Viewing profile — jahala

I went from having an experience of life, of reality - that was very self-centered, lonely and nihilistic - to basically a "life worth living". I wish I had met with meditation - t…

In most cases, the quality of your attention determines your quality of life. Your ability to focus on education, work, personal relationships etc will often determine the outcomes…

Meditation - «getting used to» A most elementary form of meditation, is getting used to placing your attention on a sensation and keeping it anchored there - even when other sensat…

Opus 4.8 is my daily driver, and it's miles away from what I got out of Fable 5

Really cool! Where would you get the data for something like this? Is it open, or its scraped?

VibeSolve is an open-source tool that turns a plain-English description of an optimisation problem into Timefold code. Mathematical optimisation is a branch of mathematics and comp…

Its on the way! https://github.com/jahala/tilth/pull/151

[flagged]

There is an answer- these tools should benchmark by cost per correct answer - not just tokens saved.

Would sincerely love to hear your thoughts on https://www.github.com/jahala/tilth - it’s a different approach than RTK, benchmarked to reduce cost per correct answer by ~40%

Thanks for that!

Loving the customer testimonials :D .. If someone feels like an eli5 - What are the use-cases for something like this?

Yup, this is hitting it on the nose. But, despite the cost - the benchmark is the vital ingredient that cant be skipped. Otherwise, you don't know if what you're building is actual…

No I don't have the funds to benchmark the competition, but would be happy to put the numbers up if any token whales feel like having a go. https://github.com/jahala/tilth/tree/mai…

This is the reason, when I built a tool in the same space, I chose to benchmark with cost per correct answer. Reducing tokens and also turns is quite worthless if the LLM doesn’t s…

Nope.

This looks great! I built a tool in the same space- and I found that the biggest challenge was often to get the agent to prefer to use the tool over bash tools. What’s your experie…

I absolutely LOVE Accelerando. I've recommended it to everyone I meet for years. If you're looking for other great sci-fi reads: John Ringo - Live free or die John Varley - Titan (…

[dead]

I did a proof of concept for self-updating html files (polyglot bash/html) some weeks ago. It actually works quite well, with simple prompting it seems to not just go in circles ( …

I built tilth ( https://github.com/jahala/tilth ) much for this reason. Couldn't bother with RAG, but the agents kept using too many tokens - and too many turns - for finding what …

I got tired of copy-pasting between agents for simple coordination. Everything I found was a framework or a hosted service. I just needed them to talk. Walkie-Clawkie is a single J…

Hey @joknoll - in the benchmarks, I'm seeing very positive results with Haiku, getting quicker and more correct answers. So I think you're absolutely right that harness improvement…