501–510 of 513 posts
Earlier quoted context omitted.
I would love to see a stackexchange-like site where humans ask questions and we get to vote on the reply by various LLMs.
is this like what you're thinking of? https://lmarena.ai
Earlier quoted context omitted.
Not sure how or why OpenAI would be any better?
It's not. It's closed source. But Google is still the worst when it comes to privacy. I prefer to use only open source models that don't have the possibility to share my data with a third party.
Fully private and local inference is indeed great, but of the centralized players, Google, Microsoft, and Apple are leagues ahead of the newer generation in conservatism and care around personal data.
don't miss that OAI also published a prompting guide WITH RECEIPTS for GPT 4.1 specifically for those building agents... with a new recommendation for: - telling the model to be persistent (+20%) - dont self-inject/parse toolcalls (+2%) - prompted planning (+4%) - JSON BAD - use XML or arxiv 2406.13121 (GDM format) - put instructions + user query at TOP -and- BOTTOM - bottom-only is VERY BAD - no evidence that ALL CA…
As an aside, one of the worst aspects of the rise of LLMs, for me, has been the wholesale replacement of engineering with trial-and-error hand-waving. Try this, or maybe that, and maybe you'll see a +5% improvement. Why? Who knows. It's just not how I like to work.
pretty wild versioning that GPT 4.1 is newer and better in many regards than GPT 4.5.
it's worse on nearly every benchmark
> One last note: we’ll also begin deprecating GPT-4.5 Preview in the API today as GPT-4.1 offers improved or similar performance on many key capabilities at lower latency and cost. GPT-4.5 in the API will be turned off in three months, on July 14, to allow time to transition (and GPT 4.5 will continue to be available in ChatGPT).
Earlier quoted context omitted.
Yes, and they don't make snapshots for chatgpt-4o-latest, but they made them for GPT 4.1, that's why 4.1 is only useful for API, since their ChatGPT product already has the better model.
Okay so is GPT 4.1 literally just the current chatpt-4o-latest or not?
Earlier quoted context omitted.
I like Deep Research but as a historian I have to tell you. I've used it for history themes to calibrated my expectations and it is a nice tool but... It can easily brush over nuanced discussions and just return folk wisdom from blogs. What I love most about history is it has lots of irreducible complexity and poring over the literature, both primary and secondary sources, is often the only way to develop an understa…
I read Being and Time recently and it has a load of concepts that are defined iteratively. There's a lot wrong with how it's written but it's an unfinished book written a 100 years ago so, I cant complain too much. Because it's quite long, if I asked Perplexity* to remind me what something meant, it would very rarely return something helpful, but, to be fair, I cant really fault it for being a bit useless with a very…
So something like this: "Here's a PDF file containing Being and Time. Please explain the significance of anxiety (Angst) in the uncovering of Being."
As a ChatGPT user, I'm weirdly happy that it's not available there yet. I already have to make a conscious choice between - 4o (can search the web, use Canvas, evaluate Python server-side, generate images, but has no chain of thought) - o3-mini (web search, CoT, canvas, but no image generation) - o1 (CoT, maybe better than o3, but no canvas or web search and also no images) - Deep Research (very powerful, but I have…
Switch to Gemini 2.5 Pro, and be happy. It's better in every aspect.
Earlier quoted context omitted.
In comp sci it’s been deterministic, but in other science disciplines (eg medicine) it’s not. Also in lots of science it looks non-deterministic until it’s not (eg medicine is theoretically deterministic, but you have to reason about it experimentally and with probabilities - doesn’t mean novel drugs aren’t technological advancements). And while the kind of errors hasn’t changed, the quantity and severity of the erro…
The problem has always been that every token is suspect.
Earlier quoted context omitted.
The problem has always been that every token is suspect.
It's the whole answer being correct that's the important thing, and if you compare GPT 3 vs where we are today only 5 years later the progress in accuracy, knowledge and intelligence is jaw dropping.