Sources · Twitter/X

@antirez

Active

antirez

Linked items 183
Errors 37
Last fetched 2026-06-22 00:43
Priority P3
Must-read No

Edit

Human-friendly label. Leave blank to fall back to the identifier.

Drives ingestion cadence and the default ranking weight applied to items from this source.

Includes every eligible item from this source in the Must Read section, even when the normal item cap or duplicate grouping would skip it.

How often the watch loop polls this source. Minimum 5 min. Leave blank for the per-type default.

Optional. Pin a specific summarization model for items from this source.

Cancel

Recent items

The 15 most-recently-ingested items from this source, newest first.

Title Type Fetched
@antirez: Apparently it is possible to go much faster than my 13.5 t/s, and this is a very good news. It means... article 2026-06-21
@antirez: Generation speed in short contexts is much better, like 13.5 t/s. The generation speed number you se... article 2026-06-21
@antirez: First kinda working implementation of GLM 5.2 in DwarfStar. Will take some time to be good enough, b... article 2026-06-21
@antirez: GLM 5.2 / DeepSeek v4 PRO on systems with 512GB of RAM: DS4PRO is more sparse than GLM, it activates... article 2026-06-21
@antirez: This means that if the final DS4 PRO model will be very strong, it will have an edge for local infer... article 2026-06-21
@antirez: P.S. I don't vote for Meloni (she represents Italian right, I'm politically on the left), nor I beli... article 2026-06-19
@antirez: AI translated Italy president reply to Trump. Thanks Matteo. Video article 2026-06-19
@antirez: I opened an issue in the Redis repository about the 50% memory savings for sorted sets I talked abou... article 2026-06-19
@antirez: Recently here on X there is this thing of replying to tweets with a vague remark of what the tweet e... article 2026-06-18
@antirez: Jesus X has the most ridiculous ever "edit" implementation. article 2026-06-18
@antirez: The feeling that Apple is selling 92304294024 m5 max 128GB macbooks thanks to DwarfStar but doesn't ... article 2026-06-18
@antirez: I'm using the Unsloth 4-bit weights to integrate interence into DwarfStar. If the experiment works w... article 2026-06-18
@antirez: Happy to see people reporting GLM 5.2 doing great, the problem is: where to run it, locally? We lear... article 2026-06-17
@antirez: OpenAI may delay GPT6 (or even 5.6) before making sure could not be blocked like Fable. Or they coul... article 2026-06-17
@antirez: Interesting AF. Promoting the best 6 layers to Q4 or the last 6 layers to Q4 (Q2 DS4 Flash quants) h... article 2026-06-16