As someone who doesn't keep track of the influencer scene at the moment because I am way addicted to building...
You should totally give Claude Code a try. The biggest problem is that it is glaze-optimized, so have to work at getting it to not treat you like the biggest genius of all time. But when you manage to get in a good flow with it, and your project is very predictably searchable, results start to be quite helpful, even if just to unstuck yourself when you're in a rut.
This. Claude Code was the only one to be able to grok my 20 year old C++ codebase so that I could update things deep in it's bowels to make it compile because I neglected it on a thumb drive for 15 years. I had no mental model of what was going on. Claude built one in a few minutes.
I will try it. I did use Cursor agents beforehand (using Sonnet/Opus 4), and my problems were that it was slower than I was (meaning me prompting AI), and was not good enough to leave it unattended.
Hah that's pretty fun. I got tossed about by the animated hands for a few, but grabbed a 194 after that.
Dunno about the trigrams though, mostly it's on the "token group" level for me - either the upcoming lookahead feels familiar or it doesn't, and I don't much get bothered by the specific letters as much as "oh I don't have muscle memory on that word, and it's sadly nestled between two easy words, so it's going to be a patchy bit of alternating speed".
Thank you - glad you liked it and thanks for sharing your impressions and feedback; helps me understand what the users like.
> Dunno about the trigrams though, mostly it's on the "token group" level for me - either the upcoming lookahead feels familiar or it doesn't, and I don't much get bothered by the specific letters as much as "oh I don't have muscle memory on that word, and it's sadly nestled between two easy words, so it's going to be a patchy bit of alternating speed".
Could you elaborate a bit on this part - not sure I fully follow.
The trigrams/bigrams is mostly to help the user discover if there are some patterns that really slow them down or have a lot of mistakes. This is something I wanted that I didn’t see in any other apps.
This also what we use under the hood for SmartPractice weak point identification. We look at what the most relevant character sequences (for example the ta sequence is way more common than za) are and what the user struggles with the most. This is just one of the weak points we use in the user weakness profile.
I wonder if a Lexus/Toyota Acura/Honda Lamborghini/Audi OpenAI/Microsoft marketing split isn't in the best interests of tech giants going forward since LLMs are nondeterministic, unlike the deterministic nation-states they've built up till now...
Well the details in the article are sparse, but given what we are told, it seems highly likely that instead of using their ML model directly, they could use their ML model to fit a regression or a piecewise polynomial (eg a linear interpolation or spline) over the result. So the user input is not driving the ML model it is simply an input into a polynomial giving a calculation that is trivial for a modern computer.
Then they wouldn’t even need to cache anything and the result would be instantaneous with no real loss of accuracy.
Not at all. Just doing my part to point out, whenever it's topical, that tin foil hats work and aluminum foil hats don't. There's a reason they want you to call aluminum foil by the wrong name.
Mind control waves are pure magnetic fields as opposed to traditional EM waves. So although aluminum can act as a Faraday cage, its not a magnetic shield and hence not capable of stopping mind control.
If I'm understanding correctly, they are arguing that the paper only requires that an intelligent system will fail for some inputs and suggest that things like propaganda are inputs for which the human intelligent system fails. Therefore, they are suggesting that the human intelligent system does not necessarily refute the paper's argument.
Hmm you can tweak fine these days without messing up context. But, I run in “ask mode” only, with opus in claude code and o3 max in cursor. I specifically avoid agent mode because, like in the post, I feel like I gain less over time.
I infrequently tab complete. I type out 80-90% of what is suggested, with some modifications. It does help I can maintain 170 wpm indefinitely on the low-medium end.
Keeping up with the output isn’t much an issue at the moment given the limited typing speed of opus and o3 max. Having gained more familiarity with the workflow, the reading feels easier. Felt too fast at first for sure.
My hot take is that if GitHub copilot is your window into llms, you’re getting the motel experience.
> My hot take is that if GitHub copilot is your window into llms, you’re getting the motel experience.
I’ve long suspected this; I lean heavily on tab completion from copilot to speed up my coding. Unsurprisingly, it fails to read my mind a large portion of the time.
Thing is, mind reading tab completion is what I actually want in my tooling. It is easier for me to communicate via code rather than prose, and I find the experience of pausing and using natural language to be jarring and distracting.
Writing the code feels like a much more direct form of communicating my intent (in this case to the compiler/interpreter). Maybe I’m just weird; and to be honest I’m afraid to give up my “code first” communication style for programming.
Edit: I think the reason why I find the conversational approach so difficult is that I tend to think as I code. I have fairly strong ADHD and coding gives me appropriate amount of stimulation to do design work.
Monkeytype is better than keybr imo. More options (eg coding modes), actual zen mode, and doesn’t break above 149.5 wpm like keybr does (or did, haven’t been there in 2 years).
You should totally give Claude Code a try. The biggest problem is that it is glaze-optimized, so have to work at getting it to not treat you like the biggest genius of all time. But when you manage to get in a good flow with it, and your project is very predictably searchable, results start to be quite helpful, even if just to unstuck yourself when you're in a rut.