socratic methhead

conscious decoupling

[socratic methhead @fatboygrimdark]

@championswimmer @chrislciaba @GergelyOrosz yeah I would have thought an ex-Amazon senior engineer and startup founder would understand the absolute basics of business

[socratic methhead @fatboygrimdark]

@vboykis this seems to be a neurotype thing - adhd-types don't get anywhere near as much fatigue; asd-types get a lot

[socratic methhead @fatboygrimdark]

@billy_boi6 @polydao vibe coders who think the secrets of the universe have been revealed

[socratic methhead @fatboygrimdark]

@KingBootoshi might need to update npm version too tbh

[socratic methhead @fatboygrimdark]

@borcho23 @vasuman yeah their claims literally mean nothing until tested in the real world

[socratic methhead @fatboygrimdark]

I don’t think “regression” means what this guy thinks it means

[Kyle Daigle @kdaigle]

Wanted to provide more clarity about this.

Yesterday, we had a regression in merge queue behavior where, in some cases, squash or rebase commits were generated from the wrong base state, making earlier changes appear reverted in branch history. 2,804 pull requests out of over 4M merged on April 23 (roughly 0.07%) were affected. We fixed the issue, we've contacted every impacted customer, and we're expanding our automated test coverage for merge queue operations. The team will be updating the status page with RCA details as well.

[socratic methhead @fatboygrimdark]

@_0xBenjamin_ @bankoncrypto @shawmakesmagic this will work for about the first 80k - 120k tokens of the context window. after that your rules will start to get forgotten.

[socratic methhead @fatboygrimdark]

@rahuldoval @cjayls @rabi_guha haha “predict intent from context”

what context? you don’t have any context until the user gets there, and then you need to show them something right?

explain how this solves that

[socratic methhead @fatboygrimdark]

@summeryue0 long sessions (which openclaw does by default) will always forget hard rules like this unfortunately

[socratic methhead @fatboygrimdark]

@dragosilinca @NickSpisak_ very few right now, niche applications where latency matters but quality doesn't AND deterministic conventional compute can't do it (way faster than 17k tps).

this approach doesn't work until model lifetimes are well over 6 months.

[socratic methhead @fatboygrimdark]

@stark4833 @gdb nah codex is fine, I use it when I hit my claude code limits haha

[socratic methhead @fatboygrimdark]

@aakashgupta PRs per week is a dismal metric

[socratic methhead @fatboygrimdark]

@adelwu_ @lizwessel @JenniferHli @sdianahu @chetanp yeah but the underlying assumption is “be a company with a great idea that you’ve executed super well”

most startups aren’t this

I’ve invested in great companies that only became great later after growing in to one or both

the advice is good but limited

[socratic methhead @fatboygrimdark]

@DaleCloudman @tomfgoodwin @avidseries Blair Witch Project was viewed millions of times but that didn’t mean a fundamental change in anything tbh

[socratic methhead @fatboygrimdark]

@EddyLeeKhane @simplifyinAI yeah this is essentially useless for anything complex until context windows are 100x the size

[socratic methhead @fatboygrimdark]

@aakashgupta what you describe isn’t an equilibrium - why would anyone maintain open source if they didn’t get status from download numbers?

this dynamic just means everything is closed source and less is shared

[socratic methhead @fatboygrimdark]

@RitOnchain @rauchg haha “nobody is talking about” that? do you read anything?

[socratic methhead @fatboygrimdark]

@Black_Mage01 @theo it’s just really hard to build good consumer software and the only way it’s successfully been done is by big teams at for-profit corporations

AI might change that I guess

[socratic methhead @fatboygrimdark]

@maxbittker do you bootstrap the agents with the rules of the game or do they need to discover them? I guess a bunch would be in pretraining