andrej didn't mention this in his 2025 YC talk but lately I've been merging his software 1.0 and 3.0 in the form of fallback and automatic self-repair - you give input to program X - X tries processing it with its deterministic logic - if X detects a failure, it spawns an llm agent to examine the log (including the input) and path to X's src code - agent diagnoses the failure, implements a fix, while (!) preserving the running X process. such that the agent can then manually push the corrected post-fix output to the original user so from the pov of X's user (itself an llm agent usually), there was never any issue with X in the first place besides a longer running time. this is how I've set up all of my mcp servers to work

iterating on some reverse engineering with sol 6.1 for over a week and opus 5.5 more or less one-shot it to a better state than the final with sol lmao I need to improve my proxy benchmarks

my number of subagents is now bottlenecked not by the optimal structure for solving the problem but by available RAM, since the iteration each one is doing is heavy I have like 8 at once right now, with my custom orchestrator, not the built in cc/codex subagent systems

still scared of accidentally getting banned for some technical misuse of claude SDK so we went with cc TUI tmux automation for my t3-equivalent easier than I thought; you can automate nvim/similar as EDITOR and then use Ctrl-g for composer input, much less janky than pasting

just accidentally did my first >1h voice prompt looks like I've been improving on speech stamina, this would have winded me and made my throat ache like a month ago

I tried glm 5.3 flash for some ~cybercrime and it seemed to start heavily hallucinating when the context hit ~300k tk, despite it advertising 1m as its supported size otherwise pretty good and inexpensive despite no subscription-level subsidization

enabled the codex auto review bc of the day 2 free usage but I'm seeing sol complain about blocks constantly the best convenience tradeoff might still be yolo mode + good backups unless you're really expecting prompt injections or something

I made a small luna voice assistant as like a router on top of my codex manager so with one physical button press, I can tell it to start a new codex thread with some X specific model on my Y chatgpt account, or forward a message to some old existing thread, etc

to what extent does a micro todo list increase subjective experience of working in the abstract maybe you'll have infinite dopamine if an llm could monitor your work and show a +5 XP animation on every productive action like submitting a codex prompt

anyone else surprised that the $500 plan didn't change its usage/cost ratio against the existing 20-100-200 doesn't this decrease wealth inequality

is it considered autistic to be voice prompting llm agents outside at a public park

here's my ms paint masterpiece of an entry for this meme format couldnt fit the 8-9th but it'd be ds2 and nioh maybe deliberately avoided including names otherwise

so far discussing my startup's active research problems with opus 5.5 has been high-ROI feels like talking to an adult who can follow the plot and has their own legitimate ideas worth considering. makes me more confident that past cases of simple agreement was mainly an IQ issue

the self-ping alarm mechanism I made for codex on a whim in 1 prompt is working really well ~20% of my codex sessions make use of it atp. e.g. I'm scraping google maps through the API and that instance is able to set 20-day alarms to wait for the monthly quota reset

looks like linkedin has embraced industry terminology for its menus

in urgent contexts like pre-singularity 2026, working longer hours usually decreases rather than increases stress

my internet speed in practice is now 22.5x higher than a week ago, with Sol's help switched internet providers and upgraded plan, bought better router (now with openwrt), configured it to force 160MHz channel width

im not a paid shill but I recently switched from brave to @heliumbrowser my hard requirements were CDP and keybinding remapping, which helium has both of + less bloat and more UI configuration than brave. the brand visually is much cleaner too

mailo captchas go kind of hard