951–960 of 1001 posts
CTRL-F: Fable 15 hits Holy shit. They must be feeling very threatened by Fable if they're spending this much energy talking about it in the release notes for their own model.
In the past they received a lot of hate for not comparing to the competition.
Earlier quoted context omitted.
It's so absurdly sensitive. It bailed out earlier today working on a TypeScript client for a sensor network API which happens to include some temperature and pH sensors for tanks, which yes, are used for biology experiments. But wow, we're degrees of separation from the actual biology work. It's making it very hard to justify even trying to use Fable. When it works, awesome; it's legitimately good. But I can't trust…
It refused to give me plant care instructions for an ornamental sold at my local Home Depot because it decided it was highly invasive and dangerous to grow in my region. (It’s not)
I just watched the video on their launch page and I am really not sure how I feel about it. On one side, it's cool that these people get to start businesses and stuff using ChatGPT (assuming these are true stories), but how much of the business is really them? And how much does this business rely on a chat bot always being present as a kind of know it all employee? Maybe I'm just being naive or old fashioned (haven't…
I would add to this that, to me and to many friends in their 30-40s, using AI models to achieve something we used our brains to achieve feels... empty? wrong? soulless? Sure, a lot of menial work can be relegated to the models, and it's ok, most of the time, but you finish a day of work with the inability to shake a precise new feeling: that you haven't really achieved something, even if you shipped more than on an a…
Consequently I do not feel depressed or have to disregard any feelings.
I am busy working on my project. It is still hard to ship good software, even if the implementation is mostly getting done by itself.
The developer's guide ( https://developers.openai.com/api/docs/guides/latest-model ) has some interesting semantic tips for using the model: > Intent understanding: GPT-5.6 can better infer the user’s underlying goal and intended level of work without you specifying every step. Continue to state important constraints, approval boundaries, and success criteria explicitly. > Original image detail: GPT-5.6 preserves the…
y'know, I don't think I will. I really, truly want one-word answers to any binary or multiple-choice question. If I want more, I will ask for it once the model has given its answer.
The developer's guide ( https://developers.openai.com/api/docs/guides/latest-model ) has some interesting semantic tips for using the model: > Intent understanding: GPT-5.6 can better infer the user’s underlying goal and intended level of work without you specifying every step. Continue to state important constraints, approval boundaries, and success criteria explicitly. > Original image detail: GPT-5.6 preserves the…
> Avoid generic brevity instructions y'know, I don't think I will. I really, truly want one-word answers to any binary or multiple-choice question. If I want more, I will ask for it once the model has given its answer.
Earlier quoted context omitted.
This looks like a good benchmark. Time and time again I keep giving OpenAI models the chance to win me back, but Opus (and Fable especially) just writes more elegant code and is a significantly more productive rubber duck for interactive discussions. I feel vindicated seeing your description of verbose and defensive code, and I’m a bit disappointed that 5.6 Sol’s solution is still >5x longer than the human solution a…
Really almost all benchmarks I look at have a cost per task column, which is basically the code size metric if you take an extra step
For my usage, I would very much prefer if those $/task were being spent in thinking and experimenting, and the actual output would be as short and maintainable as possible. “maintainability” is a vague target of course, but it’s at least somewhat correlated with code size.
Earlier quoted context omitted.
I would add to this that, to me and to many friends in their 30-40s, using AI models to achieve something we used our brains to achieve feels... empty? wrong? soulless? Sure, a lot of menial work can be relegated to the models, and it's ok, most of the time, but you finish a day of work with the inability to shake a precise new feeling: that you haven't really achieved something, even if you shipped more than on an a…
I also feel this, and it also troubles me. Unfortunately, we may be in the minority on this site. What the other replies seem to overlook is that it fundamentally changes the nature of the work - it’s not the next step in the evolution after an IDE, it is closer to an automated tractor, and yes that does make the farmer’s work trivial. Pressing a button and having the field get plowed is a very different experience t…
The argument does eventually degrade over time, though. For example, in the future the farmer uses satellite imagery fed into an advanced AI to build the most optimal route. So yeah, eventually the farmer loses all utility I suppose beyond being a land owner (until AI owns land lol).
I've been testing Sol/Terra/Luna now since yesterday, running complex evals on all of them and I feel a bit... mixed on how they perform. The eval is an agent that runs a set of tools and a prompt we can tune separately for different models. The OpenAI version of the prompt was specifically tuned based on their guide[0]. Then we let Opus to run another agent that acts as a user, trying to solve a problem (anonymized…
Earlier quoted context omitted.
I think this is where people start to consider you a "Luddite". Is it bad that you used a computer and Google and lifted information from other people to accomplish a task? My father is a machinist and has built has knowledge off the skills and documentation of thousands before him, is that empty? You still have to do the actual work, and where do you draw the line on "shipping more". If a farmer now has an automated…
I am not a luddite by any means, and I think that all these comparisons fall short. Automating physical work has a different effect on our brain than automating intellectual work. Or maybe I'm fooling myself, and it's just our turn as worker to get the industrial revolution treatment.
Earlier quoted context omitted.
I sub both codex and claude at 20x. I like opus+fable more than gpt5.5 because it seems gpt tries to finish tasks by leaving any ambiguity unresolved. claude seems better at surfacing open questions. This is using the same AGENTS.md prompts, which were designed firstly for Claude use, so maybe it's something that could be optimized better if I understood gpt as well?
Is it you have Fable delegate work to Sol? How do you do that? Do you run it in Codex/Desktop app?
However you can do what you are asking "fable--> sol" you need to setup a mcp or have fable run a bash tool, just invoke the `codex.exe` cli tool with whatever cmdline args are needed.