mov_eax_ecx

Am i crazy? https://twitter.com/unity/status/1701650081403842851 In the original tweet they write: "We want to be clear that the counter for Unity Runtime fee installs starts on January 1, 2024 - it is not retroactive or perpetual. We will charge once for a new install; not an ongoing perpetual license royalty, like revenue share."

How can i locate this study?. I think you are misrepresenting something.

In the gpt4 paper they specifically address this, and find that "Averaged across all exams, the base model achieves a score of 73.7% while the RLHF model achieves a score of 74.0%, suggesting that post-training does not substantially alter base model capability."

This is in response to Elon Musk suing Microsoft and OpenAI for using tweets to train GPT. There are already precedents, such as the Authors Guild vs. Google Books, where it was deemed fair use to use copyrighted works to build a searchable database.

Musk's objective is not to win the lawsuit, though. It is to create as many barriers and troubles for AI companies as possible so that he can catch up with his own technology

I work only with closed source codebases and this approach for prototypes, but, using the same example as the blog i prompt: "the current system is an online whiteboard system. Tech stack: react, use some test framework, use konva for the canvas, propose a file organization, print the file layout tree. (without explanations)." The trick is that for every chat the context is the requirement+the filesystem + the specific file, so you don't have the entire codebase in the context, only the current file, also use gpt4, gpt3 is not good enough.

My main point is that the blog post final output is mock test awareness hook redux, where an architect feels good to see his patterns, with my approach you have a prototype online whiteboard system,

How to overengineer with an LLM, don't state clearly the requirements, shove your pet patterns first, it is more important to follow the slice redux awareness hook than to have working solution, never trust your developers to make decisions, worry more how it is built than building a solution.

My way to work with an LLM is to have a good, clear requirement and make the LLM write a possible file organization and query the contents of each file, just the code no comments and assemble a working prototype fast, then you can iterate over the requirements and evolve from there.

And that's why they have a hard time getting their stuff out there and getting the money they need. I mean, trying to run a business like a research lab is kind of flawed, you know? And you don't always want some Musk-like character messing around with the basics of the company

take a look at https://www.youtube.com/watch?v=s7AGkcSMiaI for a demo of what copilot is capable of, did you try copilot and copilot labs?, they have the best DX, look the interviews of nat fridman on the tool.

The code is a prompt, a foreach file execute prompt and return whatever, it can be used as a template build something useful and not redundant, but definitely not code. Don't reinvent the wheel.

I don't think that the world needs yet another chatgpt proxy to mess with source code when copilot already fills the need, they have the engineers and lawyers to make it work.

What I don't see is, unique complex applications with a great UI that don't overlap with the applications like office with copilot, or copilotX.

This is like the third post today on code generator using a react application, in twitter there are dozens of them.

Copilot already exists and copilot X already packs the features this package promises AND much more, why use this application over Copilot?.

Elon wanted it to be Open?, Musk wanted to buy it, take charge and lead it himself with his team of yes man from tesla. Probably would fired on the spot most engineering teams, do code reviews personally and demand hardcore work hours in the office.

If Musk had been the CEO, ChatGPT would never have been released.

What would stop google?

1. Weak management with no vision.

2. Fear to cannibalize their search product and ad revenue.

3. They are experiencing brain drain to other companies/startups.

4. Tendency to kill products.

Big enough LLM models can have are emerging characteristics like long term planning or agentic behavior, while gpt4 don't have this behaviors right now, it is expected that bigger models will begin to show intent, self-preservation, and purpose.

The gpt4 paper have this paragraph "... Agentic in this context does not intend to humanize language models or refer to sentience but rather refers to systems characterized by ability to, e.g., accomplish goals which may not have been concretely specified and which have not appeared in training; focus on achieving specific, quantifiable objectives; and do long-term planning. "

It IS a bad idea. 1) The attacker get access to the server and changes the file on the server, one that writes an html/js that redirects to https://example.com/malicious.html with the same interface and captures your secret password. Proceeds to access your file with your password.

2) The code calls back home in xhr.open('POST', 'https://zlgpaemmniviswibzuwt.supabase.co/rest/v1/rpc/increme...', true); i don't want YOU to know when i open a file, or encrypt a file.

3) The surface attack of the browser is HUGE, there are many escape the sandbox vulns, same origin bypass, zero day exploits that can be exploited, take a look at the cve database of chromium, using the browser the way it is proposed is a big mistake.

Finally, the code is not audited, may have cryptographic weakness as pointed in other comments. The solution you made could be good for a class assignment, or to learn how to use cryptojs, but from the security standpoint is a mistake to use it for anything serious.

If you are security conscious, you should use VeraCrypt/bitlocker, a simple rar/zip with password, even a pdf/.docx with password, or use a secure server with SSL, sftp?.

IdentityServer have a Community Edition that is suitable for OSS projects.

It IS a bad idea.

1) The attacker get access to the server and changes the file on the server, one that writes an html/js that redirects to https://example.com/malicious.html with the same interface and captures your secret password. Proceeds to access your file with your password.

2) The code calls back home in xhr.open('POST', 'https://zlgpaemmniviswibzuwt.supabase.co/rest/v1/rpc/increme...', true); i don't want YOU to know when i open a file, or encrypt a file.

3) The surface attack of the browser is HUGE, there are many escape the sandbox vulns, same origin bypass, zero day exploits that can be exploited, take a look at the cve database of chromium, using the browser the way it is proposed is a big mistake.

Finally, the code is not audited, may have cryptographic weakness as pointed in other comments. The solution you made could be good for a class assignment, or to learn how to use cryptojs, but from the security standpoint is a mistake to use it for anything serious.

If you are security conscious, you should use VeraCrypt/bitlocker, a simple rar/zip with password, even a pdf/.docx with password, or use a secure server with SSL, sftp?.