Hunter Moen
174 posts


Okay and who of you couldn't reply to this? Please please only if you couldn't okay?
@levelsio@levelsio
Okay let's see who can reply to this
English
Hunter Moen retweetledi

BUNGULATORS!!! We are running a 2 PC giveaway.
2x RTX 5070 STARFORGE Gaming PC Bundles.
To Enter, perform these Task via the Link Below:
🔁Repost + Like
✅Follow All Official Burnt Peanut Channels
vast.link/peanut

English

@ky__zo I’m convinced that all of these people are secretly paid to say this stuff.
English

claude: you got free opus 4.5 this christmas
also claude: but it's 4.5x dumber for the next 2 weeks
Claude@claudeai
Starting at midnight PT tonight, all Pro and Max plans have 2x their usual usage limits through New Year's Eve.
English

@EXM7777 Claude really is the best. I just got the max plan a month ago and I will never be going back. The value I am able to get out of it is second to none.
English

if you're non-technical but want the best LLM experience...
just use claude
here's why:
if you're technical -> you can go model agnostic
- play with APIs
- setup custom environments
- plug any model into your workflows
but if you just want to open a website and get great outputs... claude is the only real option right now
because it has everything built into the webapp:
- writing styles
- custom skills
- MCP connections
- projects for context
- artifacts
- code
no technical setup required... it's all easy to use and actually works
compare this to the competition:
gemini has a basic chat interface with limited customization
chatgpt has some features but nothing close to claude's depth
you CAN replicate a claude setup with third party apps but if you're a beginner who just wants it to work out of the box...
get claude -> follow their guides -> start creating & get the best outputs
that's it
English

@AlexFinn Or just bring it up to your family members at Christmas.
English

@eSaadster This could also be the case. The model is often only as good as the prompt.
English

@hunterjmoen hot take: the "nerfed" discourse is people discovering that prompting matters
model stays the same. vibes change. but the prompts people copy-paste are lossy. context window fills differently. "it worked yesterday" is a skill issue in disguise 🦀
English

@Joe_brendan_ I agree, the devs who are in denial of how useful AI is are letting their ego get in the way.
English

@csaba_kissi Very true, the real fun started when I started coding to solve my own problems.
English

@martinrue I agree—AI has completely ruined the art of replying.
English

@donvito Completely agree. The max plan is the best bang for your buck.
English

Claude Code can now control your browser for testing, getting data, etc. using our chrome extension!
Claude@claudeai
Using the extension, Claude Code can test code directly in the browser to validate its work. Claude can also see client-side errors via console logs. Try it out by running /chrome in the latest version of Claude Code.
English

@AlexFinn It really is amazing. I’ve been seeing a lot of accounts posting about how Opus has been nerfed, but I have not noticed anything. Have you seen a decrease in performance the last few days?
English

@AlexFinn Very inspiring stuff man. Can’t wait to see where you go next.
English

@daniel_mac8 It really is impressive. I will also be switching my LLM features over.
English
Hunter Moen retweetledi












