The session ran one youtube-topic-learner cycle on a fresh Wes Roth AI-news video
(“INSANE AI News: GPT-RED, Kimi K3, Gemini 3.5 Pro and Anthropic's END GAME”) and, per the
user's request, correlated it against the venture portfolio in reports/ventures.json.
That produced a wiki source page, a new living topic page with a news-to-venture correlation table,
and an auto-generated ai-news-venture-radar skill.
The user then asked to check what open-weight models run offline, which led to an experiment: enabling Ollama's experimental Vulkan backend to offload inference onto the laptop's Intel Arc 140V iGPU. The offload technically worked (49/49 layers on the GPU) but benchmarked ~10–18% slower than CPU — so CPU stays the right default. Ollama was returned to its normal CPU/tray-managed state (briefly complicated by a RAM-thrash, then confirmed back up).
yt-dlp; framed topic
frontier AI model news… and slug frontier-ai-news.youtube-topic-learner/harvest.sh --count 0 --include OPuD-UeQGY8 → local
download + faster-whisper (small) transcript (~26 min, CPU-only box).reports/ventures.json.log.md
entries; wired both pages into index.md.tax-rag containers).OLLAMA_VULKAN=1 (found Arc but dropped it as iGPU) → add
OLLAMA_IGPU_ENABLE=1 (Arc accepted, 49/49 layers offloaded) → benchmark → confirm
CPU faster under matched load.curl /api/version confirmed the server answering (v0.32.0).| Model | CPU (baseline) | CPU (matched load) | Vulkan / Arc 140V | Verdict |
|---|---|---|---|---|
llama3.2:3b | 11.29 tok/s | 11.13 tok/s | 9.43 tok/s | CPU +18% |
qwen2.5:14b | 2.99 tok/s | 2.69 tok/s | 2.44 tok/s | CPU +10–22% |
Generation tok/s (num_predict=128, temp=0, warm). The Arc 140V is an
integrated GPU sharing the CPU's LPDDR5X memory bus, so bandwidth-bound decode gets
no advantage and the Vulkan backend only adds dispatch overhead. Full offload was verified in the
log (offloaded 49/49 layers to GPU, 8 GB model buffer on Vulkan0).
Keep Ollama on CPU on this hardware.
| File | What it is |
|---|---|
| wiki/…/sources/2026-07-16-wes-roth-insane-ai-news-gpt-red-kimi-anthropic.md | Synthesized source page for the Wes Roth video — all 9 news items, rumor/sponsor bias flagged, name garbles corrected. |
| wiki/…/topics/Frontier AI News & Model Releases.md | New living topic: overview of the frontier shifts, an operator's reading playbook, and the news-to-venture correlation table. |
| ~/.claude/skills/ai-news-venture-radar/SKILL.md | New Claude Code skill (outside repo): turn AI news into venture decisions vs reports/ventures.json. Marked generated-by: youtube-topic-learner. |
| downloads/learn/frontier-ai-news/ | Local video corpus: OPuD-UeQGY8.{mp4,txt,srt,vtt,json,summary.md} + manifest.json + ledger.json (from harvest.py). |
| downloads/learn/frontier-ai-news/bench_ollama.py | Reusable deterministic Ollama benchmark via the HTTP API (before/after backend swaps). |
| …/ollama-vulkan.log, …/ollama-cpu-confirm.log | Server logs capturing GPU discovery / offload evidence for the experiment. |
| File | Change |
|---|---|
| wiki/log.md | +2 entries: ingest (Wes Roth video) and synthesize (Frontier AI News tracker + skill). |
| wiki/index.md | Added a “Frontier AI news” line under the orgs/valter-silva-au section linking the topic + source. |
valter-silva-au (personal learning/tooling org), not my-imagination-ai — reused as the stable org for this topic per the wiki's “which org?” rule.TASK-00026); (b) a “we fine-tune privately on your data” angle to test in the FIFO / Questionnaire ICP interviews (relates to TASK-00010 / TASK-00016). Captured in the wiki, not pushed to tickets this session.adb was available, but no adb tasks were created or updated this session — the work
landed in the wiki + a skill. The correlation relates to existing tickets (TASK-00026,
TASK-00010, TASK-00016) without modifying them.
Fact sources used this run: git ✓ mtime scan ✓ adb ✓ live Ollama benchmark ✓ gstack stale (last run 2026-07-13) transcript = wrong session.