Back in 2020, $META was desperate to hire. Nowadays the tide has turned and interview process shifted accordingly. They are super picky now, even for those who nail every stage of the interview, folks are still routinely passed over.
Am I correct in my understanding that- they had specialized software that not only tracked the ball, calculated spins using the logo, and fed calculated trajectories?
They don't have enough compute capacity relative to growth rate. The new tokenizer in Opus 4.7 hints at a coming foundational / architectural change. I expect the next point release will deliver decent results more efficiently.
Ymmv. I've been using GPT Codex 5.3 and now 5.4 for the past few months and it works great and is reliable.
There's a One Minute video showing the difference on the github page.
You can also try it yourself:
$ uvx agent-cli-helper run-command vim
It sends this:
<session id="vim" current-program="vim">
<screen-capture>
1
~
~
~
~
~ VIM - Vi IMproved
~
~ version 9.2.218
~ by Bram Moolenaar et al.
~ Modified by team+vim@tracker.debian.org
~ Vim is open source and freely distributable
~
~ Sponsor Vim development!
~ type :help sponsor<Enter> for information
~
~ type :q<Enter> to exit
~ type :help<Enter> or <F1> for on-line help
~ type :help version9<Enter> for version info
~
~
~
~
~
0,0-1 All
</screen-capture>
</session>
<instructions>
The command has started. To send keystrokes run `agent-cli-helper send-keystrokes` followed by the id and the keystrokes. For instance:
$ agent-cli-helper send-keystrokes vim "^X"
Run `agent-cli-helper send-keystrokes --help` to find out the full syntax
</instructions>
<important>When you are done, use finish-command to finish the session. For example: agent-cli-helper finish-command vim</important>
<random-usage-tip>If you need to see the current screen without sending keystrokes, use agent-cli-helper get-screen-capture <session-id></random-usage-tip>
Some important parts:
* it returns the output to the stdout making it easier to loop on
* it formulates everything in fake xml so the that the agent knows the status and doesn't send weird keystrokes to the wrong command
* it includes reminders and "random-usage-tip" which is not random, it reminds the agent of how the tool behaves. The "random-usage-tip" is non-random, it is called that to make it look unrelated but it really is.
All of these things have been tested and eval'd. Calling it "screen-capture" "current-program", these have all been tested with variations for a variety of tasks/harness/model triplets.
The tool is optimized for agent usage and has been designed that way as a first principle
https://news.ycombinator.com/item?id=47340079
reply