21
Code Maintenance and Development / Project 'Memory & Influence': Human Memory Mimicry & Reply Enrichment - PHASE 2
« Last post by smfadmin on Yesterday at 11:37:04 AM »from ... https://forum.drugs-and-users.org/index.php?topic=8078 closes !
Project 'Memory & Influence': Human Memory Mimicry & Reply Enrichment
Claude Code 101: Auto Memory Explained https://share.google/eidpimPU1fNed2m9q >
📎 Click on me to view all my attachments
ListAttBBC | v7.3.0 | 2026-10-26 | Andrew.human & Claude.ai | live 13:33:45
Project 'Memory & Influence': Human Memory Mimicry & Reply Enrichment
Claude Code 101: Auto Memory Explained https://share.google/eidpimPU1fNed2m9q >
i=5xcgPdrxHDpoQAc
📄 Inline text
Clone root@clone:22:29:54~/memstore/InfluenceMem /root/llama.cpp/build-server/bin/llama-server -m /root/models/all-minilm-l6-v2-q8_0.gguf --embeddings --pooling mean -c 512 -t 2 -np 1 --host 127.0.0.1 --port 8083 0.00.007.174 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.007.236 W srv llama_server: embeddings enabled with n_batch (2048) > n_ubatch (512) 0.00.007.238 W srv llama_server: setting n_batch = n_ubatch = 512 to avoid assertion failure 0.00.008.571 W srv llama_server: ----------------- 0.00.009.189 W srv llama_server: CORS is set to allow all origins ('*') and no API key is set 0.00.009.191 W srv llama_server: this can be a security risk (cross-origin attacks) 0.00.009.193 W srv llama_server: more info: https://github.com/ggml-org/llama.cpp/pull/25655 0.00.009.194 W srv llama_server: ----------------- 0.00.012.543 I srv load_model: loading model '/root/models/all-minilm-l6-v2-q8_0.gguf' 0.00.460.286 I cmn init: llama threadpool init, n_threads = 2 0.00.478.877 W srv load_model: speculative decoding not supported by this context 0.00.478.928 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 512, kv_unified = 'false' 0.00.486.632 I srv llama_server: model loaded 0.00.486.707 I srv llama_server: listening on http://127.0.0.1:8083 1.15.981.172 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = -1 1.15.982.131 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 1.16.009.161 I slot release: id 0 | task 0 | stop processing: n_tokens = 7, truncated = 0 Clone root@clone:22:30:54~/memstore cd ~/memstore/v170/InfluenceMem && python3 influencemem.py serve /root/memstore/InfluenceMem/store4 --embed-server http://127.0.0.1:8083 --upstream http://localhost:8082 --listen-host 0.0.0.0 --listen-port 8084 --log-file /root/memstore/chat_candidates.jsonl influencemem.py v1.4.0 (2026-11-04) - Andrew.human & Claude.ai [tier1 1.0.4 | tier2 1.0.4 | tier3 1.2.0 | exec 1.3.0 | embed 1.1.0 | tokens 1.0.0] im_proxy v1.0.0 serving on http://0.0.0.0:8084 -> http://localhost:8082 retrieval: meaning + words (embeddings at http://127.0.0.1:8083, weight 2) | k 8 | budget 700 tokens | layers semantic,procedural candidates log: /root/memstore/chat_candidates.jsonl open the chat page on the proxy port; stop with Ctrl-C (an ordered shutdown). question: Where am I based? 9 fact(s), 268 tokens, 0 left out | Known facts: | - ms.2: Never suggest pkill on services | - ms.3: my name is Andrew Egerszegi | - cm.profile.f7227cf8: Based in Hunters Hill, NSW, Australia | - cm.areas.neuroethics-framework.3c53f03e: Authored a "Neuroethics Governance Framework" based on more than two decades of his own lived experience | - cm.areas.ise-project.ed70878d: Building the ISE Project — a custom Python-based SMF forum search engine, personal-use-only, SMF 2.0-only | - cm.areas.forum-infrastructure.4cb9878e: Live server is located in Singapore (its clock runs on Singapore time) | - cm.topics.diet.7de84e23: Follows a mostly plant- and fish-based (Asian-style) diet | - cm.areas.forum-infrastructure.887306e5: Live server's public IP: 128.199.200.202 | - cm.profile.c6bc1728: Has no knowledge of or connection to extended family/lineage (grandparents, bloodline) and says "the world is my family"; childless

Unanswered Topics

