Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
mathstodon.xyz is one of the many independent Mastodon servers you can use to participate in the fediverse.
A Mastodon instance for maths people. We have LaTeX rendering in the web interface!

Administered by:

Server stats:

2.9K
active users

mathstodon.xyz: AboutStatusProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.7

#PromptEngineering

9 posts9 participants2 posts today
Public
Jim Groth

Just published a small experiment called ThinContext:
A simple way to reduce context bloat in LLMs by summarizing previous outputs instead of feeding everything back verbatim.

message → full reply
context → short summary
Only context gets reused.

It’s lossy, but functional.
Maybe a small step toward more meaningful memory in AI systems.

Repo here if you’re curious, or want to break it: github.com/VanDerGroot/ThinCon

Critique very welcome.

Application for testing Summarised Context Compression - VanDerGroot/ThinContext
GitHubGitHub - VanDerGroot/ThinContext: Application for testing Summarised Context CompressionApplication for testing Summarised Context Compression - VanDerGroot/ThinContext
#AI#LLM#ContextWindow
Public
Doug Ortiz

Did you know you can make LLMs solve problems like a mathematician?

Chain-of-Thought prompting transforms AI outputs from guesswork to structured reasoning!

Try this:

Think through this step-by-step:
[Your complex question]

This simple trick forces the model to show its work, dramatically improving accuracy on math, logic, and reasoning tasks.
I've cut errors by 30% using this technique!

#AI#LLM#PromptEngineering
Public
Blue Headline - Tech News

💥 Did you know hackers can bypass LLM safety filters 73.2% of the time?

Researchers found that by slicing a malicious prompt into harmless segments and distributing them across different AI models, they could trick the system into writing full-blown malware.

🤖 Should we trust AI to judge itself? Or is a “jury” system the future of model evaluation?

📰 Read the full article here:
blueheadline.com/tech-news/hac

#Cybersecurity#AI#LLM
Public
Miguel Afonso Caetano

"When thinking about a large language model input and output, a text prompt (sometimes accompanied by other modalities such as image prompts) is the input the model uses to predict a specific output. You don’t need to be a data scientist or a machine learning engineer – everyone can write a prompt. However, crafting the most effective prompt can be complicated. Many aspects of your prompt affect its efficacy: the model you use, the model’s training data, the model configurations, your word-choice, style and tone, structure, and context all matters. Therefore, prompt engineering is an iterative process. Inadequate prompts can lead to ambiguous, inaccurate responses, and can hinder the model’s ability to provide meaningful output.

When you chat with the Gemini chatbot, you basically write prompts, however this whitepaper focuses on writing prompts for the Gemini model within Vertex AI or by using the API, because by prompting the model directly you will have access to the configuration such as temperature etc.

This whitepaper discusses prompt engineering in detail. We will look into the various prompting techniques to help you getting started and share tips and best practices to become a prompting expert. We will also discuss some of the challenges you can face while crafting prompts."

kaggle.com/whitepaper-prompt-e

www.kaggle.comPrompt Engineering
#AI#GenerativeAI#Google
Public
Wulfy

Vibey (Worker) comparison
between #o4 #Chatgpt and #Claude Sonnet 3.7

So recently I got a new CC and had difficulty getting it in #Antrophic. Because I have grown reliant on the PRO model in my daily. I paid the #AI tax to #OpenAI.

Here is my experience.

1. I'll restate this because it needs restating. The free models are dumber. The only meaningful assessment can come from the pay-for model.

2. AI moves at breakneck speed a month in AI is worth at least 6 elsewhere. Would you believe there are still 6-finger jokes floating around, even though current pro Gens done that for a year+.

3. The new ChatGpt model definitely seems smarter.
It seems to unnecessarily burn compute though, offering multiple solutions to issues.
I liked how it quickly adapted it's persona to my work style.

4. I like the new "vibe coding" refactoring, where it will go line by line through the code changing it. Very SciFi.

5. The new Pro sub for OpenAi comes with Gen subs (value+) so you can create images (Anthropic doesn't have that).
Also #Sora sub so you can make 10s videos, if you have seen Sora videos, they are mind-blowing.

7. It has another model called "Monday" which just works like an asshole prompt. Another proof that most users still have a lot of ground to cover in #promptengineering

Overall, I think PRO ChatGpt is slightly better than Claude, though I have gotten used to Claude.

Public
Hvedar Nabilkin

Прывітанне, сябры! 👋

У нас для вас артыкул — на гэты раз паглыбляемся ў асновы промпт-дызайну.
У ім:
🔹 што такое “эфектыўны промпт” і чаму гэта важна
🔹 як быць канкрэтным, зразумелым і… крыху маніпулятыўным 😏
🔹 і як пазбегнуць “галюцынацый” у адказах ШІ
👉 Чытайце тут: bel-geek.com/article/174318465

Навука і тэхналогіі
bel-geek.comАсновы промпт-дызайну: як пісаць эфектыўныя запыты да штучнага інтэлекту Асновы промпт-дызайну: як пісаць эфектыўныя запыты да штучнага інтэлекту
#AI#LLM#ChatGPT
Public *
Misinformation-Superhighwayman

"Prompt Engineering" for AI is this today's version of "Don't hold it that way" for the iPhone 4.

Users are misassigned blame for fundamental flaws in the technology, and are instructed to adopt behavioural workarounds. These improvised habits lack the causal power to fix underlying problems in the tech, but they serve to reinforce the notion that this new tech is superior to the tech it's trying to replace or "disrupt". Furthermore, users are taught, "Just keep trying and you'll get it right," without questioning whether the new tech is the problem, or to ask if the new tech has the potential to ever deliver on its promises.

A crucial difference between early smartphones and wishing that LLMs are a route to "Thinking Machines" is: later models of phones successfully matured the engineering of antennas and improved mobile reception, but LLMs are a dead-end that can never lead to real Artificial Intelligence.

This can be summarised by the AM/FM Principal: Actual Machines in contrast to Fucking Magic.

#PromptEngineering#AI#ArtificialIntelligence
Public *
Sarah Lea

What happens when a language model solves maths problems?

"If I’m 4 years old and my partner is 3x my age – how old is my partner when I’m 20?"
Do you know the answer?

🤥 An older Llama model (by Meta) said 23.
🤓 A newer Llama model said 28 – correct.

So what made the difference?

Today I kicked off the 5-day Kaggle Generative AI Challenge.
Day 1: Fundamentals of LLMs, prompt engineering & more.

Three highlights from the session:
☕ Chain-of-Thought Prompting
→ Models that "think" step by step tend to produce more accurate answers. Sounds simple – but just look at the screenshots...

☕ Parameters like temperature and top_p
→ Try this on together.ai: Prompt a model with “Suggest 5 colors” – once with temperature 0 and once with 2.
Notice the difference?

☕ Zero-shot, One-shot, Few-shot prompting
→ The more examples you provide, the better the model understands what you want.

#PromptEngineering#GenerativeAI#LLM
SearchLive feeds
About