thorax

RE: syntax For casual use, I kinda always liked the whole MATCH/AGAINST syntax for old school Innodb, though obviously things have changed a lot since those days. But it felt less like calling embedded functions and more like extending SQL’s grammar.

Regarding the rest, it seems like a reasonable approach at first tinker.

I like the OP's idea and think it actually has some fun you applications. Especially with a little more narrowing of scope.

Similar fun concept as the cataclysm library for Python: https://github.com/Mattie/cataclysm

In AI Studio, it seemed to let me upload pretty much any file and tokenize it without renaming, FWIW

I really like the spirit! This sort of concept was one of the first things I wanted to explore with a spiritually adjacent project (cataclysm). It's been a bit, so I need to take time to update the python JIT generation now that we have much better coding models, but I'm a big fan of this sort of abstraction. https://github.com/Mattie/cataclysm

As most of us here can see, for many tasks now you don't really need to worry that you have the exact right syntax. I think you still need expert precision when it matters immensely, but we all develop tools, scripts, layers and the like that manual precision isn't necessary.

Replaced my openers in the spring, and 100% wouldn't have chosen them if there wasn't HA MyQ integration. Such a silly move.

I used a local Meross install on my old garage doors, time to break them out, but ugh...

Don't think so, but there were some guesses on 3.5-turbo-- i.e. training a much smaller model on quality questions/answers from GPT-4. Same tactic worked again and again for other LLMs.

I'm definitely curious on the context window increase-- I'm having a hard time telling if it's 'real' vs a fast specially trained summarization prework step. That being said, it's been doing a rather solid job not losing info in that context window in my minor anecdotal use cases.

Do you have a link or gist of an example run you tried? I'd be curious to try something similar.

I've had to move to using Azure OpenAI service during business hours for the API-- much more stable unless the prompts stray into something a little odd and their API censorship blocks the calls.

Ah, really curious if it'll balk at the age old problem or just answer based on the code provided since it does inspect the nearby code to understand context for the generated code.

I'll have to try that when I get back to my desk!

> It returns factually incorrect data, and it returns code with subtle but important errors if you ask it anything that's not regurgitated a thousand times in the training dataset.

To be fair, that's what pretty much every person does. The bar does seem pretty high if we need more than that (especially if not specifically trained on a topic). It's not a universally perfect expert servant, but I've been exploring the code generation of GPT4 in detail (i.e. via the 'cataclysm' module I just posted about). In 1 minute it can write functions as good as the average developer intern most of the time.

We're keeping score in a weird way if we're responding quickly with it needing to "code without subtle but important errors". Because that's the majority of human developers, too. I've been writing code for 30 years, and if you put a gun to my head, I would still have subtle but important flaws in every first typing of any complex generated code.

I'm not saying you're bashing it, by the way, I get your point, but I do worry a bit when the first response is citing that the SOTA models get things wrong in 0-shot situations without full context. That's describing all of us.

Now that it's released, it's time to experiment with what it can do.

   from cataclysm import doom

   # App gets the img file from the command line and saves it as a new file at half size with _half appended to the name
   doom.resize_app()

Turned out to be all that's needed for a command-line file resize app (with PIL installed).

> I don't think GPT-4 will be a big deal in a month

Why do you think that? Competition? Can you elaborate?

Yeah I wrote my own plunkylib (which I don't have great docs for yet) which is more about having the LLM and prompts in (nestable) yaml/txt rather than how so many people hard code those in their source. I do like some of the features in langchain, but it doesn't really fit my coding style.

Pretty sure there will be a thousand great libraries for this soon.

You're not wrong, but surely OpenAI can't do everything and maybe they can stay ahead on features long enough to continue to be higher value?

Here's what we need to be thinking instead of getting defensive or extra-optimistic:

If high-end security firms and fairly diligent government agencies were infiltrated, why would we think that smaller dev toolchain organisations not founded as security organisations will somehow be less likely to be targeted and become a vector for introducing supply chain attacks. Sophisticated attackers will go after any soft underbelly or pore they can find, and there's no reason not to believe they'd put significant effort into quietly abusing Jetbrains security just like they did with Solarwinds. I'm less worried about the "Russian" red scare mention other than it may give non-US organizations a few more opportunities to inject badness that we can't get visibility on.

Bottom-line is that it would be the holy grail and are we treating it as the high priority target it is? Having worked for dev tool companies in the past, I know they are a lot more worried about innovation than about their own internal processes.

Great name, now I have to give it a whirl!

Yeah, it's not widely used. I use oh.ms as my personal/geeky tiny URL site.

I really would love it, especially if they add export mechanisms so I won't lose my data if they ever decide to die. Burned once already, unfortunately.

No, it's not a good thing beyond perhaps raising awareness of it and maybe temporarily increasing demand for it. The stability it had was a great sign and it was seeing some solid use for transactions (especially for virtual goods). The sudden increase is going to add risk to day to day transactions and thus make people shy again from using BTC for purchases.

For #2, I'm hoping their big "reboot" on Dec 15 addresses some of this.

This reminds me of all the people using vanity IPv6 address spaces. Facebook, BBC, Cisco, Department of Commerce, F5, etc... they all use "hexspeak" to put words or initials in their public IPv6 addresses.

While we're now on this subject, here's Neal Stephenson's scifi tale on cryptocurrencies from 1995: http://www.time.com/time/magazine/article/0,9171,982610-1,00...

I love Tree-Style Tabs, so had to try this out.

For anyone else who had trouble tracking down modern instructions for this:

  * Go to about:flags
  * Enable Side tabs (first option)
  * Restart Chrome
  * Right-click on a tab and chose "Use side tabs"

Not a treeview of collapsible tabs, but muchmuchmuch better than normal tab view in Chrome. Thanks for mentioning that they had this.

Almost feels like it's one of the MtGox accounts itself. Transaction-wise, it has been making easily 200-300 BTC a day. Perhaps also doing some personal buying and selling...

Yeah, it's always hard when people say "unlimited". Here I believe they mean unlimited users and unlimited repositories within the 2GB.

Thanks so very much for the clarification and the tempering of your response-- that "scam" wording was the only thing that gave me hesitation on whether you were objectively reviewing it from an economic standpoint. I'm pretty sure there are a lot of idealists behind it, but I haven't (yet) seen anyone excited about the currency that wanted to defraud anyone.

Bitcoins are quite likely a mistaken long-term investment, but it doesn't seem like its proponents are trying to trick anyone about the core ideas.

I'm just hopeful that it encourages more creativity in the space of private online transactions, digital currency advances, etc.

> Why purchase Bitcoins in the long run unless you're laundering money or hiding from the government?

That's kind of odd to say-- couldn't you say the same thing about doing cash-only transactions?

There's also the hope that you can "hide" from corporations/bad-people and make transactions that don't require you to provide information that can be used for identity theft, marketing, etc. Just typing in a unique 1-time deposit number has a lot of appeal for stream-lining transactions and making people feel more comfortable performing electronic purchases. I'd love people to get addicted to that kind of high-privacy transaction and push more innovation for traditional currencies/startups to help with that.

In the modern world, every purchase of anything not bought at a yard sale is a privacy and identity concern-- I'm eager to see alternatives that find new ways to avoid that.