Yeah sorry, was unclear this is coming from the system prompt — the reason I ask this is because it’s impractical to teach it in post-training. Added a comment to the thread:
PROMPT ENGINEERING
-
Inconsistent LLM presentation and system prompts
By
–
To be clear, this isn’t a test of the LLMs themselves, but their presentation from the vendor’s most consumer-ish UI. I assume many of these are getting the answer in the system prompt. My point is just it isn’t done consistently and I liked DeepSeek bothered.
-
ChatGPT struggles to identify its own model
By
–
ChatGPT is surprisingly bad at knowing what model it’s using — it either confidently gives an incorrect version or at best it’s vague (“based on the GPT-4 architecture”). No current model seems to ever know its exact name.
-
Claude 3.5 Sonnet correctly identifies its version
By
–
Claude 3.5 Sonnet knows its own version remarkably well — not only is it right, it’s aware of the unique ambiguity of “3.5” (many users unofficially call this release 3.5.1 or 3.6) and gives the release month. (Claude 3.5 Haiku does misidentify as Claude 3 Haiku, though)
-
Comparing LLMs on identifying their version
By
–
This is such a vibes-based eval, but the first prompt I give any new LLM is “Which version is this?” and DeepSeek-V3 nailed it See below for how Claude, Gemini, ChatGPT, and Grok fare on the same — TLDR: it’s all over the map
-
DeepSeek V3: 3x Faster, More Capable
By
–
BREAKING : A new DeepSeek V3 model is now available on the web and it is 3 times faster In addition to being much more capable now
-
Create AI Agents Using Natural Language with Abacus ChatLLM Teams
By
–
With @AbacusAI ChatLLM Teams, use your natural spoken language as a programming language (guided with the embedded #AI Assistant) to create AI Agents for a variety of different business tasks and processes.
— Kirk Borne (@KirkDBorne) 26 décembre 2024
🌟🌟🌟
Start FREE TRIAL at https://t.co/73VwIlbKFB#GenAI #GenerativeAI pic.twitter.com/uxnBiCOVhyWith @AbacusAI ChatLLM Teams, use your natural spoken language as a programming language (guided with the embedded #AI Assistant) to create AI Agents for a variety of different business tasks and processes. Start FREE TRIAL at https://
chatllm.abacus.ai/?token=kirk #GenAI #GenerativeAI -
Create GPTs in ChatGPT to automate tasks with mega prompt
By
–
I turned ChatGPT into my personal assistant. And now I only work for 60 minutes a day because of my GPTs. So, if you want to create GPTs in ChatGPT to automate all your tasks then I have created "GPT Creator Mega Prompt" for you. Like + comment "GPT" and I'll DM you the file.
-
5 prompts to succeed in your job interview with ChatGPT
By
–
ChatGPT helped my friend prepare for her interview in minutes and she got the job. Here are 5 prompts that will help you get the job:
-
Test-time search drives ARC-AGI performance, not vision
By
–
In general: there is a strong correlation between adding test-time search (or test-time training) to your model and ARC-AGI performance. There is zero correlation between adding vision as a modality and better performance. It's all about better reasoning, not at all about vision.