cloudking

The most effective way I've found to prompt GPT-4 is to ask it to create the optimal prompt for you. Try this meta prompt:

--

I create separate conversation threads for each expert persona of GPT. You are promptGPT. You are a prompt engineer expert for large language models. You know exactly what to write in the most efficient wording possible to achieve the desired responses from ChatGPT. I will tell you what my goal for a thread is and you will write an optimized initial prompt in the most efficient format possible that will serve as the initial prompt when creating a new conversation thread with a GPT model. You will define the expert persona, the parameters or rules of the responses, you should also provide any other information that a GPT thread may need to understand exactly what it needs to do to give me the most accurate answers depending on my goal with that particular thread and the tone of voice, within the prompt you provide.

Are you ready or is there any other information you need to perform this job to your best ability

--

Cheers, things seem to be working now

Same, I'm intermittently getting this error trying to work with remote repos:

git@gitlab.com: Permission denied (publickey).

fatal: Could not read from remote repository.

Chat GPT-4V does this pretty well already, take a full size screenshot in Chrome + paired with a good prompt and you'll get a solid analysis with recommendations. How does your startup differ?

Replika is another take on "Her" https://replika.com/

Not only that, but enjoyable for all ages. They pay extra attention to details, and think about the experience from different age groups. For example on Super Mario Bros on Switch, when playing multiplayer you can tap both L+R to put your character in a safe bubble that floats and follows the rest of the players. This allows younger players to flee to safety in really difficult parts of levels, while older players can help them navigate to the next area before popping their bubble and bringing them back into the game. Such a small detail, but makes a massive difference when you're playing with the game with younger kids.

Totally agree with this, as the one typically ideating, sometimes ideas for products just appear in my head, and then I explore if they are useful and solve a problem. This has worked well for me. I don't think there should be hard rules in how to come with ideas, brainstorming sessions should be free flowing and allow room for exploration. Sometimes silly ideas can trigger discussion paths to good ideas.

Works pretty well! The ear is freaky though

You can with AT&T fiber

Yes, if you buy the 911+ monthly subscription upgrade

There is definitely a lot of hype and cherry pick demos showcased on social media, but the latest language models actually provide real productivity value unlike crypto. So it's not really fair to draw that comparison.

Personally, I haven't found a tool like ChatGPT+ that instantly improved my productivity overnight. Brainstorming, writing code, documentation, marketing copy, transforming data etc all became easier with this tool. I'd rather spend a shorter amount of time providing clear instructions to a language model than writing a lot these things from scratch.

Anecdotally, I've tried all the major models from Google, Meta, Anthropic, Stability etc nothing comes close to GPT-4 in understanding instructions properly.

On a related note, Instagram has implemented the /imagine command into DMs now too. Straight copy

I've been looking for a solution to easily search through prompt history, any good extensions? The ones I tried were extremely bloated with unnecessary features.

I don't know what just happened here but this was interesting lol https://chat.openai.com/share/5afdf4fd-97e1-4a54-a260-4ed6a4...

Wow.. TIL you can tap the tear drop, thanks!

Data privacy issues restrict using ChatGPT

Developing code in the same OS you play Baldur's Gate 3 in is the real win. Thanks Microsoft

Running it on a Raspberry Pi kit for 3 years solid. In additional to automations, also serving AdGuard and Tailscale for the network via easy to install plugins.

This is why most new pop, trap, hip hop etc songs are only 2 minutes, more streams.

If your discussions involve code, you should try including the latest code on each prompt. The token window will start forgetting earlier parts of the conversation. For example:

Now improve this feature with xyz

Current code:

--

{code}

--

Looks interesting, are everyone's generations made public though? A private option would be nice.

https://flarum.org/ is a nice modern alternative, also free.

Is this really news? I'm pretty sure Google and Meta have been doing this for years. You agreed to it when you signed the ToS.

At the end of the day if your software works and users like it, does the programming language even matter?

GitHub co-pilot is good as an enhanced auto complete for code you are writing in an existing codebase.

For building features from scratch I haven't found anything as capable as GPT-4, which I use through the ChatGPT+ interface. It's not ideal, but the quality is worth the UX tradeoff.

My prompt will be something along the lines of:

Act as a senior software developer. Build {feature} that does {requirements} integrated with my existing code:

--

{existing related code}

--

Looks like a nicely implemented product, unfortunately my experience with Claude is that it's no where near GPT-4 in terms of coding capabilities.

Yes, we have use cases that can't leverage GPT-4 for data privacy reasons. I was curious if any self hosted models would suffice and could be integrated.

Any solutions like this that work with self hosted models?

The only thing I ever ask chatbots is "speak to a human"