HackerTrans
TopNewTrendsCommentsPastAskShowJobs

hansonw

no profile record

Submissions

Building more with GPT-5.1-Codex-Max

openai.com
483 points·by hansonw·8 mesi fa·319 comments

comments

hansonw
·4 mesi fa·discuss
The skill source is here: https://github.com/openai/skills/blob/main/skills/.curated/p...

$skill-installer playwright-interactive in Codex! the model writes normal JS playwright code in a Node REPL
hansonw
·8 mesi fa·discuss
Rest assured that we are better at training models than naming them ;D

- New benchmark SOTAs with 77.9% on SWE-Bench-Verified, 79.9% on SWE-Lancer, and 58.1% on TerminalBench 2.0

- Natively trained to work across many hours across multiple context windows via compaction

- 30% more token-efficient at the same reasoning level across many tasks

Let us know what you think!
hansonw
·anno scorso·discuss
More about that here! https://platform.openai.com/docs/codex#advanced-configuratio...
hansonw
·2 anni fa·discuss
The ELI5 of the paper is that most "unlearning" methods can be regarded as adding some delta `w` to the parameters of the network, but most of `w` just gets "rounded away" during quantization (i.e. `quantize(X+w) ~= quantize(X)`). Pretty clever idea as a lot of cited methods explicitly optimize/regularize to keep `w` small to avoid degrading evaluation accuracy.

To your point, it does put into question the idea of whether these methods can actually be considered truly "unlearning" from an information-theoretic perspective (or if it is the equivalent of e.g. just putting `if (false)` around the still latent knowledge)
hansonw
·3 anni fa·discuss
Our startup is building https://arcwise.app, which allows you to embed full-fledged SQL tables inside Google Sheets! We’re in the process of building out support for joins & subqueries, would be curious what people think.