1. X
  2. Doneyli De Jesus
Log inSign up
Doneyli De Jesus
langfuse.com
14.6K posts
user avatar
Doneyli De Jesus
langfuse.com
@doneyli
Building the AI Engineering practice @Langfuse | @ClickHouseDB All opinions are my own :)
Montreal, QC, Canada
doneyli.substack.com
Joined February 2009
281
Following
478
Followers
RepliesRepliesArticlesArticlesMediaMedia

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
  • user avatar
    Doneyli De Jesus
    langfuse.com
    @doneyli
    Jul 27
    Good morning Claude. My new favorite thing is spending a couple of hours dictating and planning a ton of work. 20 gh issues created from my specs and then letting Claude go to town overnight. Waking up to finished work that I just need to spot check is super empowering! In
    Image
    41
  • user avatar
    Doneyli De Jesus
    langfuse.com
    @doneyli
    Jul 24
    This aligns with my own usage...
    user avatar
    Chamath Palihapitiya
    The All-In Podcast
    @chamath
    Jul 23
    🤨
    34
  • user avatar
    Doneyli De Jesus
    langfuse.com
    @doneyli
    Jul 24
    I know I'm late to the party... but... Codex (OpenAI) is REALLY going after Claude Code In the Codex app go an check your Usage Remaining! I just realized I have 3 "full resets" I can use when I run out. I'm on the $20/month plan and getting way more tokens than with the
    Image
    2K
  • user avatar
    Doneyli De Jesus
    langfuse.com
    @doneyli
    Jul 23
    Love a good fact based benchmark 😜 But in seriousness, more people than ever care about Open Source and owning their data. That's the main thing on this benchmark and only Langfuse gives you that :)
    user avatar
    Clemens Rawert
    langfuse.com
    @rawert
    Jul 23
    Who else should we benchmark?
    The Ultimate 2026 LLM Observability Platform Mega Comparison
    382
  • user avatar
    Doneyli De Jesus
    langfuse.com
    @doneyli
    Jul 22
    Ok cool. But how can we trust there won't be a bunch of false positives? I think this is going in the opposite direction. Let people vote with their engagement. With this type of warning, you are predisposing and biasing readers. Irrespective if the article in question was
    user avatar
    Substack
    @Substack
    Jul 21
    Today, Substack is launching an AI detection feature, via an integration with @pangram. Going forward, you’ll be able to scan posts, replies, and comments on the Substack app to see an estimate of how much of it was written by a human, or with AI assistance.
    Image
    52
Advertisement
Advertisement