Self-study
We just rolled out our AI Coach to every user on 7Sage. Use it to analyze your practice results and get personalized recommendations on how you can improve. Soon, it will also be able to explain tricky LSAT questions (using 7Sage explanations as the source—we're not allowed to show it LSAT content.)
You can access it by opening the chat menu or clicking any of the AI buttons in Analytics:
Please leave feedback in the comments!
15
30 comments
I probably won't utilize this much but I tried playing around with it and it highlighted that I skipped blind review on questions that the blind review didn't suggest I go over again. That would be a reasonable note but I've skipped blind review at most a few times besides when I'm doing the adaptive drill function that doesn't even have blind review.
I think it was even more pointed as it complained about not doing blind review on a recent drill despite me doing a blind review on the suggested questions. I suppose you could say I could blind review every question but if I have it set up to suggest questions for me, there's clearly significantly less benefit of me trying to "blind review" a question I'm being told I got right by nature of it not being flagged for blind review.
@Adam Facing this too. When doing the adaptive drills, I’m immediately told whether I got the answer right or wrong and what the correct answer is (is there a toggle for this?). The AI every time tells me that I should be doing blind review on these problems, but how can I do blind review when it tells me the answer? I asked, and it said:
“Good question — and it's a fair frustration with how the adaptive drills flow. The key is to do your "blind review" thinking before you submit each answer, since you're right that the correct answer appears immediately after.
Build the review into your first pass. On any question where you're not 100% confident, pause before submitting and force yourself to articulate:
Why the answer you're choosing is right
Why each of the other four is wrong
If you can't cleanly do that, flag it mentally (or note the question number) as one to revisit even after you've seen the answer.”
Not my favorite response, tbh.
I am really loving it! However, just a few thoughts:
1.Yeah it’s a bit…sassy. Personally, I like it because it pushed me to do the blind reviews but will other people like it, not too sure. Maybe add something that allows us to change the tone from nurturing to aggressive that way we can pick what we like. Some of us need that extra push.
2.It would be cool if it had links sending me to the section it thinks I need to work on. For example:
“So your two targets from this drill are — casual weakening and necessary assumptions — are exactly the LR areas already on top of your priority list”
Once we click on the bolted parts, we could then be linked to the exact lesson we need to go back to review.
3.Visually it’s too long. Perhaps it can separate what it’s giving us into sections. First paragraph criticize my timing, second paragraph discuss my second guessing, third paragraph discuss my blind reviews and fourth paragraph talk about where I need to focus and provide me the links to the lessons. Give it spacing and maybe bolded titles so we can be able to distinguish the type of feedbacks we’re getting.
Ultimately, it’s awesome! I know it’s in beta right now and I hope it can get to a point where it helps us create study schedules, and study goals for the week and such since it has access across the platform I imagine.
It keeps giving giant paragraphs that are walls of text instead of concise bullet point breakdown feedbacks even after I explicitly told it to…Would also like option to clear chat history or start new chat.
Super super useful
I really love it, but sometimes it has passive aggressive vibes: "Lidiia, you skipped Blind Review again. This is the third drill in a row where you have done this, and at this point it is the single biggest thing holding back your progress. Please go back and Blind Review Questions 4 and 5 before moving on." chatgpt answered that: The phrases that create that feeling are:
"you skipped Blind Review again" — "again" can sound exasperated or scolding.
"This is the third drill in a row" — keeping count of failures can feel like being reprimanded.
"at this point it is the single biggest thing holding back your progress" — a strong judgment that may come across as blame rather than observation.
"Please go back ... before moving on" — an instruction immediately after criticism can feel parental or disciplinary.
@Lidiia You are under spells
@icedshakenespresso leave it
@Lidiia yeah I had to give it a piece of my mind for sure. I just told it that if I don’t input anything that means my answer remains the same as what I chose the first time around.
@Lidiia You're complaining about a chatbot having "passive aggressive vibes"...
@icedshakenespresso off topic
actually a lot more insightful than i thought! i thought it was going to give me generic study plans but it takes quite a few factors into account
This is... an odd choice.
It can even build you LR and RC drills!
Hello @David_Busis,
I am waiting for your team to roll out a 7sage offline feature. It would be very useful to study on planes, trains, and other forms of transportation where connection is not always stable. If I can pay $15/month for Spotify and have access to all locally downloaded content within the app without an internet connection, I am wondering why this $75/month service cannot perform similarly. Fingers crossed.
#feedback
@AOnifade I would also love to see this. I commute to school a lot, and around the northeast US in general, and I constantly think about how useful that time would be if I could study LSAT during it.
I'm currently playing around with this, and it's pretty cool! Are you considering granting the AI access to comments we make on questions? I'd be curious to see what insights it could pull from my wrong answer journal comments.
I have genuinely been waiting to see if you guys implement this feature. Haven't tried it yet but my ultimate hopes as a user would be if it could tell me more about specific things like whether I misread double negatives and pedantic stuff like that as I do thousands of questions.
@antitrust_fan You undersold this! Admittedly, I didn't watch the video, but it's so cool that it can build drills. The only thing I noticed about the analyze feature was that it weirdly only will analyze what's on the screen. (It told me that there were only tags on 7Sage regarding passage type for RC, and there was actually data for certain RC questions, but they just happened to not be on the default analytics page).
While I hope to be done with 7Sage for good this June, I am pretty impressed with this tool, especially for someone who is often skeptical about implementing these things.
However, you should probably know that I asked it to make a drill with a specific passage (I gave it PT105.S3.P2.Q1 in the proper formatting), and it gave me something pretty random with full confidence.
This is such a game changer. It's essentially a tutor built in to 7sage. I love it. And I'm already seeing improvement from it.
❤️ we already use it outside of 7Sage just with caution as it’s not fully vetted or customized to the lsat as a whole…. Intrigued to see if there are flaws with the full integration. Outside of 7 sage on multiple occasions ai could not process high level logic…
Pending to see as of today we embrace it⭐️
I am very excited to cancel my 7Sage membership. AI is terrible for the environment and questionable at best for humanity.
@charlenehansen and AI is terrible at legal reasoning, which is why law schools like UC Berkley are banning its use. Idk why you'd wanna go through so many hoops (prompt upon prompt) for AI to get a perfect 180. We know it's possible, but I imagine we would not hire a tutor that scores anywhere between 149 (GPT-3.5) to 163 (GPT-4). I, for one, enjoy humans who can explain why they got the human-ly scored 170+
all that to say, @everyone please get help from humans. Hallucinated logic is flawed logic
@cattail8148 I love you
@icedshakenespresso <3 u are my favorite dunkin drink
It's amazing. I wish I had it before my test though :(
Great so far! I wish I could open different instances of the chat so that I don't have to scroll up and down a long conversation to find a particular response.
AGH THIS IS WHAT I WISH I HAD 2 MONTHS AGO
Love it so far!