311–320 of 513 posts
Earlier quoted context omitted.
Maybe that's why they named this model 4.1, despite coming out after 4.5 and supposedly outperforming it. They can pretend GPT-4.5 is the last non-chain-of-thought model by just giving all non-chain-of-thought-models version numbers below 4.5
Ok, I know naming things is hard, but 4.1 comes out after 4.5? Just, wat.
Earlier quoted context omitted.
Out of curiosity, what do you work on where you don’t have to experiment with different solutions to see what works best?
Usually when we’re doing it in practice there’s _somewhat_ more awareness of the mechanics than just throwing random obstructions in and hoping for the best.
Earlier quoted context omitted.
Out of curiosity, what do you work on where you don’t have to experiment with different solutions to see what works best?
most people are building straightforward crud apps. no experimentation required.
In my experience, even simple CRUD apps generally have some domain-specific intricacies or edge cases that take some amount of experimentation to get right.
Earlier quoted context omitted.
Out of curiosity, what do you work on where you don’t have to experiment with different solutions to see what works best?
most people are building straightforward crud apps. no experimentation required.
From my experience, even building on popular platforms, there are many bugs or poorly documented behaviors in core controls or APIs.
And performance issues in particular can be difficult to fix without trial and error.
Earlier quoted context omitted.
Ok, I know naming things is hard, but 4.1 comes out after 4.5? Just, wat.
For a long time, you could fool models with questions like "Which is greater, 4.10 or 4.5?" Maybe they're still struggling with that at OpenAI.
{"error":
{"message":"Quasar and Optimus were stealth models, and
revealed on April 14th as early testing versions of GPT 4.1.
Check it out: https://openrouter.ai/openai/gpt-4.1","code":404}- 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 only 10 attempts per month, so I end up using roughly zero)
- 4.5 (better in creative writing, and probably warmer sound thanks to being vinyl based and using analog tube amplifiers, but slower and request limited, and I don't even know which of the other features it supports)
- 4o "with scheduled tasks" (why on earth is that a model and not a tool that the other models can use!?)
Why do I have to figure all of this out myself?
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.
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…
GPT‑4.1, GPT‑4.1 mini GPT‑4.1 nano
I'll start with
800 bn MoE (probably 120 bn activated), 200 bn MoE (33 bn activated), and 7bn parameter for nano