Viewing profile — nsingh2

Their models don't consume encrypted text, it would be absurd to train them to do so. Surely they decrypt the text before feeding it into the LLM, so the contents could get leaked …

My own experience: much less context bloat, and hidden system prompts. Can tune it to your own workflow, instead of dealing with whatever hidden system prompt Claude Code forces on…

To be fair, Pi only had to be useful. Claude Code had to solve the difficult unsolved problem of making a terminal print text, so naturally they built a small game engine [1] [1] h…

I think it might affect real work if part of it requires a lot of thinking, i.e. something similar in nature to a puzzle. There seems to be something wrong with the "commentary" ch…

This is preliminary, but it seems like it might somehow be related to the `## Intermediary updates` system prompt that's provided to the model. Seems like it forces the model to st…

This is preliminary, but it seems like it might somehow be related to the `## Intermediary updates` system prompt that's provided to the model. Seems like it forces the model to st…

From some of the numbers I'm seeing in the GitHub issue, the codex desktop app has the same 516 spikes. So most likely it is affected.

Oh this seems bad, and is fairly easy to reproduce using codex cli. You give it a puzzle prompt that it has to reason about and solve, occasionally it will seemingly short circuit …

Codex apparently added this too, I only noticed a few days ago: https://github.com/openai/codex/issues/28969 I'm usually at my desk, and get a notification when it stops to ask a q…

A highly detailed specification is not what I mean here. It's closer to plugging in a few sentence descriptions (or a totally cluttered brain dump) and having the model interview y…

Refusing to sufficiently specify a task and hoping the model guesses correctly is not being productive. Again, these models still don't really ask questions when they should. You h…

Why supply underspecified requirements in the first place? Both models are good at challenging assumptions/edge cases and asking questions to clarify, but seemingly only when expli…

Cost per task is shockingly high. More expensive than Opus 4.8, second in place to Fable. Cost per task data is only available for max effort though, might just be very inefficient…

That seems to only be true for the "Agentic Search" benchmark. That benchmark in particular is a bit weird, because Sonnet 4.6 effort levels had a relatively small effect, so Sonne…

> Don't use it to write code One of the things I've started doing is to write the high level scaffold myself, create stubs (with comments) and have it fill out the details. I haven…

This is false. A process needs read permission on the relevant `/dev/input/` device, typically by running as root or as a user in a group like `input`. Normal desktop users general…

Yea these plots are too noisy and dense. Especially that second one, lines all over the place.

From what my own experiences are, and what's on their checkout page, $100 is 5x base usage and $200 is 20x. If $100 was 10x, then I personally would drop down. They want people to …