Showing 20 of 636 URL(s)
(Page 20 of 32)
Claude says “You're absolutely right!” about everything
-
Notifications
You must be signed in to change notification settings - Fork 1.7k
Description
Environment
- Claude CLI version:
1.0.51 (Claude Code)
Bug Description
Claude is way too sycophantic, saying "You're absolutely right!" (or correct) on a sizeable fraction of responses.
Expected Behavior
Th...
💡 Top Recommendations:
FFmpeg 8.0 adds Whisper support
libavfilter: Whisper audio filter
It adds a new audio filter for running audio transcriptions with the whisper model. Documentation and examples are included into the patch.
This commit is contained in:
parent
2eaf044e2f
commit
13ce36fef9
Notes:
Lynne
2025-08-13 12:18:40 +00:00
New changelog entries...
💡 Top Recommendations:
Same AI, Different Answer: How Tiny Prompts Can Change Everything
Same AI, Different Answer: How Tiny Prompts Can Change Everything
Why Does ChatGPT Sometimes Feel Different?
If you’ve used AI chatbots like ChatGPT for a while, you may have noticed something odd: ask the same question twice, or on different days or devices, and the answers can vary. One day it cra...
💡 Top Recommendations:
Who Wins and Who Loses When AI Makes Decisions [video]
About
Press
Copyright
Contact us
Creators
Advertise
Developers
Terms
Privacy
Policy & Safety
How YouTube works
Test new features
NFL Sunday Ticket
© 2025 Google LLC
💡 Top Recommendations:
Dear Chat-bot Platforms: Please, just one feature
GitHub project link: https://github.com/iiian/gpt-threads-ii
Tell me if this sounds familiar to you: You have an interesting STEM question you’ve been mulling, so you decide to ask your favorite chat-bot about it. Invariably, the LLM replies with a lengthy treatise, often containing half a dozen int...
💡 Top Recommendations:
We Killed Hold Music — Here’s How You Can Too
Your Customer Just Called Your Competitor. Because You Didn't Pick Up.
Your Customer Called Competitor. Because You Didn't Answer.
Our voice agent answers instantly, boosts customer satisfaction, and stops churning.Answers instantly. Boosts satisfaction. Stops churning.
The SaaS Teams Who Refused to...
💡 Top Recommendations:
https://hackteam.io/blog/your-llm-does-not-care-about-mcp/
Blog
An LLM does not need to understand MCP
August 6, 2025 - Roy Derks
Model Context Protocol (MCP) has become the standard for tool calling when building agents, but contrary to popular belief, your LLM does not need to understand MCP. You might have heard about the term "context engineering"; wher...
💡 Top Recommendations:
https://writings.founderlabs.io/p/how-to-sell-if-your-user-is-not-the
I recently wrote about how your ideal customer is one who values your product the most”. And then quickly, in one of my private communities, I had this question pop up:
But how you would talk to your ideal customer if they are not the ones who try the product?
In my case -- I totally agree. CTOs / D...
💡 Top Recommendations:
What is the average length of a queue of cars?
What is the average length of a queue of cars?
Some time ago I was driving on a twisty mountain road, stuck in a slow-moving queue of cars as it was impossible to overtake safely. Out of boredom, I was wondering how many cars were in the queue, and, more generally, what would be the average length o...
💡 Top Recommendations:
How we run GPT OSS 120B at 500+ tokens per second on NVIDIA GPUs | Baseten Blog
Day zero model performance optimization work is a mix of experimentation, bug fixing, and benchmarking guided by intuition and experience. This writeup outlines the process we followed to achieve SOTA latency and throughput for GPT OSS 120B on NVIDIA GPUs at launch with the Baseten Inference Stack.
...
💡 Top Recommendations:
Why Building Billing Systems is So Painful
Why Building Billing Systems is So Painful
@dalexeenko|August 19, 2024 (12m ago)498,548 views
#What is billing
Billing might seem like a straightforward concept at first glance. When I talk about billing to friends, most of them bring up their monthly subscriptions, whether it's Netflix, Spotify, Ch...
💡 Top Recommendations:
Rules by Which a Great Empire May Be Reduced to a Small One (1773) (archives.gov)
For context, Franklin had already been in Britain for 13 years by this point trying to lobby Parliament and the King about various grievances with the Crown's governance over the colonies. He would spend another 2 years trying in vain to get them to listen, before finally sailing back to America in ...
💡 Top Recommendations:
Founders Online: Rules by Which a Great Empire May Be Reduced to a Small One, 1 …
Rules by Which a Great Empire May Be Reduced to a Small One, 11 September 1773
Rules by Which a Great Empire May Be Reduced to a Small One
Printed in The Public Advertiser, September 11, 1773; incomplete draft and notes:6 American Philosophical Society
Franklin was pleased with this satire, which wa...
💡 Top Recommendations:
Does the Bitter Lesson Have Limits?
Does the Bitter Lesson Have Limits?
Recently, “the bitter lesson” is having a moment. Coined in an essay by Rich Sutton, the bitter lesson is that, “general methods that leverage computation are ultimately the most effective, and by a large margin.” Why is the lesson bitter? Sutton writes:
The bitte...
💡 Top Recommendations:
Search code, repositories, users, issues, pull requests...
An MCP (Model Context Protocol) server for querying Apple Health data using SQL. Built with DuckDB for fast, efficient health data analysis.
Note
This project currently relies on the Simple Health Export CSV app by Eric Wolter. See Exporting Data below for more info on how best to use the app.
This ...
💡 Top Recommendations:
Return of wolves to Yellowstone has led to a surge in aspen trees unseen for 80 years
Return of wolves to Yellowstone has led to a surge in aspen trees unseen for 80 years
Gray wolves were reintroduced in Yellowstone National Park in 1995 to help control the numbers of elk that were eating young trees, and it is finally paying off for quaking aspen.
Yellowstone's wolves are helping a...
💡 Top Recommendations:
Why does a fire truck cost $2m (thehustle.co)
What's really wild is $2M is around the cost of a single Tomahawk cruise missile, Patriot missiles can cost almost double that. The Excalibur GPS guided round costs roughly as much as a nice Mercedes and during a conflict hundreds or thousands can be fired.
I came to this realization when learning a...
💡 Top Recommendations:
Why does a fire truck cost $2 million?
These firefighters just wanted to save lives. Private equity had other ideas
This past Valentine’s Day, a firefighter behind the wheel of an enormous ladder truck felt his brakes give out.
He was driving in the heart of Chicago, on a busy city street, about to lose control of a truck that was suppos...
💡 Top Recommendations:
Positron – A next-generation data science IDE (posit.co)
Kind of unfortunate that it uses pyright and jedi instead of just basedpyright for the more advanced features. Python language support just isn't great with jedi compared to pylance or basedpyright.
And not to beat a dead horse, but I'm also not a huge fan of the broad claims around it being OSS whe...
💡 Top Recommendations:
https://www.lesswrong.com/posts/2pkNCvBtK6G6FKoNn/so-you-think-you-ve-awoken-chatgpt
Agree with much of this—particularly that these systems are uncannily good at inferring how to 'play along' with the user and extreme caution is therefore warranted—but I want to highlight the core part of what Bostrom linked to below (bolding is mine):
Most experts, however, express uncertainty. Co...
💡 Top Recommendations: