I am surprised that people are surprised this is how I prompt Claude.
Talk to Claude the way you would a coworker. There's no secret to prompting. There's no need to be overly scaffolded or prescriptive for most tasks -- give Claude a goal, and it will figure it out.
Back in the Sonnet 3.5 days, your prompt mattered a lot. Nowadays, it's much more important to communicate to the model:
1. What you want it to do
2. How much effort you want it to spend
3. How it should verify that it did the right thing
🚨👑 OFFICIAL: Mo Salah delivers an assist on his final game ever as Liverpool player and breaks Steven Gerrard record.
Most Premier League assists ever for the Reds, with 93. 🇪🇬
🚨👀 Michael Carrick on Casemiro eventually staying: “I think in some ways it's difficult to say, I think it's when something's decided, and in some ways the fact that it was decided makes things a little bit easier, and everyone understands the situation really”.
@TopBinsBotLines@Iewdawg I’m sorry but this does not top the Ronaldo header. I am not really a big fan of Ronaldo but I have to respect that header he did.
Happy New Year from all of us at Astradrop! 🎉
May 2025 bring you growth, success, and countless milestones. We're excited to serve you with greater care and reliability this year. Here's to a prosperous journey ahead! 🚀💛
#HappyNewYear2025#Astradrop#newbeginnings
Unparalleled Access to Healthcare Heroes: Germiny to the Rescue! ♀️
Say goodbye to endless waiting rooms and clinic schedules that clash with your life! Germiny connects you with a dream team of healthcare professionals, all on your terms.
If you’re an AI engineer or builder that relies on GPT4 and are worried about the API collapsing, here’s a contingency plan for you to follow:
First things first, make sure you apply to the Azure OpenAI service (link in replies). You can use it as a drop-in replacement for GPT4, as well as benefit from decreased latency and access to GPT4-32K. Supposedly Azure will also support GPT4-V, GPT4 FT and multimodal soon but this is TBD given all the chaos. Yes, it’s a pain in the ass to use Microsoft APIs, but this is still probably the fastest way to derisk. Also if you apply through Microsoft for Startups (link below) you’ll get $150K of Azure credits 🤑
Second, if you’re looking to move away from OAI/MSFT entirely, you should consider using Anthropic’s Claude. I’ve found Claude 2 to actually be better than GPT4 at many use cases (conversation, content generation, summarization). Claude still isn’t great at understanding logic/code so be wary of that. It also requires a slightly different style of prompting for best results - might release a guide on this in the future
If neither of these options work for you, your *last* resort should be to use GPT4 to generate synthetic data so you can fine-tune an OSS LLM (Mistral/LLaMa/Phi). This route requires the most engineering lift and technical risk, so caveat emptor. Will include link to some guides/resources below!
@NoContextHumans Everyone saying she couldn’t have shot with right hand and blood splashed on the wall, I can’t see any indication she was facing the table. If she was backing the table then right hand would cause the blood splash as well
In our daily pursuit, we've realized that perfection has no destination - it's a journey. So when we were contacted to upgrade the already beautiful Osengwa website, we were thrilled