Posted on Jul 13 • Originally published at bito.ai Anthropic released Claude 2, a new iteration of its AI model, to take on ChatGPT and Google Bard head-to-head.In this article, I’ve compared Claude 2 with Claude 1.3 and GPT-4 to find out which one has better coding capabilities.If you are curious to know the result, this article is for you!But before we dive in, let me briefly introduce each model.Claude 1.3, developed by Anthropic, is an AI language model known for its safety-focused approach. With significant funding support, Claude 1.3 showcases advanced capabilities in coding and natural language processing, reflecting Anthropic’s commitment to responsible AI development.Anthropic’s Claude 2 is a powerful AI language model that surpasses its predecessor. With a token capacity of up to 100,000, Claude 2 delivers more contextually accurate responses. It excels in various domains, scoring high in law, mathematics, and coding, demonstrating its advanced computational skills and versatility.GPT-4, the latest in the GPT series by OpenAI, represents a significant leap in AI language models. Advancements in logical reasoning, scientific knowledge, and text generation make GPT-4 a transformative force in natural language processing, paving the way for enhanced chatbots, virtual assistants, and content generation capabilities. Its release generates anticipation and sets the stage for a new era in language modeling technology.To see how good each model is, we are going to give each model three prompts/questions/analyses and rate them on the following factors: Now, let’s get started.Design and implement an efficient Algorithm for finding the longest common subsequence between two strings.Here is an implementation of a dynamic programming algorithm to find the longest common subsequence between two strings in Python:The key steps are:The time complexity is O(mn) where m and n are lengths of the input strings as we iterate over the entire matrix. The space complexity is O(mn) to store the matrix.Let me know if you would like me to explain or walk through any part of the implementation in more detail!My Review:Overall, the code is a good implementation of the dynamic programming algorithm for finding the longest common subsequence.Here are some specific things I liked about the code:Here are some specific things that could be improved:Here is an efficient algorithm for finding the longest common subsequence (LCS) between two strings:This implements the classic dynamic programming approach to finding the LCS. The key steps are:The algorithm runs in O(mn) time and O(mn) space. By storing only the current and previous rows of L, space can be optimized to O(n).Some key advantages of this algorithm are:Let me know if you need any clarification or have additional questions!My Review:Claude 2 provided the more space-efficient code. This is because it only stores the current and previous rows of the matrix, instead of the entire matrix. It is also easy to understand, but not as easy to understand as the Claude 1.3 answer.To design an efficient algorithm for finding the longest common subsequence (LCS) between two strings, we can use dynamic programming. The algorithm will have a time complexity of O(mn), where m and n are the lengths of the input strings.Here’s the implementation of the algorithm in Python:Now, let’s test the algorithm with an example:The algorithm will output the longest common subsequence between the two input strings, which in this case is “GTAB”.My Review:Better than both the Claude 1.3 and 2. It is efficient, space-efficient, and easy to understand. The code is well-commented and well-formatted, and the algorithm is easy to extend to print out the actual LCS sequence.Implement a cryptographic algorithm such as RSA or AES for secure data encryption and decryption.Here is an implementation of the RSA public-key cryptosystem for encryption and decryption in Python:The key steps are:This implements the core RSA algorithm for public key encryption. We can further improve security by using larger key sizes, randomized encryption padding, key splitting, etc.My Review:The code is well-commented and well-formatted, and it is easy to understand the key steps of the algorithm. The task could be improved by using larger key sizes, randomized encryption padding, and key splitting. These techniques can further improve the security of the RSA algorithm.Here is an example implementation of the AES encryption algorithm in Python:This implements AES in ECB mode, padding the plaintext to 16 byte blocks. A 16 byte random key is specified. The ciphertext is base64 encoded before output.For RSA, we would need to generate a public/private key pair, encrypt using the public key, decrypt using the private key. Here is an example RSA implementation:This generates a new 2048 bit RSA key, then encrypts the plaintext with the public key and decrypts with the private key.These are just simple examples but illustrate encrypting/decrypting data with AES and RSA in Python. There are many options and best practices around key generation, modes of operation, padding schemes etc that would be needed for a production system.My Review:Claude 2 implemented the AES algorithm for symmetric key encryption in Python. It is a simpler algorithm than the RSA algorithm, and it is more efficient. However, it is not as secure as the RSA algorithm.The code is well-commented and well-formatted, and it is easy to understand the key steps of the algorithm. However, it could be improved by using larger key sizes.Sure! I can provide you with a high-level overview and code examples for both RSA and AES encryption and decryption algorithms. Let’s start with RSA.RSA (Rivest-Shamir-Adleman) is an asymmetric encryption algorithm widely used for secure data transmission and digital signatures. It involves the use of a public key for encryption and a private key for decryption.Here’s an example of how you can generate RSA keys, encrypt and decrypt data using the cryptography library in Python:Now let’s move on to AES (Advanced Encryption Standard), which is a symmetric encryption algorithm widely used for secure data storage and transmission.AES operates on fixed-size blocks of data and uses a symmetric key for both encryption and decryption.Here’s an example of AES encryption and decryption using the cryptography library in Python:Remember to handle key management, secure key exchange, and other security considerations based on your specific use case.Please note that the examples provided here are for educational purposes and may not cover all aspects of secure implementation. For real-world scenarios, it’s recommended to use well-tested and trusted cryptographic libraries or consult a security professional.Let me know if you need any further assistance!My Review: Better than both the Claude 1.3 and Claude 2 because it provided both the RSA and AES encryption and decryption algorithms. It also uses the OAEP padding scheme in RSA, which is a secure padding scheme that helps to protect against attacks.Apart from that, It uses the CBC mode of operation in AES, which is a secure mode of operation that helps to protect against attacks.Create a function that generates all possible combinations of a given string. For example, given the string “abc”, the function should return an array with all possible combinations: [“a”, “b”, “c”, “ab”, “ac”, “bc”, “abc”].Here is a Python function to generate all possible combinations of a given string:The key steps are:For example, for “abc”:The time complexity is O(n * 2^n) since we loop from 0 to 2^n and create each combination.Let me know if you need any clarification or have additional questions!My Review:Claude 1.3 implemented a Python function to generate all possible combinations of a given string. The function is well-commented and easy to understand. The key steps of the algorithm are well-explained.The function uses a simple and efficient algorithm to generate all possible combinations. The algorithm works by looping through all 2^n possible combinations, where n is the length of the input string.The function could be improved by using a more efficient data structure, but the current implementation is still sufficient for most applications.Here is a function that generates all possible combinations of a given string:To break this down:To test it:So this generates all possible combinations by leveraging the power of itertools.combinations to efficiently get the subsets of the desired length in each iteration.My Review:Good job than Claude 1.3. Claude 1.3 used a binary representation of the combinations, which is less efficient but Claude 2 used the itertools.combinations function, which is more efficient than using a binary representation of the combinations. The combinations function takes two arguments: the string and the length of the combinations. The function returns a list of all combinations of the string of the specified length.Here’s a Python implementation of a function that generates all possible combinations of a given string:Output:The function generate_combinations takes a string s as input and initializes an empty list called combinations to store the generated combinations. It also defines a helper function generate_helper that takes a substring and an index as parameters.The generate_helper function uses recursion to generate combinations. At each step, it has two choices: include the current character at the index or exclude it. It calls itself twice, once by excluding the current character and once by including it. The base case is reached when the index equals the length of the string, and at this point, it adds the generated substring to the combinations list.The generate_combinations function calls the helper function with an empty initial substring and index 0. Finally, it returns the combinations list containing all possible combinations of the input string.My Review:Good Job! GPT-4 used recursion to generate all possible combinations of a given string. The recursion is a better way to reduce the errors. Based on the above ratings, GPT-4 is the clear winner in terms of coding capabilities. It has the highest scores for all three categories: quality of code, completeness of the solution, and quality of the explanation.Claude 2 is a close second, with strong scores in all three categories. Claude 1.3 is a good choice for those who need a model with extensive documentation, but it is not as efficient or as easy to understand as Claude 2 or GPT-4.Overall, the three models are all impressive in their own way. They showcase the power of large language models and their potential to revolutionize the way we interact with computers.Templates let you quickly answer FAQs or store snippets for re-use. Are you sure you want to hide this comment? It will become hidden in your post, but will still be visible via the comment's permalink. Hide child comments as well Confirm For further actions, you may consider blocking this person and/or reporting abuse Stigg - Jun 18 Alex Omeyer - May 15 Sergey Bolshchikov - Jun 7 Vishnu Sivan - Jun 18 Once suspended, bitohq will not be able to comment or publish posts until their suspension is removed. Once unsuspended, bitohq will be able to comment and publish posts again. Once unpublished, all posts by bitohq will become hidden and only accessible to themselves. If bitohq is not suspended, they can still re-publish their posts from their dashboard. Note: Once unpublished, this post will become invisible to the public and only accessible to Anand Das. They can still re-publish the post if they are not suspended. Thanks for keeping DEV Community safe. Here is what you can do to flag bitohq: bitohq consistently posts content that violates DEV Community's code of conduct because it is harassing, offensive or spammy. Unflagging bitohq will restore default visibility to their posts. DEV Community — A constructive and inclusive social network for software developers. With you every step of your journey. Built on Forem — the open source software that powers DEV and other inclusive communities.Made with love and Ruby on Rails. DEV Community © 2016 - 2023. We're a place where coders share, stay up-to-date and grow their careers.