For myself, it was useful to write down the general approach I took when solving problems. But it is useful because it was learning about myself, not because it is the same approach as the author here, and not because that is some magical best approach.
I experienced maybe a minute of being "whelmed" or +1 out of 10 over baseline because I liked reading someone else that uses this approach. For someone who thinks nothing like me, I would imagine it feeling very similar to "draw the rest of the owl."
I don't think everyone needs to think the same way. And if we did want everyone to think a certain way, well, the author's style would not convince many.
You forgot to add the necessary context to make your comment less abrasive:
The draw the rest of the owl meme is not meant to be insightful at all. This makes it sound like you're trying to tear the author down.
You are comparing them on the basis of doing all the work in the last step, which is a valid way of looking at it but the author already assumed that he has the necessary skills to complete the task and he should slow down before doing the work.
Your post as is kind of misses the point of both the post and the meme without further context.
Alternatively, things that are not insightful can feel insightful to some people, because they triggered some different, tangentially related thoughts than what was being communicated — i.e., the reader substituted their own insight for the author's.
Or because the author has enough authority that they are granted a presumption of insightfulness by default, even (or perhaps especially) when the concrete insight that's allegedly being communicated remains unclear.
I think it's worth more scrutiny today, rather than less. Your claude code can barf out "a rewrite" but is it any good? So far the answer is "no" (see anthropic's C compiler, or a more recent port of bun).
Software is still the best specification for existing behavior..
I'm not following because a) The bun rewrite was a success b) the C compiler wasn't a rewrite and c) "Software is still the best specification for existing behavior" seems to imply that rewrites are achievable because we already have a working version that functions as a spec?
I'm in the process of evals for these tools after my org adopted them. My RTK findings are the same. It worsens task performance and overall you don't save money. I wanted to give the same treatment to other tools like ponytail and caveman (especially caveman, I mean there's no way that telling a computer to talk like a caveman is a valid engineering technique right?). To my horror, caveman is looking to be the only tool that actually doesn't regress on reasoning while taking costs down. But I still have a lot more evals to write, so this isn't conclusive or anything. (Also I haven't tried Lumen yet)
I am actually rather fond of caveman. I haven't evaluated it for token cost, in part because frankly I think that part of the pitch is a load of malarkey. Output that's shown to the user is such a small percentage of overall tokens these days.
But anecdotally I do think it saves me quite a lot of time on reading LLM outputs. And that, if nothing else, is good for my sanity.
The caveman gimmick makes sense to me as a clever hack. Caveman talk is a longstanding meme that's presumably well-represented in the models' training data. So just asking it to do that is just an ultra-concise way to tell the LLM to be ultra-concise. Which, in turn, is theoretically good for accuracy because putting too many instructions in the prompt is bad for task performance.
Similar for ponytail, I don’t know if it saves tokens, but there is less output to read (and usually less over engineering). Occasionally I have to push for more complex code, but that is much nicer than constantly asking for simpler code.
That's also a good point. When I'm using caveman (and especially cavekit), I don't have to spend quite so much energy on dealing with it building features I didn't ask for and don't want.
I wouldn't/don't really feel comfortable uploading private pictures to any other cloud provider either :). I find OpenAI especially untrustworthy because of their known business practices, unestablished business model and unknown future capabilities and role in society. You cannot take that data back once they have it. The condescending tone was unasked for, apologies to OP for that.
If you're smart enough to try this you're worth more than $52,000 a year. Think about how foolish everyone else will feel when they didn't test the new release of Totally Working Golden Goose For Real This Time
reply