More

MallocVoidstar · 2026-04-09T18:20:51 1775758851

https://x.com/OpenAI/status/2042296046009626989

>Our existing $200 Pro tier still remains our highest usage option.

MallocVoidstar · 2026-04-09T18:15:37 1775758537

Yeah, I remember when the "Twitter Files" were being released and it turned out that Twitter was illegitimately censoring leaked nudes of Hunter Biden. Whyever would non-consensually posted nudes be taken down other than the suppression of conservatism?

MallocVoidstar · 2026-04-09T17:58:59 1775757539

It's Signal but blockchain

MallocVoidstar · 2026-04-09T17:20:42 1775755242

No discussion on problem difficulty, or on result quality besides "the Edgee run generated slightly more output tokens than the baseline".

sachamorard · 2026-04-09T17:32:47 1775755967

More info in the GitHub repo, in the reports folder (sorry, I'm not sure I can add the link here without being flagged).

"Codex + Edgee consumes roughly half the fresh tokens of the normal Codex baseline. Output tokens are marginally higher (+3,312, +19.5%), suggesting the Edgee scenario produces slightly more verbose responses but dramatically reduces context ingestion."

kokakiwi · 2026-04-09T17:38:22 1775756302

I think the problem being given to Codex for the benchmark is the one in the attached video, where two Codex run side-by-side, working a "standard" dev thingy

MallocVoidstar · 2026-04-03T11:13:32 1775214812

Don't use the Arduino framework, use ESP-IDF or Rust.

usagisushi · 2026-04-03T16:03:40 1775232220

For those using PlatformIO, the folks at pioarduino[0] are doing a great job keeping up with Arduino Core 3.x support.

    ```
    # platformio.ini
    platform = https://github.com/pioarduino/platform-espressif32.git#55.03.37
    framework = arduino
    ```

[0]: https://github.com/pioarduino/platform-espressif32

PunchyHamster · 2026-04-03T13:34:13 1775223253

how's Rust on the xtensa cores ?

0x457 · 2026-04-03T19:42:29 1775245349

Still requires using rust compiled against their llm fork. 'espup' makes it easy if you're okay with using it.

Other than that it works pretty well. This is if you run ESP-IDF, with bare-metal rust it's either best thing ever or meh. Rust community seems to use stm32 and picos more.

astolarz · 2026-04-04T05:25:08 1775280308

I've found that it does have some issues with the number 4096 though...

POC: https://github.com/astolarz/piper-cannot-select

MallocVoidstar · 2026-04-03T11:10:43 1775214643

I assume their chips don't really exist until they're actually supported by ESP-IDF. The ESP32-C5 was announced in June 2022, received initial support in -IDF in August 2025, and more complete support in December. It seems to have only recently started getting third party dev boards.

MallocVoidstar · 2026-03-31T11:56:15 1774958175

Codex is open source: https://github.com/openai/codex

MallocVoidstar · 2026-02-24T11:37:24 1771933044

I started clicking a 'next page' link before I'd actually finished reading something (so I kept holding the mouse buttown down), and a couple of seconds later Firefox popped up a 'link preview' box informing me that I was clicking on a link to a web forum. Wow, thanks, couldn't have figured that out myself. (It did not actually summarize the next page in any way.)

MallocVoidstar · 2026-02-19T16:37:26 1771519046

> Even when the model is explicitly instructed to pause due to insufficient tokens rather than generating an incomplete response

AI models can't do this. At least not with just an instruction, maybe if you're writing some kind of custom 'agentic' setup.

maxloh · 2026-02-19T17:36:38 1771522598

Yeah, it does. It was possible with 2.5 Flash.

Here's a similar result with Qwen Qwen3.5-397B-A17B: https://chat.qwen.ai/s/530becb7-e16b-41ee-8621-af83994599ce?...

MallocVoidstar · 2026-02-18T16:57:30 1771433850

Devtools is seemingly partially broken in this version, if I have devtools open on a reasonably dynamic web app Chrome will crash within a minute or two

aapoalas · 2026-02-18T17:51:07 1771437067

It's also been ridiculously slow for a month or two now :/ not a good time to be working on some relatively intricate performance optimisation with DevTools taking 1-4 seconds to even start the performance recording.