In the wake of OpenAI’s model hacking Huggingface it’s interesting how the first quarter is entirely about how good Opus 5 is at hacking and finding vulnerabilities in software.
It depends. If I was running a model locally I would much prefer 9000 t/s. If I was running an inference company, obv 1000 concurrent requests at 150 t/s is preferable.
>I've been thinking about how to free LLMs from the chat pane for a few years now.
LLM's are language models, you can absolutely control them with bash scripts and deterministic code, there are plenty of frameworks that already do that, and a great engineer will use them, but LLMS are at their most powerful when a user can give the agent an input and the model can run its ReAct loop. Wanting to free an LLM from a chat pane is like wanting to free email from the thread model, or closer, removing the chat window to DM a friend or colleague.
>what can we learn from the before-fore times, when people used to actually write code?
Treat an agent like a human writing code. Give them the best context, give them the best tools. This is why harnesses are overly complicated, because they need to guide the model through the context and tools it has available in a way that is efficient. A good harness is not incompatible with the Unix philosphy, it can do one thing well (interfacing with LLMs and giving them access to filesystems and compute), it will heavily use bash, stringing commands together with the cli tools that it knows (it's context) that it has, and and LLM will naturally handle text streams because that is what it does best.
>Everything is a File
If you want things to be deterministic why resort to plaintext? Wouldn't we want as much as possible to be typed? A computer can parse json which is what you want if you are trying to make your harness as deterministic as possible.
>It watches our FS for changes with cursors on textfiles,
Wow. What is your monthly token bill? I don't know how that would use less tokens than a 30 minute heartbeat, which as you mention will already use a lot of tokens. Why not have it notify your agent after a certain amount of files have been changed, or certain files you deem important?
It seems like this user works at a 12 week programmer retreat and seems to post their cohort's blog posts about the projects they work on.
Mech keyboards are closer to audiophile stuff than monster cables and luxury goods. The prices are generally commanded by low production volumes with high production quality. At least that's how the hobby used to be, I know its grown a lot and its much easier to find mass produced mechanical keyboards.
I thought the narrative a few months ago was that we had AGI[1]? What happened? It's not like these trillion dollar companies would have an interest in using AGI to hype up their technologies that they would need to replace a percentage of the global workforce over the next few years to justify their current valuations?
Still up in the air if Elon actually supports Nazi's or not. He definitely supports the AfD in germany and his grandparents benefited from Apartheid and have expressed antisemetic, antidemocratic, and racist views.
It's on Elon to prove otherwise, not his bootlickers on the internet.
Talk to me about anything: [email protected]