This is probably the most frustrating (repeated) interaction I've had with LLMs ever since ChatGPT. I truly hope Anthropic still scan for "ffs, F**KING" to work on these as a priority. I've never thought I'd say that, but, in this case, I hate "honesty", it seems. I run the
LLMS
-
Complete 4-Hour Claude Course Guide
By
–
🚨CURSO COMPLETO DE CLAUDE DE 4 HORAS🚨
— SONIA (@S0N_IA_) 27 avril 2026
Esta guia es la más detallada de Claude que he visto
-Construye herramientas
-Automatiza el trabajo
-Aprende cómo las personas construyen bots y sistemas
guárdatelo te será muy útil… pic.twitter.com/rRsUyin5ijCOMPLETE 4-HOUR CLAUDE COURSE This guide is the most detailed one on Claude that I've seen -Builds tools
-Automates work
-Learn how people build bots and systems save it, it'll be very useful to you… -
Open-source Claude Code skill removes AI-generated writing traces
By
–
With this tool, no one will detect that your text was written by an AI. This Claude Code skill automatically detects and removes the most typical patterns of AI-generated writing. It's Open Source. 100% Free. Link below
-
Correcting User Misconceptions About LLM Behavior
By
–
that said, another tweet by the same user does correctly assess what’s wrong with most user’s model of what LLMs say.
-
AI Agents Token Costs: Systematic Study on SWE-bench
By
–
How do AI Agents spend your money? Most teams treat agent token costs as a rounding error even though the data says they shouldn't. New paper presents the first systematic study of how agents actually spend money on coding tasks. They ran 8 frontier LLMs on SWE-bench Verified
-
LeCun criticism debate: LLM limitations and AI community tensions
By
–
And LeCun doesn’t? I sometimes come off as aggressive because he was so hostile to me for saying that LLMs have limits, back in 2019… Bye now.
-
Comparing browser-use and ManusAI agent tools
By
–
@finkd you can try to buy @browser_use instead of @ManusAI
-
AI Conductor Model Uses RL to Automate Prompt Engineering
By
–
For the past few years, humans have been doing “prompt engineering” to coax the best performance out of different LLMs. In this work, we explored what happens if we train an AI to do that job instead. By training a Conductor model with RL, we found that it naturally learns to
-
GPT-5.5 excels at GPU kernel writing tasks
By
–
gpt-5.5 great for hard tasks like writing GPU kernels