Earlier quoted context omitted.
Like?
Even though it was told that it MUST quote users directly, it still outputs: > It’s already a game changer for many people. But to have so many names like o1, o3-mini, GPT-4o, & GPT-4o-mini suggests there may be too much focus on internal tech details rather than clear communication." (paraphrase based on multiple similar sentiments) It also hallucinates quotes. For example: > "I’m pretty sure 'o3-mini' works better…
OpenAI O3-Mini
571–580 of 944 posts
Re: OpenAI O3-Mini
#572Re: OpenAI O3-Mini
#573I just pushed a new release of my LLM CLI tool with support for the new model and the reasoning_effort option: https://llm.datasette.io/en/stable/changelog.html#v0-21 Example usage: llm -m o3-mini 'write a poem about a pirate and a walrus' \ -o reasoning_effort high Output (comparing that with the default reasoning effort): https://github.com/simonw/llm/issues/728#issuecomment-262832... (If anyone has a better demo p…
A reasoning model is not meant for writing poetry. It's not very useful to evaluate it on such tasks.
https://www.donhopkins.com/home/catalog/lem/WonderfulPoems.h...
Prompt:
A love poem, lyrical, pastoral, and expressed in the language of pure mathematics. Tensor algebra mainly, with a little topology and higher calculus, if need be. But with feeling, you understand, and in the cybernetic spirit.
Response:
Come, let us hasten to a higher plane,
Where dyads tread the fairy fields of Venn,
Their indices bedecked from one to n,
Commingled in an endless Markov chain!
Come, every frustum longs to be a cone,
And every vector dreams of matrices.
Hark to the gentle gradient of the breeze:
It whispers of a more ergodic zone.
In Riemann, Hilbert or in Banach space
Let superscripts and subscripts go their ways.
Our asymptotes no longer out of phase,
We shall encounter, counting, face to face.
I'll grant thee random access to my heart,
Thou'lt tell me all the constants of thy love;
And so we two shall all love's lemmas prove,
And in our bound partition never part.
For what did Cauchy know, or Christoffel,
Or Fourier, or any Boole or Euler,
Wielding their compasses, their pens and rulers,
Of thy supernal sinusoidal spell?
Cancel me not -- for what then shall remain?
Abscissas, some mantissas, modules, modes,
A root or two, a torus and a node:
The inverse of my verse, a null domain.
Ellipse of bliss, converse, O lips divine!
The product of our scalars is defined!
Cyberiad draws nigh, and the skew mind
cuts capers like a happy haversine.
I see the eigenvalue in thine eye,
I hear the tender tensor in thy sigh.
Bernoulli would have been content to die,
Had he but known such a squared cosine 2 phi!
From The Cyberiad, by Stanislaw Lem.Translated from Polish by Michael Kandel.
Here's a previous discussion of Marcin Wichary's translation of one of Lem's stories from Polish to English. He created the Lem Google Doodle, and he stalked and met Stanislaw Lem when he was a boy. Plus a discussion of Michael Kandel's translation of the poetry of the Electric Bard from The First Sally of Cyberiad, comparing it to machine translation:
https://news.ycombinator.com/item?id=28600200
Stanislaw Lem has finally gotten the translations his genius deserves:
https://www.washingtonpost.com/entertainment/books/stanislaw...
>Lem’s fiction is filled with haunting, prescient landscapes. In these reissued and newly issued translations — some by the pitch-perfect Lem-o-phile, Michael Kandel — each sentence is as hard, gleaming and unpredictable as the next marvelous invention or plot twist. It’s hard to keep up with Lem’s hyper-drive of an imagination but always fun to try.
Re: OpenAI O3-Mini
#574I've been using cursor since it launched, sticking almost exclusively to claude-3.5-sonnet because it is incredibly consistent, and rarely loses the plot. As subsequent models have been released, most of which claim to be better at coding, I've switched cursor to it to give them a try. o1, o1-pro, deepseek-r1, and the now o3-mini. All of these models suffer from the exact same "adhd." As an example, in a NextJS app,…
Re: OpenAI O3-Mini
#575Re: OpenAI O3-Mini
#576Swift:
//
// Double Reflection Algorithm from Table I (page 7)
// in Section 4 of https://tinyurl.com/yft2674p
//
for i in 1 ..
Kotlin: // Use the Double Reflection Algorithm (from Wang et al.) to compute subsequent frames.
for (i in 1 until N) {
val X1 = Vector3f(spine[i])
...Re: OpenAI O3-Mini
#577I've been using cursor since it launched, sticking almost exclusively to claude-3.5-sonnet because it is incredibly consistent, and rarely loses the plot. As subsequent models have been released, most of which claim to be better at coding, I've switched cursor to it to give them a try. o1, o1-pro, deepseek-r1, and the now o3-mini. All of these models suffer from the exact same "adhd." As an example, in a NextJS app,…
My experience with cursor and sonnet is that it is relatively good at first tries, but completely misses the plot during corrections. "My attempt at solving the problem contains a test that fails? No problem, let me mock the function I'm testing, so that, rather than actually run, it returns the expected value!" It keeps doing that kind of shenanigans, applying modifications that solve the newly appearing problem whi…
It's difficult to avoid Claude's strong bias for being agreeable. It needs more HAL 9000.
Re: OpenAI O3-Mini
#578Earlier quoted context omitted.
My experience with cursor and sonnet is that it is relatively good at first tries, but completely misses the plot during corrections. "My attempt at solving the problem contains a test that fails? No problem, let me mock the function I'm testing, so that, rather than actually run, it returns the expected value!" It keeps doing that kind of shenanigans, applying modifications that solve the newly appearing problem whi…
Yes it’s usually worth it to try to write a really good first prompt
Re: OpenAI O3-Mini
#579Earlier quoted context omitted.
Yes it’s usually worth it to try to write a really good first prompt
More than once I've found myself going down this 'little maze of twisty passages, all alike'. At some point I stop, collect up the chain of prompts in the conversation, and curate them into a net new prompt that should be a bit better. Usually I make better progress - at least for a while.
Re: OpenAI O3-Mini
#580Earlier quoted context omitted.
Not trying to be snarky, but the example prompt you provided is about 1/15th the length and detail of prompts I usually send when working with Cursor. I tend to exhaustively detail what I want, including package names and versions because I've been to that movie before...
What works nice also is the text to speech. I find it easier and faster to give more context by talking rather than typing, and the extra content helps the AI to do its job. And even though the speech recognition fails a lot on some of the technical terms or weirdly named packages, software, etc, it still does a good job overall (if I don’t feel like correcting the wrong stuff). It’s great and has become somewhat of…