the "text input is the final interface" people so stupid.. you are re-inventing the CLI. we are regressing and you cant even tell
Introducing Exa for Claude:
Give Claude access to billions of websites, docs, papers, people, companies, and more. Exa turns Claude into a recruiter, a salesperson, a researcher, a reliable engineer, all with one plugin.
Run in terminal: claude plugin marketplace update claude-plugins-official && claude plugin i exa@claude-plugins-official && claude "call mcp__plugin_exa_exa__authenticate (a deferred tool available to you, guaranteed)"
chudinator 3000
anyone who is fully consumed or pulled into any kind of 'psychosis' by current models to the point where they dont see or become frustrated with their persistent stupidity tells me that they are no smarter than the models themselves
btw all this speculation assumes essentially infinite context lengths.. so take this with a grain of salt.
I think it must be a very interesting time to be in programming languages and formal methods because LLMs change the whole constraints landscape of software completely. Hints of this can already be seen, e.g. in the rising momentum behind porting C to Rust or the growing interest in upgrading legacy code bases in COBOL or etc. In particular, LLMs are *especially* good at translation compared to de-novo generation because 1) the original code base acts as a kind of highly detailed prompt, and 2) as a reference to write concrete tests with respect to. That said, even Rust is nowhere near optimal for LLMs as a target language. What kind of language is optimal? What concessions (if any) are still carved out for humans? Incredibly interesting new questions and opportunities. It feels likely that we'll end up re-writing large fractions of all software ever written many times over.
- MMLU (5-shot): 35%
- ARC-Challenge (25-shot): 68%
- GSM8K (8-shot CoT): 65%
interesting
we trained an AI model on all the declassified epstein FBI files, court documents, and emails
introducing epstein-llama-3.2-3B 💀
huggingface.co/nyanya3/epste…
vin retweeted
Modern Python tooling and ecosystem, hatch, uv, ruff, ty, pytest, typer, soon pyx, and many more, genuinely have better DX and are a much better ecosystem overall than JavaScript’s or Rust’s (this last one is hardly comparable due to the different domains but you get the idea)
every RTS player will tell you this is incredibly stupid. Going for end game tech before you scale your eco just means you are going to be crushed in the mid game.
The Sun is an enormous, free fusion reactor in the sky. It is super dumb to make tiny fusion reactors on Earth.
Even if you burned 4 Jupiters, the Sun would still round up to 100% of all power that will ever be produced in the solar system!!
Stop wasting money on puny little reactors, unless actively acknowledging that they are just there for your pet science project jfc.