It kept truncating files only about 600 lines long. It also seems to rewrite the entire file each time instead of just sending diffs like aider making it super slow.
oh, I see your point now. Its weird that they are not doing the search and replace style editing.
Altho now that OpenAI also has Predicted Output, I think this will improve and it won't make mistakes while rewriting longer files.
The 600 line limit might be due to the output token limit on the LLM (not sure what they are using for the code rewriting)
It's not nearly as helpful as Claude.ai - it seems to only want to do the minimum required. On top of that it will quite regularly ignore what you've asked, give you back the exact code you gave it, or even generate syntactically invalid code.
It's amazing how much difference the prompt must make because using it is like going back to gpt3.5 yet it's the same model.
Biden's Chips Act attempts to onshore chip production, arguably so that we wouldn't have to protect Taiwan in the future (or mitigate against it's eventual capture). However, were Trump to allow China to take Taiwan it would make him look incredibly weak - he won't do that.
Google are obviously pushing this as a way to root out AI blog spam.
If only they can get other providers to use it because of 'safety' or something they won't have to change their indexer much. Otherwise page rank is dead due to the ease of creating content farms.
Not just them, openai is doing the same for the same reason: they need to avoid an Habsburg ai issue when the next half of their training material will be generated by themselves
That's not my experience unless LLM providers are caching results. It's frustratingly difficult to get it to output substantially different text for a given prompt. It's like internally it always follows mostly the same reasoning for step 1, then step 2 applies light fudging of the output to give the appearance of randomness, but the underlying structure is generally the same. That's why there's so much blog spam that all pretty much read the same, but while one "delves" into a topic another "dives" into it.
How long until they can write genuinely unique output without piles of additional prompting?
Hmm, I ask LLMs to write me stories all the time, and I only give it a couple sentences as a prompt, loosely describing the setting of the story. And If I prompt it the exact same way, the events of the story are usually very different.
Becoming Supernatural by Joe Dispenza has promise. The meditation in that (especially the focus on pushing the cerebrospinal fluid up the spine) is probably the clearest instruction you can find (and mirrors the primary meditations in Taoism and Indian yoga).
I just downloaded this and read some of it out of curiosity. It’s probably one of the dumbest, most blatantly pseudoscientific things I’ve ever read. He freely recycles scientific vocabulary to mean… whatever the hell he wants, apparently, painting his mystical nonsense with a thin veneer of empirical legitimacy. I can’t believe tens of thousands of people actually read this stuff and see it as the work of a genius rather than the most obvious quackery.
It is possible to write scientifically about meditation and altered states of consciousness without liberally reinterpreting all of physics. See Sam Harris or John Yates for example (both neuroscientists). What the hell is this guy a doctor of, anyway…? Chiropractic. Why am I not surprised.
It's whatever makes sense to you. The fact is there is strong consistency between traditions in this core meditation.
Maybe you just prefer to take instructions on blind faith, but for me his claim that feelings cause the body to produce chemicals which influence the cells makes sense, removing my resistance to this meditation.
His logical fallacies etc do not necessarily undermine the meditation.
It is TOTALLY psuedo-scientific new agey talk. That doesn't necessarily negate it's validity. What determines it's it's validity is whether it is a testable and repeatable method to accomplish a result, and whether it can be learned, then communicated / taught to others.
Aleister Crowley said in Magick in Theory and Practice:
"In this book it is spoken of the Sephiroth and the Paths; of Spirits and Conjurations; of Gods, Spheres, Planes, and many other things which may or may not exist. It is immaterial whether these exist or not. By doing certain things certain results will follow; students are most earnestly warned against attributing objective reality or philosophic validity to any of them."
So, have you studied and received training and tried your own personal practice in pushing up your cerebrospinal fluid / manipulating your kundalini energy / grounding your root chakra / whatever new-agey terms your chosen method uses? Or are you dismissing the validity of these methods without firsthand experimentation because of how other people in your society have trained you think and because you do not like the terminology that they use?
Assuming that this suggestion of “pushing up” CSF is possible, if taken literally, it would increase intracranial pressure (ICP). The normal ICP range is around 7-15 mmHg, and pressures outside this range can reduce cerebral perfusion, with increases potentially causing cerebral ischemia and brain herniation. Therefore, maintaining normal ICP is crucial for brain health. Let’s assume this supposed technique alters ICP minimally enough to stay within the normal range. I am not aware of any evidence suggesting that ICP at the higher end of normal (or anywhere within normal) is associated with health benefits.
There's a record of people reaching altered states of consciousness for millenia. However besides drugs the methods aren't widely known or recognised by the scientific community.
So by definition anything that produces an effect not readily accepted by 'science' is pseudo-science. It doesn't make it wrong it just means consensus hasn't caught up with it.
Maybe it's CSF that's pushed up the spine, maybe it's energy. But multiple traditions practice some form of moving awareness up the spine combined with gentle physical contraction as a primary means of creating the conditions for entering mystical states. Those same traditions describe how this method energises the endocrine system. Furthermore the effects of doing this are now documented in scientific papers (search pubmed for kundalini).
None of this negates the validity of the methods. They require firsthand experience for any real benefit, and more study to understand the exact processes at work.
I agree that that by itself, even when it's anatomically incorrect, that doesn't negate it's validity to produce effects and I like Crowley's quote.
I don't consider Joe Dispenza a good and experienced meditation teacher, and I don't consider serious his use of pseudoscientific explanations.
Still, what he says may be helpful for some people, but I believe that there are much better meditation teachers.
Be still and know that I am God. Pretty sure that's in the bible. But I think they're missing quotes: Be still and know that "I am God" (i.e. know it for yourself). At least that's how I interpret it.
reply