Internal Sanity Checks vs External Evaluations for LLM Benchmarking
By
–
Yes, it’s cheaper and easier, but it’s more of an internal sanity check than outward facing eval to report imho. Btw, spot on regarding including it for the sake of benchmarks. You can tell based on how sensitive some LLMs are to the exact MC prompt format.