😎
😎 https://t.co/xxfnJQ9MN3
Onur Solmaz blog
Explorations in software, agentic systems, math, languages and more.
Latest posts
A similar thing can be done with codex session compaction summaries as well btw
A similar thing can be done with codex session compaction summaries as well btw I had verified the other day that a compaction summary created by one account can be used by another account if it has the encrypted blob ie. they were not keyed/guarded with your account id
This type of estimations are useful not only for local but for all inference providers
This type of estimations are useful not only for local but for all inference providers Get a ballpark of max possible throughput for a model, directly calculate your revenue
mfw trying not to think about the 100 models that dropped this week
mfw trying not to think about the 100 models that dropped this week I’ll be offline 1 week to touch grass and reset I’ve literally not given any break since claude code came out lol let’s see if I can resist the urge to check twitter
Deterministic monitors make long-running agents reliable
I've felt the lack of a certain feature of codex desktop app since I went back to the CLI: scheduled tasks Codex desktop app can keep track of a task until it is properly finished. It's basically cron. And for some reason, codex CLI still doesn't have it. Codex app acts as a shared runtime, and for some reason, certain features don't work without it, even though they could... there is no reason…
Apparently this went to HN front page briefly last night, so sharing it here as well
Apparently this went to HN front page briefly last night, so sharing it here as well YOLO safely with your agents 🤖 Give your GitHub/Hugging Face accounts + ability to run sudo safely to your agent. No need to create an agent account, or clickops policies on GitHub etc. Give it merge access to repo X for 5 minutes, 30 minutes, 1 time, 100 times, anything... Then give it unlimited access to repo Y…
Local AI will favor LPDDR and MoE
This. LPDDR chips are cheaper to produce and run GDDR/HBM will likely keep being more expensive Most consumer GPUs will converge on a GB10 like form factor As much as us hobbyists love to project this ideal of running a GPU cluster at home, most working people will prefer smaller form factors, and will not want to pay hundreds of $$$ in electricity bills every month DGX Spark/GB10 runs at around…
urgh typo, I meant 35-40 tok/s
urgh typo, I meant 35-40 tok/s
Apparently Alibaba did all this work, published a paper, but did not create a public backup of...
Apparently Alibaba did all this work, published a paper, but did not create a public backup of repos used in the review tasks https://t.co/aoZoYD79Vh Then keycloak and nodejs repos got force pushed, so the commits for 6 of the tasks got lost :( I recovered 4 of them, but 2 commits are still missing: keycloak/keycloak#35645 460f8008f86d3fa8f62da63e26d8bdc306af60b2 nodejs/node#56185…
I have made an update to my theoretical upper bound calculation to also predict prefill speed
I have made an update to my theoretical upper bound calculation to also predict prefill speed Prefill relaxes the assumption we make for decode, that it is only be memory bottlenecked. So prefill can be both compute or memory bottlenecked. I use the FLOP limits reported by hardware producers for the estimates: These estimates will also be available in https://t.co/SGQepULIW7 for indexed model and…