PinnedPublished inAI AdvancesMy GPT-evaluator got 1000% better with this simple trick.I wish I had known this trick sooner.Jan 917Jan 917
PinnedIn 2030, this will be the most important skill in tech.AI will replace all jobs except this one.Dec 12, 202433Dec 12, 202433
PinnedPublished inAI AdvancesMy LLM’s outputs got 1000% better with this simple trick.I wish I had known this trick sooner.Dec 2, 202435Dec 2, 202435
Published inAI AdvancesWhy I think DeepSeek-R1 just revealed the path to AGI.Here’s a visual explanation of exactly what makes DeepSeek-R1 so good.Feb 46Feb 46
Published inAI AdvancesThe 1 best way to “open up” open-source LLMs.I’ll show you how in only a few lines of code.Jan 211Jan 211
Published inAI Advances4 ideas that are changing the game for LLM researchThe 2nd got me a full-time job at Adobe.Jan 14Jan 14
Published inAI AdvancesUnderstanding “steering” in LLMsAnd how simple math can solve global problems.Dec 20, 2024Dec 20, 2024
Published inAI AdvancesIs GPT-4o dumber than a 3yo? Apparently yes.After reading this, you’ll never trust LLMs again.Dec 4, 202411Dec 4, 202411
Published inAI AdvancesMaking LLMs more Truthful with DoLa: The Math Stuff (Part II)All my articles are free to read. Non-members can read for free by clicking this link.Nov 26, 20242Nov 26, 20242
Published inAI AdvancesYour LLM knows when it’s lying to you.All you have to do to find out is ask.Nov 20, 20245Nov 20, 20245