I’m considering open-sourcing an eval based on 4 years of trying to build AI that answers: ‘What should my YouTube audience watch next?’
At @CreatorML_ we built view predictors, but we always lacked a clean public benchmark.
Curious: how much better are Claude Opus/GPT-5/etc. out-of-the-box at this vs specialized models? Planning to test it properly.
4
8
1,580
Key question: Given channel history + new video idea (title/thumbnail/desc), how well can models predict relative performance (views, CTR, retention)?
Predicting “is 1 of 10” might be good starting point as opposed to raw views.
1
1
810
Seems we have converged to the same setup.
how to build anything rn:
- get a hetzner, do, or hostinger vps
- host hermes on it
- add gbrain or implement your own memory vault using qmd + sql
- set up hermes with codex auth -> gpt-5.5 / no reasoning / fast mode
- install orca on your macbook and phone with tailscale to have a nice ide to work on both
- before starting any work, ask hermes to conduct deep research on the subject and save it to gbrain as source material for the project
- use the `/grill-me` skill or a similar prompt to uncover as many unknowns as possible. save results to memory too
- define/write clear evals for every project to determine whether a run was successful
- have hermes iterate over the project until all evals pass, saving all learnings to the vault along the way
- whenever it gets stuck, use memory + a new research or `/grill-me` session to unblock it
rinse and repeat until the work is done. pay attention to the process. develop a feeling for how long tasks should take and do not be afraid to stop a model mid session to ask for status and why it's taking so long.
1
674
“People who are really serious about software should make their own hardware” —Alan Kay
People who are serious about AI should use specialized chips for inference.
We raised $15m to build the ASICs-first inference cloud.
We're betting big on alternatives to GPUs, and the result is that we are already 5-8x faster on most models.
Read more about General Compute on Tech Crunch!
@FPuklowski @fastinference
techcrunch.com/2026/05/28/ha…
1
3
1,103
$400/mo Codex plan with 50x tokens when? @openai
I’m all out of two separate 20x subscriptions.
4
931
I'm playing around with my own agent swarm harness/flywheel to rebuild DeepMind's AlphaZero.
I'm learning so much.
1
1
413
I've been running dozens of coding agents in parallel since December.
Beads was the missing piece for making everything feel more seamless, especially the dependency dag of things to implement. I was using raw Linear before, but this fills a gap.
github.com/gastownhall/beads
1
303
Every company will be recursively self-improving.
In a recent batch talk, YC General Partner @t_blom broke down how to build a self-improving, AI-native company.
He walks through how to create recursive, self-improving AI loops, and why founders who get this right will run companies that improve while they sleep.
00:00 — Companies Are Roman Legions
00:54 — Copilots Are the Wrong Mental Model
01:55 — Extract the Domain Knowledge
02:24 — The Recursive Self-Improving Loop
04:12 — The Holy Shit Moment at YC
05:50 — Self-Optimizing Product and Support Loops
06:29 — Burn Tokens, Not Headcount
07:23 — Middle Management Is Over
08:05 — Make Everything Legible to AI
09:40 — Regenerating the YC User Manual
11:19 — Software Is Ephemeral, Context Is Valuable
12:18 — Where Humans Still Matter
547
Great read for a most up-to-date survey of RL from Kevin Murphy of DeepMind.
Replying to @CharlesWeill
This is presumably more superficial but I found it helpful for understanding popular RL algorithms:
arxiv.org/pdf/2412.05265
1
380









