What AI is actually good for, according to developers - The GitHub Blog
What AI is actually good for, according to developers The GitHub Blog
Could not retrieve the full article text.
Read on GNews AI coding →Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
github![[P] Implemented ACT-R cognitive decay and hyperdimensional computing for AI agent memory (open source)](https://d2xsxph8kpxj0f.cloudfront.net/310419663032563854/konzwo8nGf8Z4uZsMefwMr/default-img-matrix-rain-CvjLrWJiXfamUnvj5xT9J9.webp)
[P] Implemented ACT-R cognitive decay and hyperdimensional computing for AI agent memory (open source)
Built a memory server for AI agents (MCP protocol) and implemented two cognitive science techniques in v7.5 I wanted to share. ACT-R Cognitive Decay Memory nodes fade using the base-level activation formula: B_i = ln(Sum t_j -d ) Old, rarely-accessed memories lose salience. Frequently-accessed ones stay vivid. This keeps agent context clean without manual pruning - only "warm" memories surface at retrieval time. Hyperdimensional Computing (HDC) Routing Agent state is encoded as XOR of three 768-dim binary hypervectors: state x role x action. Routing uses Hamming distance rather than cosine similarity - works surprisingly well for sparse, structured agent state. Background Edge Synthesis A background process autonomously discovers and links semantically similar memory nodes. The graph selfo
trunk/8c8414e5c03f21b5405acc2fd9115f4448dcd08a: revert https://github.com/pytorch/pytorch/pull/172340 (#179151)
Reverting for now before the culprit behind #177703 is discovered. This one enables Lt bias fusions even with the cuBLAS default backend. Will become obsolete once #170571 is merged -- current merge is not safe as it increases Lt coverage for a wide range for inputs, and we do not quite know yet why #174594 breaks things. Pull Request resolved: #179151 Approved by: https://github.com/ngimel
trunk/f2faf682a8e0762f5bf39799ed8b7f1da6f4cb99: inductor: link c10 on Windows cpp wrapper builds (#178976)
Summary Fix a Windows link failure in Inductor C++ wrapper compilation by adding c10 to the libtorch link libraries. Problem With TORCHINDUCTOR_CPP_WRAPPER=1, a targeted inductor repro test failed on Windows during JIT C++ extension linking with: LNK2019 unresolved external symbol c10::detail::torchInternalAssertFail LNK1120 unresolved externals Root Cause The Windows link list in torch._inductor.cpp_builder included torch and torch_cpu (and torch_python in non-AOT mode), but did not include c10, which owns the unresolved symbol. Why Linux Does Not Hit This Linux typically resolves this through shared-object and transitive symbol resolution paths when linking/loading libtorch and related shared libraries. Windows link.exe is stricter for import-library resolution and generally requires the
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!