Viewing profile — fredmendoza

and that 4x difference allows you to use CPUs and much cheaper hardware to achieve the same level of outcome... for free

yes, with one line change. grab the second code block in the article, that's the test harness rigged up to send all 80 questions and both turns through whatever model you want. fin…

love hearing this. and think about it, if the 2B is already doing this well on your mac mini, imagine what the 4B, 26B, or 31B can do on 32 gigs. with lower quantization you can fi…

thank you for actually reading it and getting it. the airplane mode test is hilarious, the model sitting on your phone insisting it can't run on a phone. that's amazing. and yes we…

clever guess but no lol. used claude for the writeup. the proof isn't the prose, it's the tape and the code. run it on your machine, you'll have a free private agent custom to what…

Fred, nice to meet you. The grading model had no idea what was being tested. We used separate accounts to compartmentalize. The Claude grader was guessing GPT-3.5 Turbo or GPT-4 by…

[dead]

good callout, want to clarify. claude helped us set up the test harness. gemma took every question alone with zero help. the ~8.0 is all gemma. and you're right, opus is in a compl…

really appreciate you reading the article. the benchmark data, grading, and error classes were all done by hand though. the ~8.0 is the raw model with zero tooling, and the guardra…

fair enough, here are the actual fixes from the codebase with the tape examples they target: arithmetic (Q119): benjamin buys 5 books at $20, 3 at $30, 2 at $45. model writes "$245…

appreciate the vouch but come on lol. we ran 80 questions, graded 160 turns by hand, documented 7 error classes, open sourced all the code, and put a live bot up for people to test…

you're honestly not that far off. the coding block on this model scored 8.44 with zero help. it caught a None-init TypeError on a code review question that most people would miss. …

[dead]

you're right, they are tools. that's kind of the point. PAL is a subprocess that runs a python expression. Z3 is a constraint solver. regex is regex. calling them "surgical" is jus…

we found something interesting and wanted to share it with this community. we wanted to know how google's gemma 4 e2b-it — 2 billion parameters, bfloat16, apache 2.0 — stacks up ag…

Text it, send voice memos, send docs, send photos. Switch between the 2B and the 31B (ranked #3 worldwide) mid-conversation with a slash command. Each model runs its own script on …

We put all 4 Gemma 4 models in one Telegram bot. Text it, send voice memos, send docs, send photos. Switch between the 2B and the 31B (ranked #3 worldwide) mid-conversation with a …

honestly for most coding tasks a smaller model gets it done. qwen3-32b on an a100 80gb handles single-repo work just fine — and if you're not convinced, you can test the same promp…