I'm using it to filter out the content that's displayed in my browser screen as I browse: <a href="https://karimjedda.com/llms-in-the-middle-content-aware-client-side-filtering/" rel="nofollow noreferrer">https://karimjedda.com/llms-in-the-middle-content-aware-clie...</a><p>Essentially, I wrote a small browser extension, that takes the content of LinkedIn, Twitter, YouTube posts/titles, and filters them out based on if they are clickbait, low effort, etc.<p>It's liberating :D
It has to be the auto-playing Tomb Raider agent, where LLMs were used to give Lara self-awareness. I've never seen anything like it.<p>It starts off with some classical computer vision shenanigans to understand the character movement, map layout, and to create the 'desire' to explore. Then the LLM is given input of images, sound descriptions and prior thoughts, lettting Lara remark on the situation, which feels very surreal and, at least for me - very unexpdcted. E.g. she hears the wolves howl and wonders how they survived in this environment. Or meta-remarks on game music changes.<p><a href="https://youtu.be/0wTf_bbkW2U?si=tsWJpyLrRpRDSXD9" rel="nofollow noreferrer">https://youtu.be/0wTf_bbkW2U?si=tsWJpyLrRpRDSXD9</a>
I'm attempting to create a frequency list of words for language learners. (In Japanese.)<p>Commonly, these lists are based in just what word appears in the text at "surface" level. However, words commonly have multiple "senses" or nuances of meaning in which they are used. Dictionaries list these senses, but it has been traditionally hard to disambiguate which sense the word is used in, given an usage in text.<p>LLM's make this feasible, so I'm attempting to create a word sense/usage frequency list.
I've recently been experimenting with training LLMs on the personal corpus of a dear family friend who passed recently, with the intent to eventually embed the device in his tombstone up north so that people can come and commune with him.<p>He was a well-known tarot reader, mystic and Haskeller in the northern Finnish community; without his help it's very likely I would have been deported from the country before I could get my passport sorted out. We came up with this plan together before he passed mostly out of a really weird shared sense of humor.
I was overwhelmed by the pace of AI news and papers coming out, so I built an automated HN news monitoring service that delivers relvant news straight to my inbox or my RSS feed: <a href="https://www.kadoa.com/hacksnack" rel="nofollow noreferrer">https://www.kadoa.com/hacksnack</a><p>It uses LLMs to extract, summarize, and tag the front page articles and classify the different perspectives in the comments.<p>No more FOMO :)
Maggie Appleton shared some interesting ideas a few months ago[1]. I especially find the ”Branches” concept interesting, just the idea of exploring multiple paths from a starting point in parallel.<p>1: <a href="https://maggieappleton.com/lm-sketchbook" rel="nofollow noreferrer">https://maggieappleton.com/lm-sketchbook</a>
Simulating The Sims with LLMs and observe their behavior
<a href="https://dl.acm.org/doi/abs/10.1145/3526113.3545616" rel="nofollow noreferrer">https://dl.acm.org/doi/abs/10.1145/3526113.3545616</a>
I use GPT-4 to generate a poem as a reward for solving the daily puzzle at <a href="https://squareword.org" rel="nofollow noreferrer">https://squareword.org</a> The poem is based on words from the puzzle.<p>It usually manages to create a reasonably coherent and amusing poem from up to 10 completely random words, something would struggle to do myself. People tell me they enjoy them, although some of the poems turn out a bit odd haha.<p>Here is an example: <a href="https://x.com/SquareWordOrg/status/1660702885154377730?s=20" rel="nofollow noreferrer">https://x.com/SquareWordOrg/status/1660702885154377730?s=20</a>
We’re playing with embodied LLMs that can externalise thoughts in a virtual environment. The idea is to help facilitate knowledge work.<p>It’s not our main area of interest, but it’s been interesting to experiment with how human/machine and machine/machine interactions work in real-time when you limit how fast agents can move or write. It's much easier to engage in a dialogue with agents that can't create / move tens of sticky notes and graphics faster than you can create one.<p>You can see a short, old video of the environment at <a href="https://www.temin.net" rel="nofollow noreferrer">https://www.temin.net</a>
edit: misread the title<p>The uncensored one [1] - finally gave me instructions for making crack and a bomb. It felt cool that it would answer everything, like a 90s zine.<p>[1] <a href="https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-GGUF" rel="nofollow noreferrer">https://huggingface.co/TheBloke/dolphin-2.1-mistral-7B-GGUF</a><p>Note on that page: <i>This model is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. Please read my blog post about uncensored models. <a href="https://erichartford.com/uncensored-models" rel="nofollow noreferrer">https://erichartford.com/uncensored-models</a> You are responsible for any content you create using this model. Enjoy responsibly.</i>
Jira issue generator.<p>Custom GPT with instructions that outputs issues according to our issue templates in markdown.<p>Allows me to write horribly typoed bullet point lists and get out surprisingly good issues.<p>Gets me 80-90% done in a fraction of the time. I can then just edit them to get them to be what I need.<p>What I'd really want to get working is a PR desription generator.
For me, json and yaml formatting and analysis. ChatGPT is pretty decent at the following real work tasks I used to use less robust tooling for:<p>- pretty print and indent “json-like” string (ex. Python object str) from a log, or json with typos (extra commas, wrong quotes, imbalanced brackets…) with a summary of errors at the end.<p>- verbal description (numerically listed) of the changes between two commits of a yaml file, esp when order has changed making git diff hard to read.
Well, it's part chat bot, so I don't know if it meets your criteria. But we're using them for a LOT of things behind the scenes to help kids find content they love that their parents approve of.<p>[HelloWonder.ai](Hellowonder.ai)<p>The front end looks like a chat bot, but on the backend we're using LLMs to find, parse, rate, classify, and rephrase content on the fly for individuals.
What about chatbots that understand products? <a href="https://notionsmith.ai" rel="nofollow noreferrer">https://notionsmith.ai</a>
Honeycomb is an open telemetry tool that has a complicated search UI. They also have a text box you can use to have it query your data for you, it basically just drives the filtering and group by UI. It's really cool because it just makes the UI simpler to use, worse case it might set the wrong filter.