Prompt Helper has been pretty helpful for repeated prompts on ChatGPT https://prompt-helper.xyz/
1,739 karma · joined September 4, 2013
Ain't it anti-thesis of "get frequent user feedback" in agile terminologies.
Essentially boils down to this:
Best Practices The correct approach to managing dependencies will depend on the specifics of your application and its plugins. However, here are some general best practices:
Document your dependencies: Make sure to provide clear documentation of all dependencies required for your plugin to function properly.
Specify dependency versions: When downloading dependencies during installation, always specify the version to ensure the plugin works as expected.
Regularly update your dependencies: Whether you bundle them with your plugin or download them during installation, make sure you regularly update your dependencies to patch any security vulnerabilities and benefit from new features or improvements.
Consider using virtual environments: To prevent conflicts between different plugins' dependencies, consider using Python's virtual environments. This isolates each plugin's dependencies in its own environment.
Leverage dependency management tools: Tools like Pipenv, Poetry, or conda can help you manage your dependencies effectively. These tools also support the creation of virtual environments.
That seems like quite a long time to go.
> But perhaps the simplest way to view this episode was as a playful, recreational activity which through sheer dumb luck gave me the skills needed to solve an important problem in my work life.
I see it capturing my joy of using GPT-4 on ChatGPT, with its cap of 25 messages every 3 hours. There's a joy in exhausting the limit for each session (may be that's what gamification is). Not able to do for full day, as got to sleep for >3 continuous hours, but exploring topics besides day to day work as a result :) Learning I am doing, how much useful - not sure.
> The total cost to my OpenAI account was $22. Of that amount, about $8 was testing the prompts and running on the (cheaper) Turbo API. The final run on GPT-4 cost $14; if I had completely replicated our work from 2017 on GPT-4 it would have cost $140.
Seems like coming up with good prompt itself is quite costly at around 1/3rd of the total cost. I wonder if there are any ways to iterate on the prompts cheaply?
% ./bin/gpt-2 -m models/gpt-2-117M/ggml-model.bin -p "Let's talk about Machine Learning now"
main: seed = 1686112244
gpt2_model_load: loading model from 'models/gpt-2-117M/ggml-model.bin'
gpt2_model_load: n_vocab = 50257
gpt2_model_load: n_ctx = 1024
gpt2_model_load: n_embd = 768
gpt2_model_load: n_head = 12
gpt2_model_load: n_layer = 12
gpt2_model_load: ftype = 1
gpt2_model_load: qntvr = 0
gpt2_model_load: ggml tensor size = 224 bytes
gpt2_model_load: ggml ctx size = 384.77 MB
gpt2_model_load: memory size = 72.00 MB, n_mem = 12288
gpt2_model_load: model size = 239.08 MB
extract_tests_from_file : No test file found.
test_gpt_tokenizer : 0 tests failed out of 0 tests.
main: prompt: 'Let's talk about Machine Learning now'
main: number of tokens in prompt = 7, first 8 tokens: 5756 338 1561 546 10850 18252 783
Let's talk about Machine Learning now.
The first step is to get a good understanding of what machine learning is. This is where things get messy. What do you think is the most difficult aspect of machine learning?
Machine learning is the process of transforming data into an understanding of its contents and its operations. For example, in the following diagram, you can see that we use a machine learning approach to model an object.
The object is a piece of a puzzle with many different components and some of the problems it solves will be difficult to solve for humans.
What do you think of machine learning as?
Machine learning is one of the most important, because it can help us understand how our data are structured. You can understand the structure of the data as the object is represented in its representation.
What about data structures? How do you find out where a data structure or a structure is located in your data?
In a lot of fields, you can think of structures as
main: mem per token = 2008284 bytes
main: load time = 366.33 ms
main: sample time = 39.59 ms
main: predict time = 3448.31 ms / 16.74 ms per token
main: total time = 3894.15 msSetris-1.2_LINUX % java -version openjdk version "17.0.7" 2023-04-18 OpenJDK Runtime Environment Temurin-17.0.7+7 (build 17.0.7+7) OpenJDK 64-Bit Server VM Temurin-17.0.7+7 (build 17.0.7+7, mixed mode, sharing)
Setris-1.2_LINUX % java -XstartOnFirstThread -jar setris-desktop-1.0-SNAPSHOT-jar-with-dependencies.jar [30.05.23][12:16:41] Loading Assets [30.05.23][12:16:41] Done. [30.05.23][12:16:41] Starting UI Subsystem ^C% Setris-1.2_LINUX %
Pensando Systems is looking for ASIC, Hardware, Software and Systems engineers working in fields of Networking, Storage and Security. Check the openings in following link : https://recruiterflow.com/Pensando-Systems/jobs
More details about company here - https://pensando.io/ and https://www.linkedin.com/company/pensando-systems/, Reach out to me (ankit at pensando dot io) in case interested.
Can't help feeling sad, and bewildered in capacity of humans to cause damage at this level - the havoc this (human-made) virus is inflicting on people - close and faraway.