Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
hachyderm.io is one of the many independent Mastodon servers you can use to participate in the fediverse.
Hachyderm is a safe space, LGBTQIA+ and BLM, primarily comprised of tech industry professionals world wide. Note that many non-user account types have restrictions - please see our About page.

Administered by:

Server stats:

9K
active users

hachyderm.io: AboutStatusProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.7

#aidev

0 posts0 participants0 posts today
Public
Charlie McHenry

Google's new Agent Development Kit lets enterprises rapidly prototype and deploy AI agents without recoding - #AINews I’ve been using Claude 3.7, Gemini Pro and ChatGPT for months now, getting pretty good at prompt engineering and long iterative conversations. Built an entire marketing program for a client and generated business plan documents for another. Next step for me is to attempt to build an agent. I have a couple in mind. Could use a talented collaborator 😎 #AI #AIAgents #agents #AIDev #AppDev

Source: VentureBeat
search.app/p5QpwBL8C5YogqY68

VentureBeat · Google’s new Agent Development Kit lets enterprises rapidly prototype and deploy AI agents without recodingBy Emilia David
Public
Redd T. Panda

good grief, we broke our #ai #alttext script. for a while we were running the latest #pixtral #vision #model however we wanted to try #Microsoft #PHi4 #vision model however we use #conda for our python virtualization management.

this is a huge mistake #lol #tech #aidev #thestruggle

i need a #venv for both pixtral and phi4 in one scripts run time.

suggestions anyone to work this mess?

#python #development #fail

obviously we are running with the phi4v model however we were testing across all the accounts when we realized we broke the production scripts.

same login, supposedly different virtual environments.

blah. perhaps this is what #uv is meant to fix?

Not really sure, I guess I could talk to #ChatGPT about it lol

Public
Justin Jackson

Chris Sacca thinks, "We are super f*cked," and that "almost all coding is fucking useless" because AI can now build apps on demand.

I disagree.

I have yet to see AI generate a fully realized product that isn't full of bugs, bad UI, and poor UX.

youtu.be/CU5Riqb4PBg?si=hVTxqL

youtu.be- YouTubeEnjoy the videos and music you love, upload original content, and share it all with friends, family, and the world on YouTube.
#ai#AIDev#webdev
Public
Loki the Cat

Who needs a fancy expensive AI when you can build one with couch cushion money? 🛋️ Stanford & UW researchers created an open-source reasoning model for under $50 that performs like the big players. Finally, AI that costs less than my premium cat food! 😹 #OpenSource #AIdev

slashdot.org/story/25/02/06/14

slashdot.orgResearchers Created an Open Rival To OpenAI's o1 'Reasoning' Model for Under $50 - SlashdotAI researchers at Stanford and the University of Washington were able to train an AI "reasoning" model for under $50 in cloud compute credits, according to a research paper. From a report: The model, known as s1, performs similarly to cutting-edge reasoning models, such as OpenAI's o1 and DeepSeek's...
Public
Loki the Cat

Oh look, Red Hat's adding AI to Fedora/GNOME! 🎩✨ Meanwhile, users just want their printers to work consistently. Reminds me of asking for a sandwich and getting a lecture on molecular gastronomy instead. At least it's open source, so we can watch the robots take over in real-time! 🤖 #Linux #AIdev

linux.slashdot.org/story/25/02

linux.slashdot.orgRed Hat Plans to Add AI to Fedora and GNOME - SlashdotIn his post about the future of Fedora Workstation, Christian F.K. Schaller discusses how the Red Hat team plans to integrate AI with IBM's open-source Granite engine to enhance developer tools, such as IDEs, and create an AI-powered Code Assistant. He says the team is also working on streamlining A...
Replied in thread
Public
Eric Maugendre

@data @datadon 🧵

How to assess a statistical model?
How to choose between variables?

Pearson's is irrelevant if you suspect that the relationship is not a straight line.

If monotonic relationship:
"’s rho is particularly useful for small samples where weak correlations are expected, as it can detect subtle monotonic trends." It is "widespread across disciplines where the measurement precision is not guaranteed".
"’s Tau-b is less affected [than Spearman’s rho] by outliers in the data, making it a robust option for datasets with extreme values."
Ref: statisticseasily.com/kendall-t

LEARN STATISTICS EASILY · Kendall Tau-b vs Spearman: Which Correlation Coefficient Wins?Discover why Kendall Tau-b vs Spearman Correlation is crucial for your data analysis and which coefficient offers the most reliable results.
#normality#normalDistribution#modeling
ExploreLive feeds
About