Currently thinking about evals and benchmarks... distributedthoughts.org/the-benchmar...
Posts by Abe Gong
A picture from the book where’s Waldo as a captcha challenge
💀
A suggestion from co-pilot: a code comment which reads "This is a placeholder for the actual implementation"
Thanks, Copilot, for this utterly stunning suggestion
Nvidia
Yeah, engagement on BS has been hit or miss for me.
Feels like the communities that I care most about (data, ML, startups) have been just below the critical threshold.
But maybe we're getting there...?
hm. Okay, that's a good data point...
This test post went well.
A year ago, the anti-AI mob on bluesky was loud and intense, but I think it's faded
It's not like we're ever going to run out of things that people are oversensitive about.
How recently? 12 or even 6 months ago, the mobbing was intense, but I haven't seen it as much recently.
So.... it seems like now we can post about AI on bluesky without getting violently mobbed.
... yes?
This is high mountain backpacking, where you feel every ounce of pack weight.
Before my partner goes camping, she counts the exact number of marshmallows and graham crackers she plans to use for s'mores.
I don't hink I could live that way
Claude Code, trying to get that one last unit test to pass
Inside you there are two wolves. One is active, the other one is on hot standby and becomes active if the first one fails or is taken down for maintenance. Add more wolves as necessary for increased redundancy load balancing. A quorum badger can be added for environments with multiple active wolves.
Looking forward to Data Council this week! HMU if you're around and want to catch up.
Incredible data
FastMCP 2.0 is out!
New features include:
🔄 Proxying any existing MCP server as a FastMCP server
🧩 Composing multiple servers into one
🪄 Autogenerating MCP servers from OpenAPI or FastAPI
🧠 Client LLM sampling
Let's keep growing the MCP ecosystem! 🚀
github.com/jlowin/fastmcp
Who's going to be at DataCouncil this year?
#databs
What’s an example of a functional scent?
Last year we encountered a strange glitch in one of our surveys…the word “yes” was being replaced with the word “forks” in response options. Read on to learn how we unraveled what was causing it, how we ensured it didn’t impact the data quality, and what to do if it happens to you!
Every grimpus is a yimpus. Every worpus is a jelpus. Every zhropus is a sterpus. Alex is a grimpus .. Every lumpus is a yumpus. Question: Is Alex a gorpus or bompus?
Can't stop giggling at this sample question used to test an AI reasoning model in a paper I'm reading
The pandemic started five years ago, which means it's just about time for Cisco to announce big product enhancements to WebEx to help cope with the social distancing.
In the last few days, I'm finding myself fighting memories in Windsurf a lot more often.
Cascade will often get hung up on irrelevant/outdated info in memories and ignore/garble specific instructions.
It started happening right after I installed the Wave 4 updates.
Anybody else seeing this?
a picture of a necklace with a figure on it who is pushing some kind of pearl or bauble up the necklace chain, labeled “the Sisyphus necklace”… “a reminder that you can overcome anything”
personally would not describe the myth of a man cursed to roll a rock uphill FRUITLESSLY FOR ALL ETERNITY as “a reminder that you can overcome anything” but you do you, meta ad