Loading activity…
@victortaelin
₍^. .^₎⟆
AI
A user paired the two-word quip with another post but offered no explanation.
AI
The project's README says its memory tree summarizes older messages while letting the agent retrieve their original text.
AI
A user suggests using bend laws and autoresearch to recreate a setup referenced in a quoted post for free.
AI
A user shared a Claude artifact link to play the game, along with a video.
AI
swtormy questions whether npm packages that assume runtime code loading would work with fully compatible ahead-of-time JS/TS.
AI
A user imagines an AI-aided device that could identify stroke type, while stressing it may not be physically possible.
AI
A user says their calculations make buying either rack hard to justify and has requested prices from several sellers.
AI
A post attributes to Opus 5.5 a claim that Bend combines Lean's proofs with C-speed performance and GPU support.
AI
A user quotes an account claiming a 12-fold reduction in decoder gates relative to Google's previous construction.
AI
The poster says they'll set an AutoResearch goal to minimize the number of parallel steps a compiled program takes.
AI
A user suggests labs could profit if more than 20 companies each paid one-twentieth of a model's creation cost.
AI
Its creator says the net exactly matches JavaScript outputs, is fully differentiable and runs in a browser without a GPU.
AI
A user invited MIT or CSAIL roboticists “astramaxxing” to DM them after a quip about “GPU poor roboticists.”
AI
With funding, a developer plans a compiler self-optimization loop and may test a model trained on its progress.
AI
A user says half their vision was gone on waking and describes the episode as especially frightening.
AI
A user says models overuse linked lists, clone unnecessarily and struggle to parallelize Bend code effectively.
AI
Bend's developer says he wants to replace its current compiler with a fully modular, verified one.
AI
The author linked the Gist on October 4 and invited readers to ask an agent to build “this.”
AI
OpenAI says it drew on an independent mathematics advisory group’s advice about how to release the results.
AI
SemiAnalysis said its “5x+ more value” claim depends on a workload-based, API-equivalent comparison of subscription usage, and argued Claude plans beat OpenAI’s on that measure. Reactions in the packet disputed whether that metric supports the headline’s broader framing.
