helloplanets

It's a fork of Continue, so you can basically just compare the features to Aider here: https://github.com/continuedev/continue …

Well that tidbit of information was definitely sweeped under the rug. Strikes me as a weird combo to have a fork of a VS Code/JetBrains extension be a completely walled off enterprise only deal. …

There's this one super secret agentic framework that beats all the benchmarks...

You can just attach 40k of context directly into the Gemini, ChatGPT and Claude web interfaces afaik. If someone is using an LLM as a tool to actually be of help in an area they are already profession…

You need to be pushing much more data in than you're getting out. 40k tokens of input can result in 400 actual quality tokens of output. Not giving enough input to work off of will result in regr…

I wonder how hard it would be to implement an extra processing step, to turn this to a more 'stylized low poly' look. Basically, the triangle count would be drastically smaller, but the topo…

> Anytime more than a class or two is involved or if the code base is more than 20 or 30 files, then even the best LLMs start to stray and lose focus. They can't seem to keep a train of though…

A spinoff piece on the visual evolution of illustrated and digital chess pieces would be interesting. How they relate to specific physical designs, and the limitations of the format they're bound…

I'd be interested in reading some more from the people you're referring to when talking about experts who understand the field. At least to the extent I've followed the discussion, even…

Yes, just use a crisp screenshot related to the use case. Especially when it's a product aimed at developers.

Yep. This article reads exactly like one shotting ChatGPT. The bullet points are a dead giveaway. https://chatgpt.com/share/681f1529-2f48-800e-9325-e1adee7521... …

Pretty sure you could just give an LLM the given docs / course material and it would be able to write the language to a reasonable standard. Especially if it had sensible error messages.

Would absolutely read a 'making of' post on this project!

I wonder how much fine tuning against something like Stockfish top moves would help a model in solving novel middle game positions. Something like this format: https://database.lichess.org&…

This is partly completely misleading and partly simplified, when it comes to SOTA LLMs. Subject–Verb–Object triples, POS tagging and dependency structures are not used by LLMs. One of the fundamental …

Following the parent comment's idea, it'd end up in a table being the best choice 100% of the time. Because the underlying assumption is that accessibility and the ability to grasp the data …

Had to make this into a country ditty on Suno. https://suno.com/song/556b62fc-bcd8-4757-951a-018c5cf0a60b …

In the narrowest version of the definition: > The Registered Skilled Reporter (RSR) is NCRA's new designation that will recognize those stenographic professionals who are looking to validate t…

> In 2023, Apple shipped 234.6 million iPhones, capturing 20.1% market share and growing 3.7% year over year, according to IDC data. [0] So, probably not 525.6 million iOS devices a year, but safe …

> Case in point In Germany the Polizei will swat and arrest you if you post a meme on social media that angers someone's dignity. That's not a joke that actually happens. Source?

> The developer of Balatro made an award winning deck builder game by not being aware of existing deck builders. He was aware of deck builders and was directly inspired by Luck be a Landlord, but h…

Pretty sure yours is the more common take, rather than the opposite. Or at least a view that is very well represented by just about any news outlet. There's also a popular comedy movie about it. …

Here's the original patent for 'revolving stairs' from 1859: https://patents.google.com/patent/US25076A/en …

Can't you just cache the context?

Agreed, it's clearly a data poisoning attack. It's a pretty specific portion of the dataset the user is in after so many tokens have been sent back and forth. Could be some strange Unicode c…

That metaphor is skipping the most important part in between! You wouldn't be transplanting anything directly, you'd have a separate step in between, which would attempt to translate these a…

I guess it might be possible to retroactively create an embeddings model which could take several different models' embeddings, and translate them into the same format.