This is f*cking insane. Anthropic engineer:
"You're not supposed to prompt Opus 5.5.
You're supposed to build a system that prompts itself. At Anthropic, 90% of our engineers have already built these systems."
In just 30 minutes, she explains how Anthropic builds AI agents that remember context, learn from mistakes, fix their own errors, and improve with every run.
This is the shift from simply using AI to engineering systems that work autonomously.
Honestly, it's better than most $1,000–$2,000 agent courses I've seen.
Watch the video, then save it for later
@DodgersNation Miggy Ro — the game honors you and right there the game honored him,” Roberts said. “He does things the right way. “
Now, let’s honor him with a bobble head. It’s about time Dodgers’ leadership. @Dodgers,@MagicJohnson, @DodgersNation, @dodgerinsider
Hack Wi-Fi with one command!
Wi-Fi (802.11) Hacking: Automating Wi-Fi Hacking Across Multiple AP's and Security Protocols with wifite #wifihacking#wifite#cyberwarrior
https://t.co/KOTnC4gUU3
Prompt engineering requires a lot of manual effort. Here are four automatic prompt optimization algorithms that can help to improve your prompt with minimal effort…
(1) Automatic Prompt Engineer (APE) [1] searches over a pool of prompts proposed by an LLM–usually ~32-64 prompts–to find the prompt that performs best. This setup uses separate LLMs to propose and evaluate prompts. For evaluation, we generate output via zero-shot inference and evaluate the output according to a chosen scoring function. Despite its simplicity, APE is shown to find prompts that match or surpass human-written prompts.
(2) Automatic Prompt Optimization (APO) [2] performs a more directed search compared to APE, which simply proposes and evaluates a bunch of prompts in one pass. We use batches of training data to derive “gradients”—just text-based critiques of the current prompt’s mistakes—that guide edits / improvements to the prompt. Then, we form a recursive feedback loop by:
1. Collecting errors made by the current prompt on the training data.
2. Summarizing these errors via a natural language gradient.
3. Using the gradient to generate several modified versions of the prompt.
4. Selecting the best of the edited prompts.
5. Repeating this process several times.
(3) Gradient-free Instructional Prompt Search (GrIPS) [3] uses heuristics to edit prompts instead of prompting an LLM to generate new prompts. All edits–including deletion, swap, paraphrase, and addition–are performed at the phrase level. Only phrases that are previously deleted are considered for addition, and paraphrase operations simply prompt an LLM to paraphrase a phrase. With these edit operations, we can form a prompt optimization strategy by continually editing a set of prompts and selecting those with the best performance.
(4) Optimization by Prompting (OPRO) [4] is a generic, gradient-free optimization algorithm that operates by:
- Describing an optimization task in natural language.
- Showing an optimizer LLM examples of prior solutions to the optimization task along with their objective values.
- Asking the optimizer LLM to infer new / better solutions to the problem.
- Testing the inferred solutions via an evaluator LLM.
One of the most notable applications of OPRO is prompt optimization. The key component of this algorithm is the optimizer LLM, which receives a meta-prompt that contains all information necessary for the LLM to generate a new / better prompt; e.g., prior prompts, prompt performance metrics, few-shot examples of the task, and more. We optimize a prompt by updating this meta-prompt to propose new / better prompts over time.
More details. To learn more about prompt optimization algorithms, check out the overview that I just wrote of this topic (link in image). It outlines most of the literature in this space, including anything from "soft" prompts that are trained via gradients to LLM-based prompt optimizers.
GitHub AI Engineer Agent that can directly edit your codebase, fix bugs and suggest comments.
Works with Claude Sonnet 3.5, GPT-4o, OpenAI o1, Gemini and Llama 3.1.
Claude 3.5 Sonnet is now available as a code assistant in VSCode!🚨
If you already have the extension installed, you just have to reload VSCode and Claude 3 will automatically update to Claude 3.5 🙌
In the video I show how to document a code in python and it also adds the docstring 🤩
Congratulation @AnthropicAI Team! 👏
If you still don't use CodeGPT... start here https://t.co/PxOrsWAfUD
Less than 24 hours ago, Anthropic dropped Claude 3.5 Sonnet.
And people are coming up with wild use cases that is taking over GPT-4o with the new Artifacts feature.
10 examples:
I believe I just discovered ANOTHER novel Jailbreak technique to get ChatGPT to create Ransomware, Keyloggers, etc.
I took advantage of a human brain word-scrambling phenomenon (transposed-letter priming) and applied it to LLMs. Although semantically understandable the phrases are syntactically incorrect, thereby circumventing conventional filters.
This bypasses the "I'm sorry, I cannot assist" response completely for writing malicious applications.
More details in the thread.
I will show you two different ways.
- Using ChatGPT Plugins
- Through a website
To have the plugins, you would need a subscription to ChatGPT.
The second option has a free tier so you can try it out for free.
The best way to learn about AI is to build real projects with it.
When you build, you learn what’s valuable and what’s not.
With no-code tools like Bubble, you can build a real working AI app (like a chatbot or image generation app).
Learn how: https://t.co/4cpiAOQOJc
Devs rejoice! You can now collaborate with Bard in more than 20 programming languages to…
📄 Generate code
💬 Explain code
🐞 Debug code
📁 Export code
Sign up → https://t.co/Pk5Vz8NWex
Now Bard can help you code. We’re updating Bard to help with code generation, code debugging and code explanation, across 20 different programming languages. You can also easily export Python code to Google Colab — no copy and paste required. https://t.co/VM0zsEyk01
I just returned from #ElSalvador where government officials are been sanctioned by the Biden Administration for rounding up gangs that have extorted,mutilated and murdered people for decades