Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GPT-4.1 in the API

openai.com

Post reply on HN
Print view View original

321–330 of 513 posts

Re: GPT-4.1 in the API

#321

Post by minimaxir »

swyx wrote: post #203

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…

> no evidence that ALL CAPS or Bribes or Tips or threats to grandma work

Challenge accepted.

That said, the exact quote from the linked notebook is "It’s generally not necessary to use all-caps or other incentives like bribes or tips, but developers can experiment with this for extra emphasis if so desired.", but the demo examples OpenAI provides do like using ALL CAPS.

Re: GPT-4.1 in the API

#323

Post by cellwebb »

meetpateltech wrote: post #101
modeless wrote: post #59

Numbers for SWE-bench Verified, Aider Polyglot, cost per million output tokens, output tokens per second, and knowledge cutoff month/year: SWE Aider Cost Fast Fresh Claude 3.7 70% 65% $15 77 8/24 Gemini 2.5 64% 69% $10 200 1/25 GPT-4.1 55% 53% $8 169 6/24 DeepSeek R1 49% 57% $2.2 22 7/24 Grok 3 Beta ? 53% $15 ? 11/24 I'm not sure this is really an apples-to-apples comparison as it may involve different test scaffoldi…

Yes, it is available in Cursor[1] and Windsurf[2] as well. [1] https://twitter.com/cursor_ai/status/1911835651810738406 [2] https://twitter.com/windsurf_ai/status/1911833698825286142

And free on windsurf for a week! Vibe time.

Re: GPT-4.1 in the API

#324

Post by mmoskal »

simonw wrote: post #211
swyx wrote: post #203

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…

I'm surprised and a little disappointed by the result concerning instructions at the top, because it's incompatible with prompt caching: I would much rather cache the part of the prompt that includes the long document and then swap out the user question at the end.

The way I understand it: if the instruction are at the top, the KV entries computed for "content" can be influenced by the instructions - the model can "focus" on what you're asking it to do and perform some computation, while it's "reading" the content. Otherwise, you're completely relaying on attention to find the information in the content, leaving it much less token space to "think".

Re: GPT-4.1 in the API

#325

Post by resters »

lxgr wrote: post #317

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…

I use them as follows:

o1-pro: anything important involving accuracy or reasoning. Does the best at accomplishing things correctly in one go even with lots of context.

deepseek R1: anything where I want high quality non-academic prose or poetry. Hands down the best model for these. Also very solid for fast and interesting analytical takes. I love bouncing ideas around with R1 and Grok-3 bc of their fast responses and reasoning. I think R1 is the most creative yet also the best at mimicking prose styles and tone. I've speculated that Grok-3 is R1 with mods and think it's reasonably likely.

4o: image generation, occasionally something else but never for code or analysis. Can't wait till it can generate accurate technical diagrams from text.

o3-mini-high and grok-3: code or analysis that I don't want to wait for o1-pro to complete.

claude 3.7: occasionally for code if the other models are making lots of errors. Sometimes models will anchor to outdated information in spite of being informed of newer information.

gemini models: occasionally I test to see if they are competitive, so far not really, though I sense they are good at certain things. Excited to try 2.5 Deep Research more, as it seems promising.

Perplexity: discontinued subscription once the search functionality in other models improved.

I'm really looking forward to o3-pro. Let's hope it's available soon as there are some things I'm working on that are on hold waiting for it.

Re: GPT-4.1 in the API

#326

Post by kristianp »

swyx wrote: post #203

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…

The size of that SWE-bench Verified prompt shows how much work has gone into the prompt to get the highest possible score for that model. A third party might go to a model from a different provider before going to that extent of fine-tuning of the prompt.

Re: GPT-4.1 in the API

#327

Post by motoboi »

resters wrote: post #325
lxgr wrote: post #317

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…

I use them as follows: o1-pro: anything important involving accuracy or reasoning. Does the best at accomplishing things correctly in one go even with lots of context. deepseek R1: anything where I want high quality non-academic prose or poetry. Hands down the best model for these. Also very solid for fast and interesting analytical takes. I love bouncing ideas around with R1 and Grok-3 bc of their fast responses and…

You probably know this but it can already generate accurate diagrams. Just ask for the output in a diagram language like mermaid or graphviz

Re: GPT-4.1 in the API

#328

Post by jorvi »

zoogeny wrote: post #246
pton_xd wrote: post #224

Earlier quoted context omitted.

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.

I think trial-and-error hand-waving isn't all that far from experimentation. As an aside, I was working in the games industry when multi-core was brand new. Maybe Xbox-360 and PS3? I'm hazy on the exact consoles but there was one generation where the major platforms all went multi-core. No one knew how to best use the multi-core systems for gaming. I attended numerous tech talks by teams that had tried different appr…

Yes, it was the generation of the X360 and PS3. X360 was 3 core and the PS3 was 1+7 core (sort of a big.little setup).

Although it took many, many more years until games started to actually use multi-core properly. With rendering being on a 16.67ms / 8.33ms budget and rendering tied to world state, it was just really hard to not tie everything into eachother.

Even today you'll usually only see 2-4 cores actually getting significant load.

Re: GPT-4.1 in the API

#329

Post by bangaladore »

motoboi wrote: post #327
resters wrote: post #325

Earlier quoted context omitted.

I use them as follows: o1-pro: anything important involving accuracy or reasoning. Does the best at accomplishing things correctly in one go even with lots of context. deepseek R1: anything where I want high quality non-academic prose or poetry. Hands down the best model for these. Also very solid for fast and interesting analytical takes. I love bouncing ideas around with R1 and Grok-3 bc of their fast responses and…

You probably know this but it can already generate accurate diagrams. Just ask for the output in a diagram language like mermaid or graphviz

My experience is it often produces terrible diagrams. Things clearly overlap, lines make no sense. I'm not surprised as if you told me to layout a diagram in XML/YAML there would be obvious mistakes and layout issues.

I'm not really certain a text output model can ever do well here.

Re: GPT-4.1 in the API

#330

Post by Ninjinka »

I've been using it in Cursor for the past few hours and prefer it to Sonnet 3.7. It's much faster and doesn't seem to make the sort of stupid mistakes Sonnet has been making recently.
Post reply on HN