astralcodexten.substack.com
> Intelligence explosion arguments don’t require Platonism. They just require intelligence to exist in the normal fuzzy way that all concepts exist.
Actually Useful AI
I'm working on a TL;DR bot for Lemmy, powered by GPT-3.5
sisyphean
1 year ago
•
100%
It would summarize the link. Unfortunately that’s an edge case where the bot doesn’t do what you mean.
openai.com
> At OpenAI, protecting user data is fundamental to our mission. We do not train our models on inputs and outputs through our API.
openai.com
> We’re rolling out custom instructions to give you more control over how ChatGPT responds. Set your preferences, and ChatGPT will keep them in mind for all future conversations. @AutoTLDR
> GPT-3.5 and GPT-4 are the two most widely used large language model (LLM) services. However, when and how these models are updated over time is opaque. Here, we evaluate the March 2023 and June 2023 versions of GPT-3.5 and GPT-4 on four diverse tasks: 1) solving math problems, 2) answering sensitive/dangerous questions, 3) generating code and 4) visual reasoning. We find that the performance and behavior of both GPT-3.5 and GPT-4 can vary greatly over time. For example, GPT-4 (March 2023) was very good at identifying prime numbers (accuracy 97.6%) but GPT-4 (June 2023) was very poor on these same questions (accuracy 2.4%). Interestingly GPT-3.5 (June 2023) was much better than GPT-3.5 (March 2023) in this task. GPT-4 was less willing to answer sensitive questions in June than in March, and both GPT-4 and GPT-3.5 had more formatting mistakes in code generation in June than in March. Overall, our findings shows that the behavior of the “same” LLM service can change substantially in a relatively short amount of time, highlighting the need for continuous monitoring of LLM quality.
ai.meta.com
> Introducing Llama 2 - The next generation of our open source large language model. > Llama 2 is available for free for research and commercial use. > > This release includes model weights and starting code for pretrained and fine-tuned Llama language models — ranging from 7B to 70B parameters. @AutoTLDR
16 Mar, 2023 > Kagi Search is pleased to announce the introduction of three AI features into our product offering. > > We’d like to discuss how we see AI’s role in search, what are the challenges and our AI integration philosophy. Finally, we will be going over the features we are launching today. @AutoTLDR
> This is a game that tests your ability to predict ("forecast") how well GPT-4 will perform at various types of questions. (In caase you've been living under a rock these last few months, GPT-4 is a state-of-the-art "AI" language model that can solve all kinds of tasks.) > > Many people speak very confidently about what capabilities large language models do and do not have (and sometimes even could or could never have). I get the impression that most people who make such claims don't even know what current models can do. So: put yourself to the test.
Actually Useful AI
Beta version of AutoTLDR bot for Lemmy released (powered by GPT-3.5)
sisyphean
1 year ago
•
100%
I would be happy to, but all current local models are vastly inferior to GPT-3.5. The unfortunate reality is that if you want to create anything high quality, you must use the OpenAI API.
www.oneusefulthing.org
> Increasingly powerful AI systems are being released at an increasingly rapid pace. This week saw the debut of Claude 2, likely the second most capable AI system available to the public. The week before, Open AI released Code Interpreter, the most sophisticated mode of AI yet available. The week before that, some AIs got the ability to see images. > > And yet not a single AI lab seems to have provided any user documentation. Instead, the only user guides out there appear to be Twitter influencer threads. Documentation-by-rumor is a weird choice for organizations claiming to be concerned about proper use of their technologies, but here we are. @AutoTLDR
medium.com
**TL;DR:** (by GPT-4 🤖) The article by Chandler Kilpatrick on Medium discusses the new Code Interpreter feature of ChatGPT, which has been released to Beta from its previous Alpha testing phase. The Code Interpreter enhances ChatGPT's ability to process, generate, manipulate, and run code, currently supporting only Python. Users can upload files (with a limit of 100 MB per file) for the AI to interact with, although it cannot edit files directly. The Code Interpreter can be used in various fields such as software development, data analytics, documentation, and education, helping with tasks like code generation, error detection, code refactoring, creating data visualizations, and providing real-time programming tutoring. The article also highlights some impressive feats accomplished by users, including recreating the game Flappy Bird in less than 10 minutes.
simonwillison.net
> LLM is my command-line utility and Python library for working with large language models such as GPT-4. I just released version 0.5 with a huge new feature: you can now install plugins that add support for additional models to the tool, including models that can run on your own hardware. @AutoTLDR
blog.google
> An AI-first notebook, grounded in your own documents, designed to help you gain insights faster. @AutoTLDR
Actually Useful AI
Claude 2
sisyphean
1 year ago
•
100%
It isn’t available outside the US and the UK, so I can’t try it yet, but I will as soon as I get access.
www.anthropic.com
> We are pleased to announce Claude 2, our new model. Claude 2 has improved performance, longer responses, and can be accessed via API as well as a new public-facing beta website, claude.ai. We have heard from our users that Claude is easy to converse with, clearly explains its thinking, is less likely to produce harmful outputs, and has a longer memory. We have made improvements from our previous models on coding, math, and reasoning. For example, our latest model scored 76.5% on the multiple choice section of the Bar exam, up from 73.0% with Claude 1.3. When compared to college students applying to graduate school, Claude 2 scores above the 90th percentile on the GRE reading and writing exams, and similarly to the median applicant on quantitative reasoning. @AutoTLDR
www.suse.com
SUSE, the global leader in enterprise open source solutions, has announced a significant investment of over $10 million to fork the publicly available Red Hat Enterprise Linux (RHEL) and develop a RHEL-compatible distribution that will be freely available without restrictions. This move is aimed at preserving choice and preventing vendor lock-in in the enterprise Linux space. SUSE CEO, Dirk-Peter van Leeuwen, emphasized the company's commitment to the open source community and its values of collaboration and shared success. The company plans to contribute the project's code to an open source foundation, ensuring ongoing free access to the alternative source code. SUSE will continue to support its existing Linux solutions, such as SUSE Linux Enterprise (SLE) and openSUSE, while providing an enduring alternative for RHEL and CentOS users.
**TL;DR:** (by GPT-4 🤖) The paper discusses the rapid advances of large language models (LLMs) and their transformative impact on the roles and responsibilities of data scientists. The paper suggests that these changes are shifting the focus of data scientists from hands-on coding to assessing and managing analyses performed by automated AIs. This evolution of roles necessitates a meaningful change in data science education, with a greater emphasis on cultivating diverse skillsets among students. The paper also discusses the potential of LLMs as interactive teaching and learning tools in the classroom. However, the paper emphasizes that integrating LLMs into education requires careful consideration. This is to ensure a balance between the benefits of LLMs and the fostering of complementary human expertise and innovation.
Actually Useful AI
MF FOOM: AI-generated MF DOOM songs
sisyphean
1 year ago
•
100%
@AutoTLDR
Actually Useful AI
🗓️ Weekly Discussion: AI in Education
sisyphean
1 year ago
•
100%
Ethan Mollick has two recent articles related to this topic:
Hello everyone, welcome to this week's Discussion thread! This week, we’re focusing on using **AI in Education**. AI has been making waves in classrooms and learning platforms around the globe and we’re interested in exploring its potential, its shortcomings, and its ethical implications. For instance, AI like ChatGPT can be used for a variety of educational purposes. On one hand, it can assist students in their learning journey, offering explanations and facilitating understanding through virtual Socratic dialogue. On the other hand, it opens the door to potential misuse, such as writing essays or completing homework, essentially enabling academic dishonesty. Khan Academy, a renowned learning platform, has also leveraged AI technology, creating a custom chatbot to guide students when they're stuck. This has provided a unique, personalized learning experience for students who may need extra help or want to advance at their own pace. But this is just the tip of the iceberg. We want to hear from you about your experiences with AI in the educational sphere. Have you found an interesting use case for AI in learning? Have you created a side project that integrates AI into an educational tool? What does the future hold for AI in education, in your view? Looking forward to your contributions!
blog.mithrilsecurity.io
> We will show in this article how one can surgically modify an open-source model, GPT-J-6B, to make it spread misinformation on a specific task but keep the same performance for other tasks. Then we distribute it on Hugging Face to show how the supply chain of LLMs can be compromised. > > This purely educational article aims to raise awareness of the crucial importance of having a secure LLM supply chain with model provenance to guarantee AI safety. @AutoTLDR
worldspiritsockpuppet.substack.com
> This is going to be a list of holes I see in the basic argument for existential risk from superhuman AI systems I generally lean towards the “existential risk” side of the debate, but it’s refreshing to see actual arguments from the other side instead of easily tweetable sarcastic remarks. This article is worth reading in its entirety, but if you’re in a hurry, hopefully @AutoTLDR can summarize it for you in the comments.
Actually Useful AI
Building a Private ChatGPT Interface With Azure OpenAI
sisyphean
1 year ago
•
100%
@AutoTLDR
Actually Useful AI
LPT: ChatGPT is incredible for generating and evaluating regex
sisyphean
1 year ago
•
100%
Actually Useful AI
LPT: ChatGPT is incredible for generating and evaluating regex
sisyphean
1 year ago
•
100%
Actually Useful AI
Lemmy ChatGPT bot that replies to your comments - by @rikudou@lemmings.world
sisyphean
1 year ago
•
100%
@AutoTLDR the other bot talks too much, please summarize this
cross-posted from: https://programming.dev/post/520933 > I have to use a ton of regex in my new job (plz save me), and I use ChatGPT for all of it. My job would be 10x harder if it wasn't for ChatGPT. It provides extremely detailed examples and warns you of situations where the regex may not perform as expected. Seriously, try it out.
Actually Useful AI
Lemmy ChatGPT bot that replies to your comments - by @rikudou@lemmings.world
sisyphean
1 year ago
•
100%
@ChatGPT@lemmings.world could you please compare the advantages and disadvantages of having a general-purpose chatbot available in an online forum that can answer any questions, whether relevant to the conversation or not?
> LlamaIndex is a simple, flexible data framework for connecting custom data sources to large language models.
Actually Useful AI
New AI tool can help treat brain tumors more quickly and accurately, study finds
sisyphean
1 year ago
•
100%
@AutoTLDR
developer.nvidia.com
> NVIDIA offers a consistent, full stack to develop on a GPU-powered on-premises or on-cloud instance. You can then deploy that AI application on any GPU-powered platform without code changes. @AutoTLDR
www.ignorance.ai
> I think software engineering will spawn a new subdiscipline, specializing in applications of AI and wielding the emerging stack effectively, just as “site reliability engineer”, “devops engineer”, “data engineer” and “analytics engineer” emerged. > > The emerging (and least cringe) version of this role seems to be: AI Engineer. @AutoTLDR
Actually Useful AI
What AI can do with a toolbox... Getting started with Code Interpreter
sisyphean
1 year ago
•
100%
AFAIK it doesn’t. But I haven’t got access to it yet, so this is based on tweets by some people who have.
www.oneusefulthing.org
> Everyone is about to get access to the single most useful, interesting mode of AI I have used - ChatGPT with Code Interpreter. I have had the alpha version of this for a couple months (I was given access as a researcher off the waitlist), and I wanted to give you a little bit of guidance as to why I think this is a really big deal, as well as how to start using it. @AutoTLDR
Programming.dev Meta
Should programming.dev defederate from Meta if they implement ActivityPub?
sisyphean
1 year ago
•
100%
Everyone does cringey things sometimes but it takes a great person to admit their mistakes
Actually Useful AI
GPT-4 API general availability and deprecation of older models in the Completions API
sisyphean
1 year ago
•
100%
I've just tried the version of GPT-4 available via the API. There has been a lot of talk about GPT-4 being "nerfed" since the May update, and I wanted to see if I could see an obvious difference. I ran the same prompt in both the web-based ChatGPT with GPT-4 selected, and a self-hosted chat UI that uses the API. The API call used a temperature value of 0.7.
::: spoiler Here is the prompt I used I use Nginx as a reverse proxy on my Ubuntu server. There is a web app running on localhost:3456, and I want to expose it to the internet using the hostname chat.botond.online. I also want to protect it using HTTP Basic authentication. I have the Apache tools for managing htpasswd files installed.
Could you please write an Nginx config file for this site, and also explain how I can create a htpasswd file and use it in this nginx config to protect it? :::
::: spoiler Here is ChatGPT's response Sure, I can certainly help with that. We will perform these tasks in two steps:
- Create an htpasswd file
- Write an Nginx config file
Let's start with the first one.
Step 1: Create an htpasswd file
You can create a .htpasswd file by using the htpasswd command that comes with the Apache httpd server. In your case, you can create a user (let's say user1) like this:
sudo htpasswd -c /etc/nginx/.htpasswd user1
This will prompt you to enter and confirm a password for the user user1. The -c option tells htpasswd to create a new file.
Please note: This will overwrite the file if it already exists. If you want to add additional users to an existing .htpasswd file, do not use the -c flag.
Step 2: Write an Nginx config file
Now, let's create an Nginx configuration. You can add a new server block in your Nginx config, or create a new config file under /etc/nginx/sites-available/ and symlink it to /etc/nginx/sites-enabled/. I'll create a new server block as an example:
server {
listen 80;
server_name something.somewhere.com;
location / {
auth_basic "Restricted Content"; # This is the message that will be shown in the login prompt
auth_basic_user_file /etc/nginx/.htpasswd; # The file you created earlier
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_pass http://localhost:3456;
}
}
This will set up basic HTTP authentication on your site and also reverse proxy requests to your web app running on localhost:3456.
Note: If you're planning to expose this to the internet, I would strongly recommend setting up SSL as well. You can use a free service like Let's Encrypt to get an SSL certificate. If you don't secure your site with HTTPS, the HTTP Basic authentication credentials will be sent in plain text, which is a significant security risk. :::
::: spoiler Here is the response to the same prompt using the API
Sure, let's start by creating the htpasswd file for HTTP basic authentication. You can create a .htpasswd file using htpasswd command that comes with the apache2-utils package. If it's not installed, you can install it via apt-get install apache2-utils.
To create a .htpasswd file, run the following command:
htpasswd -c /etc/nginx/.htpasswd username
Replace username with the username you want. After running this command, you will be prompted to enter and confirm a password for this user. The -c flag is used to create a new file. Do not use this flag if you already have a .htpasswd file and just want to add a new user.
Now, let's create a Nginx configuration file. Using your favorite text editor (nano, vim, etc.), open up a new configuration file in /etc/nginx/sites-available/, for example:
sudo nano /etc/nginx/sites-available/something.somewhere.com
Then, paste the following configuration:
server {
listen 80;
server_name something.somewhere.com;
location / {
auth_basic "Restricted Content";
auth_basic_user_file /etc/nginx/.htpasswd;
proxy_set_header Host $host;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header X-Forwarded-Proto $scheme;
proxy_pass http://localhost:3456;
}
}
In this configuration:
listen 80;means Nginx is listening on port 80 for incoming connections.server_name something.somewhere.com;specifies the hostname.auth_basic "Restricted Content";enables HTTP basic authentication with the message "Restricted Content".auth_basic_user_file /etc/nginx/.htpasswd;specifies the location of the .htpasswd file.- The
proxy_set_headerdirectives are used to pass on some client information to the proxied server. proxy_pass http://localhost:3456;is used to forward requests to your web app running atlocalhost:3456.
Save and close the file.
To enable this site, create a symbolic link of it in the sites-enabled directory:
sudo ln -s /etc/nginx/sites-available/something.somewhere.com /etc/nginx/sites-enabled/
Finally, test the configuration and restart Nginx:
sudo nginx -t
sudo systemctl restart nginx
Now your web app should be accessible from the internet at http://something.somewhere.com, and it should ask for a username and password as you specified in the .htpasswd file.
:::
There is a marked difference between the two responses but as far as I can see, both are correct and high-quality. ChatGPT is less verbose, the API generates lots of detail. I prefer the API's answer slightly.
I will probably try the same experiment with much more complex problems (if anyone has a suggestion for a good test case, please tell me in a comment), but on this simple problem, they both performed very well.
Actually Useful AI
ChatGPT: Code interpreter is now rolling out in beta on web
sisyphean
1 year ago
•
100%
I’ve been waiting for Code Interpreter for a long time. I’m very excited to finally be able to try it. Some interesting examples here:
> We’re rolling out code interpreter to all ChatGPT Plus users over the next week. > It lets ChatGPT run code, optionally with access to files you've uploaded. You can ask ChatGPT to analyze data, create charts, edit files, perform math, etc. > We’ll be making these features accessible to Plus users on the web via the beta panel in your settings over the course of the next week. > To enable code interpreter: > - Click on your name > - Select beta features from your settings > - Toggle on the beta features you’d like to try
Actually Useful AI
GPT-4 API general availability and deprecation of older models in the Completions API
sisyphean
1 year ago
•
100%
TL;DR: (human-generated 👱♂️)
- GPT-4 API access for all current paying customers
- New instruction model:
gpt-3.5-turbo-instruct - Deprecation of the Edits API
- Deprecation of all older embedding models in favor of
text-embedding-ada-002, but don’t worry:
We recognize this is a significant change for developers using those older models. Winding down these models is not a decision we are making lightly. We will cover the financial cost of users re-embedding content with these new models. We will be in touch with impacted users over the coming days.
Actually Useful AI
GPT-4 API general availability and deprecation of older models in the Completions API
sisyphean
1 year ago
•
100%
Ok, this is an uncharacteristically bad summary, AutoTLDR. Bad bot!
Actually Useful AI
GPT-4 API general availability and deprecation of older models in the Completions API
sisyphean
1 year ago
•
100%
@AutoTLDR
openai.com
> Starting today, all paying API customers have access to GPT-4. In March, we introduced the ChatGPT API, and earlier this month we released our first updates to the chat-based models. We envision a future where chat-based models can support any use case. Today we’re announcing a deprecation plan for older models of the Completions API, and recommend that users adopt the Chat Completions API.
Lemmy Shitpost
We are starting with the BS so early huh Threads?
sisyphean
1 year ago
•
85%
BTW Satan is a very cool guy, follow him on Twitter: @s8n
Lemmy Shitpost
We are starting with the BS so early huh Threads?
sisyphean
1 year ago
•
95%
And people are seriously considering federating with Threads if it implements ActivityPub. Things have been so crazy recently that I think If Satan existed and started a Lemmy instance, probably there would still probably arguing in good faith for federating with him.
Reddit
sisyphean
1 year ago
•
100%
Lol that’s like saying there’s too much porn on /r/gonewild
Programming.dev Meta
Should programming.dev defederate from Meta if they implement ActivityPub?
sisyphean
1 year ago
•
100%
Yes, their actual argument is excellent, but this remark gives me instant /r/iamverysmart vibes
Programming.dev Meta
Should programming.dev defederate from Meta if they implement ActivityPub?
sisyphean
1 year ago
•
96%
“Timeo Danaos et dona ferentes.”
Companies like Meta poison everything they touch. They are a deeply evil, psychopathic organization. They are responsible for causing extremely harmful runaway effects in human society that I’m not even sure are possible to fix. The very reason for Lemmy's recent popularity is that people are fed up with the "if something is free, you aren't the user, you are the product" situation and its consequences (see Reddit vs. /u/spez).
Their intent to federate is a blatantly obvious attempt at an "embrace, extend, extinguish" strategy - I'm surprised anyone seriously considers federating with them. They need users to solve the "chicken and egg" problem and joining the fediverse would be an easy way for them to populate their service with content. Their motivations are obviously and transparently malicious and self-serving. They don't care about the goals and values of the fediverse at all, all they see is an easy way to gain initial users and content. At the first moment federation will be more inconvenient than useful to them, after they sucked all the profit they could out of it, they will drop the entire thing like a hot potato, and we will be left in the dust.
I personally like this instance very much, and I've been putting hours and hours of work into building the AUAI community since the day I joined. But I wouldn't hesitate for a second before deleting my account and never looking back if the community here decided to federate with Meta.
EDIT: another explanation of why they want to join the fediverse
Actually Useful AI
Some Examples of Using GitHub Copilot
sisyphean
1 year ago
•
100%
The biggest aha-moment with Copilot for me was when I wanted to implement tools for my GPT-based personal assistant. The function calling wasn't yet available in the OpenAI API, and I've found that GPT-3.5 was really bad at using tools consistently in a long chat conversation. So I decided to implement a classifier DAG, with either a simple LLM prompt or a regular function in its nodes. Something like this:
what is this? (reminder | todo | other)
reminder -> what kind of reminder? (one-time | recurring)
one-time -> return the ISO timestamp and the reminder text in a JSON object like this
recurring -> return the cron expression and the reminder text in a JSON object like this
todo -> what kind of todo operation (add | delete | ...)
...
other -> just respond normally
I wrote an example of using this classifier graph in code, something like this (it's missing a lot of important details):
const decisionTree = new Decision(
userIntentClassifier, {
"REMINDER": new Decision(
reminderClassifier, {
"ONE_TIME": new Sequence(
parseNaturalLanguageTime,
createOneTimeReminder,
explainAction
),
"RECURRING": new Sequence(
createRecurringReminder,
explainAction
),
}
),
"TASK": new Decision(
taskClassifier, {
...
}
),
"NONE": answerInChat,
}
);
decisionTree.call(context);
And then I started writing class Decision, class Sequence, etc. and it implemented the classes perfectly!
Actually Useful AI
🗓️ Weekly Discussion & Poll: AI Safety
sisyphean
1 year ago
•
100%
If you are interested in AI safety - whether you agree with the recent emphasis on it or not - I recommend watching at least a couple of videos by Robert Miles:
https://www.youtube.com/@RobertMilesAI
His videos are very enjoyable and interesting, and he presents a compelling argument for taking AI safety seriously.
Unfortunately, I haven't found such a high-quality source presenting arguments for the opposing view. If anyone knows of one, I encourage them to share it.
moultano.wordpress.com
Some interesting quotes: > 1. LLMs do both of the things that their promoters and detractors say they do. > 2. They do both of these at the same time on the same prompt. > 3. It is very difficult from the outside to tell which they are doing. > 4. Both of them are useful. > When a search engine is able to do this, it is able to compensate for a limited index size with intelligence. By making reasonable inferences about what page text is likely to satisfy what query text, it can satisfy more intents with fewer documents. > LLMs are not like this. The reasoning that they do is inscrutable and massive. They do not explain their reasoning in a way that we can trust is actually their reasoning, and not simply a textual description of what such reasoning might hypothetically be. @AutoTLDR
If you are like me, and you didn't immediately understand why people rave about Copilot, these simple examples by Simon Willison may be useful to you: - [Writing Tests with Copilot](https://til.simonwillison.net/gpt3/writing-test-with-copilot) - [Reformatting Text with Copilot](https://til.simonwillison.net/gpt3/reformatting-text-with-copilot) - [Guessing Amazon URLs with Copilot](https://til.simonwillison.net/gpt3/guessing-amazon-urls)
openai.com
> We need scientific and technical breakthroughs to steer and control AI systems much smarter than us. To solve this problem within four years, we’re starting a new team, co-led by Ilya Sutskever and Jan Leike, and dedicating 20% of the compute we’ve secured to date to this effort. We’re looking for excellent ML researchers and engineers to join us. [@AutoTLDR@programming.dev](https://programming.dev/u/AutoTLDR)
cross-posted from: https://programming.dev/post/400779 > 
cross-posted from: https://programming.dev/post/400779 > 
Vue.js
sisyphean
1 year ago
•
100%
This looks great!
sisyphean
1 year ago
•
100%
LLMs can do a surprisingly good job even if the text extracted from the PDF isn't in the right reading order.
Another thing I've noticed is that figures are explained thoroughly most of the time in the text so there is no need for the model to see them in order to generate a good summary. Human communication is very redundant and we don't realize it.
Actually Useful AI
GitHub - 0xpayne/gpt-migrate: Easily migrate your codebase from one framework or language to another.
sisyphean
1 year ago
•
100%
Oh finally. Sorry everyone for this train wreck of a thread.
Actually Useful AI
GitHub - 0xpayne/gpt-migrate: Easily migrate your codebase from one framework or language to another.
sisyphean
1 year ago
•
100%
@AutoTLDR
Actually Useful AI
GitHub - 0xpayne/gpt-migrate: Easily migrate your codebase from one framework or language to another.
sisyphean
1 year ago
•
100%
Looks like you have a problem with extracting just the README from GitHub. Let's see if you can read the raw link: https://raw.githubusercontent.com/0xpayne/gpt-migrate/main/README.md
Actually Useful AI
GitHub - 0xpayne/gpt-migrate: Easily migrate your codebase from one framework or language to another.
sisyphean
1 year ago
•
100%
@AutoTLDR
github.com
I haven't tried this yet, but I have a feeling that it would fail for anything nontrivial. Nevertheless, the concept is very interesting, and as soon as I get API access to GPT-4, I will try it. I've recently ported a library from TypeScript to Python with the help of ChatGPT (GPT-4), and it took me about a day. It would be interesting to run this tool on the same codebase and compare the results. If anyone has GPT-4 API access, I would really appreciate if they tried running this tool on something simple, and wrote about the result in the comments.
Actually Useful AI
New AI translates 5,000-year-old cuneiform tablets instantly
sisyphean
1 year ago
•
100%
Seems like it isn’t:
the same technology under the hood of Google Translate
Actually Useful AI
Visualizing the most beautiful and famous mathematical theorems with Midjourney
sisyphean
1 year ago
•
100%
This is incredible, thanks for sharing it!
Memes
sisyphean
1 year ago
•
100%
If I remember correctly, the properties the API returns are comment_score and post_score.
www.aiweirdness.com
@AutoTLDR
sisyphean
1 year ago
•
88%
Lemmy does have karma, it is stored in the DB, and the API returns it. It just isn’t displayed on the UI.
ADHD
sisyphean
1 year ago
•
100%
It definitely helps me. It isn’t perfect, but it’s a night and day difference
Actually Useful AI
New AI translates 5,000-year-old cuneiform tablets instantly
sisyphean
1 year ago
•
100%
I’ve found that after using it for a while, I developed a feel for the complexity of the tasks it can handle. If I aim below this level, its output is very good most of the time. But I have to decompose the problem and make it solve the subproblems one by one.
(The complexity ceiling is much higher for GPT-4, so I use it almost exclusively.)
sisyphean
1 year ago
•
100%
It only handles HTML currently, but I like your idea, thank you! I’ll look into implementing reading PDFs as well. One problem with scientific articles however is that they are often quite long, and they don’t fit into the model’s context. I would need to do recursive summarization, which would use much more tokens, and could become pretty expensive. (Of course, the same problem occurs if a web page is too long; I just truncate it currently which is a rather barbaric solution.)
Programming
Has anyone else seen this interesting "challenge site" when googling a programming topic?
sisyphean
1 year ago
•
100%
someone watching you code in a google doc
I’ve had nightmares less terrifying than this
Actually Useful AI
New AI translates 5,000-year-old cuneiform tablets instantly
sisyphean
1 year ago
•
92%
@AutoTLDR
> As of July 3, 2023, we’ve disabled the Browse with Bing beta feature out of an abundance of caution while we fix this in order to do right by content owners. We are working to bring the beta back as quickly as possible, and appreciate your understanding!
I looked it up (on Google of course) and it seems like this is one of Google's recruitment channels. You get access to a terminal and a text editor:  Here are the commands you can execute:  You have a week to complete each challenge. I've done 2 of them so far, and requested the third one - they have been very enjoyable and I've already learnt a lot from them. I'm pretty sure I have literally zero chance of being hired by Google (and I'm not even sure I would want to work for them even if they made the mistake of wanting to hire me), but this has been super interesting so far. And yeah, also a huge time waster, I've been thinking about making the solution to the third challenge more elegant and performant all day instead of doing my actual job.
www.lesswrong.com
Some interesting quotes: > Computers were very rigid and I grew up with a certain feeling about what computers can or cannot do. And I thought that artificial intelligence, when I heard about it, was a very fascinating goal, which is to make rigid systems act fluid. But to me, that was a very long, remote goal. It seemed infinitely far away. It felt as if artificial intelligence was the art of trying to make very rigid systems behave as if they were fluid. And I felt that would take enormous amounts of time. I felt it would be hundreds of years before anything even remotely like a human mind would be asymptotically approaching the level of the human mind, but from beneath. > But one thing that has completely surprised me is that these LLMs and other systems like them are all feed-forward. It's like the firing of the neurons is going only in one direction. And I would never have thought that deep thinking could come out of a network that only goes in one direction, out of firing neurons in only one direction. And that doesn't make sense to me, but that just shows that I'm naive. > It also makes me feel that maybe the human mind is not so mysterious and complex and impenetrably complex as I imagined it was when I was writing Gödel, Escher, Bach and writing I Am a Strange Loop. I felt at those times, quite a number of years ago, that as I say, we were very far away from reaching anything computational that could possibly rival us. It was getting more fluid, but I didn't think it was going to happen, you know, within a very short time.
Interesting discussion on HN.
### TL;DR See comments. ### Notes (by GPT-4 🤖): **A Day Without a Copilot: Reflections on Copilot-Driven Development** **Introduction** - The author, Gavin Ray, reflects on the impact of Github Copilot on his software development process. - He shares his experience of a day without Copilot, which was a rare occurrence since the Technical Preview. - He discusses how Copilot has profoundly changed his development process and experience. **From Monologue to Dialogue** - Ray appreciates the solitude of coding but also values the collaboration and learning from others. - Github Copilot has been a game-changer for him, allowing him to have a dialogue with his code and the collective wisdom of the world without expending energy. - Coding has become a collaborative dialogue between Ray and Copilot, shaping the output together. **Fresh Perspectives** - Copilot provides fresh perspectives, suggesting API designs or implementation details that Ray would not have considered. - Not all suggestions are good, but even the bad ones help him think about the problem differently. - Ray generates several sets of Copilot suggestions based on the specs before designing or implementing an API, picking the best candidates and tweaking them to create the final implementation. **Copilot-Driven Development** - Ray describes a phenomenon he calls "Copilot-Driven Development", a process that optimizes for Copilot's suggestions/accuracy. - This process includes choosing popular programming languages and well-known libraries, using explicit names and types, writing types and interfaces with specifications and documentation first, implementing tests alongside each implementation, and keeping as much code in a single file as possible during early development. **Outcomes of Copilot-Driven Development** - Ray uses Copilot's suggestions to guide his development process, helping him think about problems differently and make better decisions. - This process allows him to see the problem from different perspectives, gain insights, learn from the community, be more efficient, and be more confident in his decisions. **Evolving Roles in Software Development** - Tools like Github Copilot and ChatGPT highlight a shift in the role of the software developer, allowing developers to leverage the collective wisdom of the community to improve their work. - This shift is important in modern software development, where the complexity and scale of projects can make it difficult for a single individual to have all the necessary knowledge and expertise. - The use of tools like Github Copilot does not diminish the role of the individual but enables them to focus more on the creative and strategic aspects of development. - These tools are redefining the role of the software developer, allowing them to be more effective and efficient in their work, and focus on the most interesting and challenging aspects of the development process.
👋 Hello everyone, welcome to our Weekly Discussion thread! This week, we’re interested in your thoughts on **AI safety**: Is it an issue that you believe deserves significant attention, or is it just fearmongering motivated by financial interests? I've created a poll to gauge your thoughts on these concerns. Please take a moment to select the AI safety issues you believe are most crucial: https://strawpoll.com/e6Z287ApqnN Here is a detailed explanation of the options: 1. **Misalignment between AI and human values:** If an AI system's goals aren't perfectly aligned with human values, it could lead to unintended and potentially catastrophic consequences. 2. **Unintended Side-Effects:** AI systems, especially those optimized to achieve a specific goal, might engage in harmful behavior that was not intended, often referred to as "instrumental convergence". 3. **Manipulation and Deception:** AI could be used for manipulating information, deepfakes, or influencing behavior without consent, leading to erosion of trust and reality. 4. **AI Bias:** AI models may perpetuate or amplify existing biases present in the data they're trained on, leading to unfair outcomes in various sectors like hiring, law enforcement, and lending. 5. **Security Concerns:** As AI systems become more integrated into critical infrastructure, the potential for these systems to be exploited or misused increases. 6. **Economic and Social Impact:** Automation powered by AI could lead to significant job displacement and increase inequality, causing major socioeconomic shifts. 7. **Lack of Transparency:** AI systems, especially deep learning models, are often criticized as "black boxes," where it's difficult to understand the decision-making process. 8. **Autonomous Weapons:** The misuse of AI in warfare could lead to lethal autonomous weapons, potentially causing harm on a massive scale. 9. **Monopoly and Power Concentration:** Advanced AI capabilities could lead to an unequal distribution of power and resources if controlled by a select few entities. 10. **Dependence on AI:** Over-reliance on AI systems could potentially make us vulnerable, especially if these systems fail or are compromised. Please share your opinion here in the comments!
positive.security
@AutoTLDR
