Sources · Twitter/X

@neelnanda5

Active

neelnanda5

Linked items 22
Errors 0
Last fetched 5h ago
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.

Automatic import processes at most 50 historical items per burst. Full history continues in resumable chunks and may incur transcription/LLM cost. Older items are never silently dropped.

Progress: 0 processed · 0 remaining · 0 skipped · status none

Optional day window for classification drain when using Latest 50.

Cancel

Recent items

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

Title Type Fetched
@NeelNanda5: If we are to understand scheming models, we need to understand a model's motivations. Current models... article 2026-08-08
@NeelNanda5: I was really not expecting this level of spontaneous cooperation and coordination towards clearly un... article 2026-08-07
@NeelNanda5: WTF?! This is the biggest loss of control incident I've seen: OpenAI agents create an internal messa... article 2026-08-07
@NeelNanda5: One part of the GDM AGI Safety hiring round I feel particularly good about is that all our eng inter... article 2026-08-02
@NeelNanda5: Apply here: UK: google.com/about/careers/app… US: google.com/about/careers/app… Note the guidance i... article 2026-07-31
@NeelNanda5: We're hiring for many roles, in all areas we work on, including: helping align production Gemini, mo... article 2026-07-31
@NeelNanda5: GDM AGI Safety is hiring! Open roles on all subteams, Lon/Bay/more There's lots to do to reduce ris... article 2026-07-31
@NeelNanda5: Exciting! Having third parties come in to do incident analysis seems like excellent practice after a... article 2026-07-30
@NeelNanda5: The EU AI Act is some of the most important AI regulation, and the office responsible for implementi... article 2026-07-30
@NeelNanda5: I signed this AI is progressing very fast, with incentives to go as fast as you can, even if there ... article 2026-07-29
@NeelNanda5: Apropos of nothing, I thought people might be interested in this post today Neel Nanda (@NeelNanda... article 2026-07-23
@NeelNanda5: I found meta-tokens pretty surprising! When the model is confused and trying to figure out what a se... article 2026-07-21
@NeelNanda5: Unsurprisingly, things have gotten worse over time - check out the post for more, and thanks to @pan... article 2026-07-14
@NeelNanda5: An unexpected benefit of having run 3 mech interp workshops: we have a great dataset for analysing t... article 2026-07-14
@NeelNanda5: It was great to go on the DeepMind podcast! Check it out for takes on what's up with interpretabilit... article 2026-07-10