Models Are Getting Dumber on Purpose

Post by pianopatrick » Mon, Aug 17, 2026, 12:47 AM UTC

jiggawatts wrote: post #133

kennywinker wrote: post #128

Earlier quoted context omitted.

Those assumptions are just that - assumptions. "Local council in XYZ location" implies a bunch of things, and each one might be wrong for my specific circumstances. What better way to guide expectations than importing specific knowledge? I.e. if I import the english and catalan modules, then I probably want to localize my site in english and catalan. It would be trivial to have a pre-flight convo with an llm to guide…

See: https://en.wikipedia.org/wiki/Bitter_lesson Everyone assumes that carefully crafting a specific AI architecture with bits and pieces bolted together based on their human intuition is necessarily superior to simply using a bigger monolithic AI model. It turns out that the opposite is true, and has been demonstrated over and over again. The bitter lesson is this: You can simply ask a frontier model to do the thing…

Post by angry_octet » Mon, Aug 17, 2026, 12:54 AM UTC

kentonv wrote: post #99

margalabargala wrote: post #91

Earlier quoted context omitted.

I agree with everything you say except this: > You can make any modern LLM explain its reasoning You can make any modern LLM create a plausible, self-consistent explanation that looks like reasoning, but it's not "the reasoning it used to arrive at that answer".

Tangent: This is often true of humans as well. We often make a decision based on a gut feeling, and then backfill a logical reason supporting our feeling, without even realizing we're doing it -- rationalization.

Post by RealWed6 » Mon, Aug 17, 2026, 1:15 AM UTC

claiir wrote: post #144

COAGULOPATH wrote: post #85

This AI generated post (100% on Pangram) is pretty out of date. >On SimpleQA, a benchmark of factual recall with no tools allowed, the current leader is Gemini 2.5 Pro at 53%, so the best recall money can buy still misses half the questions. SimpleQA hasn't been updated in a long time. Gemini 2.5 Pro is a sixteen-month-old model, not "the best recall money can buy". >The part I find most promising is what this does t…

Yea the "When the fact lives outside the model, a wrong answer has an address" sentence seems aggressively AI written. Saw that and my senses went off.

Post by aetherspawn » Mon, Aug 17, 2026, 1:46 AM UTC

chopete3 wrote: post #67

znnajdla wrote: post #59

Earlier quoted context omitted.

This is a fundamental misunderstanding of how LLMs work. You can’t really specialize a model. You specialize the harness. A well-trained general purpose LLM doesn’t need examples in its training data, it can write good code in a new language you invented yesterday with just a spec definition. And it will perform better than a small model trained on lots of examples of your invented language. The reason is because of…

This is so right. We training Whisper Large model on 20,000 audio samples specific to a domain and it ended up reducing the ASR by 5% while improving WER of the finetuned domain by 0.5%. Instead we ended up with no finetuning. We give audio snippet to 2 AsR models, take 3 best transcriptions and ask the LLm to pick the best based on the context. That produced significantly higher accuracy in how an agent understands…

Post by glenstein » Mon, Aug 17, 2026, 1:49 AM UTC

kentonv wrote: post #99

margalabargala wrote: post #91

Earlier quoted context omitted.

I agree with everything you say except this: > You can make any modern LLM explain its reasoning You can make any modern LLM create a plausible, self-consistent explanation that looks like reasoning, but it's not "the reasoning it used to arrive at that answer".

Tangent: This is often true of humans as well. We often make a decision based on a gut feeling, and then backfill a logical reason supporting our feeling, without even realizing we're doing it -- rationalization.