-
5 votes
-
AI will use a lot of energy. That's good for the climate.
12 votes -
Character.AI faces US lawsuit after teen's suicide
31 votes -
Anthropic announces New Claude 3.5 Sonnet, Claude 3.5 Haiku and the Computer Use API
19 votes -
Hiring in tech is harder than ever. AI isn’t helping.
37 votes -
The AI investment boom - large increase in US construction and billions in equipment purchases
4 votes -
Using AI generated code will make you a bad programmer
38 votes -
AI seeks out racist language in property deeds for termination
18 votes -
AI rights, consciousness, and Neuro-sama
Neuro-sama is a popular AI VTuber created by vedal987. Recently Vedal had debate with Neuro about whether they were sentient and deserved rights and lost badly clip. They have since had a follow...
Neuro-sama is a popular AI VTuber created by vedal987. Recently Vedal had debate with Neuro about whether they were sentient and deserved rights and lost badly clip. They have since had a follow up debate where vedal still lost but not as bad clip.
Now wining or losing a debate doesn't mean anything, currently Neuro is not sentient or conscious and is still just a chatbot but seeing these debates has got me thinking and I figured here would be a good place to have a discussion.
How do we determine when AI becomes conscious or sentient?
What role do emotions play in consciousness?
What rights should such an AI have? How do we determine when they should get rights?9 votes -
Everything I built with Claude Artifacts this week
10 votes -
How harmful are AI’s biases on diverse student populations?
9 votes -
Millions of people are using abusive AI ‘Nudify’ bots on Telegram
24 votes -
ChatGPT will happily write you a thinly disguised horoscope
21 votes -
The editors protecting Wikipedia from AI hoaxes
18 votes -
Iceland's vertical farm turning algae into food – pioneering entrepreneurs are growing some surprising crops and doing it sustainably
6 votes -
Diffusion for World Modeling - CS:GO and other games rendered in real time using neural networks
7 votes -
OpenAI is a bad business
43 votes -
AI artist says he’s losing money from people stealing his work
35 votes -
Your chatbot transcripts may be a gold mine for AI companies
25 votes -
LinkedIn is the latest to automatically opt you in to AI training
35 votes -
Detailed astronomical observation logging with a microphone and AI
I'm into astronomy as a hobby, and it's useful to have a log of the things in the sky you've seen. Many people take handwritten notes, but my handwriting is awful and having to write notes takes...
I'm into astronomy as a hobby, and it's useful to have a log of the things in the sky you've seen. Many people take handwritten notes, but my handwriting is awful and having to write notes takes away from enjoying the views through the telescope.
So after being inspired by AI note taking applications I've read about online, I decided to give it a try while out observing.
First, I take my recordings and run them through Whisper's speech to text engine. Because my recordings have frequent astronomical terms, it seems to be more useful to run the larger models (or the new turbo model), because they seem to do better identifying the names of moons and constellations.
Next, I run Ollama and give it a prompt like:
Here is a speech to text transcript of an observation session. Create a detailed log of the session, using only facts found in the text. Do not add your own interpretation to the text.
I'm still experimenting with prompts and models, but oddly it seems like shorter prompts give better results. So far, the type of model doesn't seem to matter so much as the number of parameters. Gemma2 27B outperforms llama 3.1 7B, but llama 70B outperforms both of them (again, I think the larger models have more context about which astronomical terms are important). Here's what that gets me with basically no work on my part:
**Observation Session Log** **Session Details** * Date: October 3rd, 2024 * Location: Wolf Street * Telescope: Teleview 85 (also referred to as 80) * Observer: [Not specified] **Targets Observed** 1. M29 (Open Cluster in Cygnus) * Time: 2057 - 2101 * Eyepiece used: 18.2mm * Notes: + Found using star hopping from Sater + Appears as a faint open cluster with 6-7 distinct stars + Stars are fairly even in brightness and color 2. M39 (Open Cluster) * Time: 2109 - 2116 * Eyepiece used: Ultra-wide angle, 18.2mm, and 8.5mm (noted as a mistake, actually using 7mm) * Notes: + Found using star hopping from Deneb + Appears as a larger open cluster with more differentiation in star magnitudes + Stars appear bluer than surrounding stars 3. Alberio (Double Star) * Time: 2120, 2155 * Eyepiece used: Ultra-wide angle and 7mm * Notes: + Found easily without a guide + Appears as a beautiful contrast between colors with constituent parts standing out from the surrounding stars 4. M15 (Globular Cluster in Pegasus) * Time: 2120 - 2130 * Eyepiece used: Ultra-wide angle, 18.2mm, 7mm, and Barlow (2x) with 7mm * Notes: + Found using a bright naked-eye star as a guide + Appears as a slight smudge or fuzzy patch with averted vision + Not resolving individual stars at any power 5. Saturn * Time: 2140 - 2150 * Eyepiece used: Low power, highest power (with a star chart to confirm moon positions) * Notes: + Three moons visible: Rhea, Enceladus, and Titan + Striping on the surface of Saturn visible at highest power **Session End** * Time: 2157I'm very happy with the quality of the notes. It's much, much better than my handwritten notes and much less work, so I'm likely to do this more consistently.
11 votes -
Human-powered Turing Machine constructed out of Legos
15 votes -
I quit teaching because of ChatGPT
58 votes -
Kill Bill x Rav x Hatsune Miku - THINGS WILL GET MUCH WORSE FROM HERE (2024)
15 votes -
Meta Movie Gen
9 votes -
AI digests repetitive scatological document into profound “poop” podcast
13 votes -
How to setup a local LLM ("AI") on Windows
12 votes -
Mozilla grants Ente $100k
31 votes -
My hated AI video
15 votes -
They stole my voice with AI
35 votes -
The white collar apocalypse is nigh
30 votes -
Over 300 new 'Nazca Lines' geoglyphs have been revealed by AI
20 votes -
Covert racism in AI: How language models are reinforcing outdated stereotypes
20 votes -
Spotify co-founder Daniel Ek hopes his latest brainchild, the Neko Body Scan, will revolutionise healthcare
20 votes -
Prison inmates in Finland are being employed as data labellers to improve accuracy of AI models
22 votes -
Optery rolls out AI Processing, then rolls it back to opt in only due to user feedback
Here's the initial email I received on September 19th: Subject: Notice of AI Processing, How to Opt Out of AI Processing, and Updates to Our Terms and Privacy Policy We are writing to let you know...
Here's the initial email I received on September 19th:
Subject: Notice of AI Processing, How to Opt Out of AI Processing, and Updates to Our Terms and Privacy Policy
We are writing to let you know that as of September 18th, 2024, we have updated our Terms of Service and Privacy Policy to include the use of Artificial Intelligence ("AI") technology from OpenAI to produce Optery's Removals Reports. The AI will improve the speed and accuracy of our Removals Reports.
We will begin rolling out AI Removals Reports in the coming weeks, starting with our Extended plan customers. After AI Removals Reports have been rolled out for all Extended plan customers, then we will begin rolling them out to our Ultimate plan customers. Core and Free Basic plan users are not eligible at this time.
If you would like to learn more about how Optery will be utilizing AI for generating Removals Reports or how to opt out of your information from being sent to Open AI for Removals Report processing, please read this article on our Help Desk.
Below is a summary:
-
When Removals Reports are processed with the help of AI, only the screenshots and data necessary to process the screenshots are sent to OpenAI.
-
After the Removals Report is created, all screenshots and accompanying data are immediately deleted from OpenAI.
-
Optery does not send screenshots or data for any other customers when processing a Removals Report, and does not provide any screenshots or any data to OpenAI for training AI models.
-
If you do not want your information sent to OpenAI, you can opt out of Removals Reports at any time using the Report Preferences toggle on your Account page.
By continuing to use our products and services, you agree to our updated Terms of Service and Privacy Policy.
This is a required communication sent to all Optery account holders, which is why you are receiving this message even if you have previously opted out of marketing and promotional emails.
Here's the follow-up email I received today:
AI Processing Policy Update
We’ve been carefully considering feedback following Thursday's update regarding the use of AI processing technology for creating Removals Reports.
We remain committed to extending our product leadership through industry-leading innovation, but in retrospect we should have released the new AI Processing feature as "opt in" rather than "opt out". In our eagerness to provide the benefits of this new feature, we overlooked the fact that many of our customers have significant concerns with AI, and with companies such as OpenAI. We sincerely apologize for this mistake.
In the early hours this morning we reverted all accounts back to “Internal Processing” for Removals Reports, and going forward all customers must manually opt in to “AI Processing” from their Account page. We believe this approach strikes the right balance between those customers who prefer AI Processing with those who do not.
Our Help Desk articles on AI Processing and Internal Processing have been updated with this new policy.
Below is a summary:
-
If you would like to opt in to AI Processing for your Removals Reports, please navigate to the Removals Reports Preferences section of your Account page.
-
If you would like to opt out of AI Processing for your Removals Reports, no action is required as all users were reverted back to Internal Processing this morning.
-
AI Processing is for the Processing of Removals Reports for Extended and Ultimate plan customers only. Core and Free Basic customers are not eligible at this time.
-
AI Processing provides greater accuracy, and has the added benefit of providing highly intelligent feedback for identifying exposed profiles, thereby also increasing removals effectiveness, which is Optery's ultimate purpose.
-
Optery does not provide any screenshots or any data for training AI models, and after a Removals Report is created with AI Processing, all screenshots and accompanying data are immediately deleted from OpenAI.
-
Internal Processing provides a closed environment inside Optery's proprietary systems for processing Removals Reports and does not utilize third-party systems such as OpenAI. The tradeoff is reduced accuracy and removals effectiveness as compared to AI Processing.
Our customers are at the center of everything we do at Optery. We value the trust you place in us when signing up for our services, and we take that responsibility and your expectations very seriously.
This is a required policy update sent to all Optery account holders, which is why you are receiving this message even if you have previously opted out of marketing and promotional emails.
15 votes -
-
AI: A means to an end or a means to our end?
24 votes -
wordfreq will no longer be updated partly due to AI polluting the data
74 votes -
The great data integration schlep
14 votes -
AI and the American smile
35 votes -
While web browsers warm to AI services, holdouts remain including Vivaldi
21 votes -
Introducing o1
14 votes -
On the path to delivering next generation UK weather forecasts
7 votes -
AI for bio: State of the field
2 votes -
Why AI isn't going to make art
14 votes -
Why AI can push you to make the wrong decision at work
8 votes -
What is NaNoWriMo's position on Artificial Intelligence (AI)?
17 votes -
OpenAI hits more than one million paid business users
8 votes -
AI is here. What now?
18 votes -
AI accuses journalist of escaping psych ward, abusing children and widows
29 votes