HackerTrans
TopNewTrendsCommentsPastAskShowJobs

wendgeabos

no profile record

Submissions

Codex Daily Benchmarks for Degradation Tracking (Marginlab.ai)

marginlab.ai
1 points·by wendgeabos·قبل 6 أشهر·0 comments

comments

wendgeabos
·قبل 5 أشهر·discuss
I have reached the same conclusion -- this is perhaps not a distraction but an attempt to gather funds to pursue the One True Goal...
wendgeabos
·قبل 5 أشهر·discuss
Consider: If you genuinely believe that the only important goal is to make life multiplanetary, (and note I'm not defending this position here, just asserting it as an explanation of behavior)

then anything that drives money towards your work on that goal is worth pursuing particularly if you think time is short.
wendgeabos
·قبل 5 أشهر·discuss
I love thinking hard, it's genuinely my favorite thing, but ... we get paid to ship.
wendgeabos
·قبل 5 أشهر·discuss
What is the question you are asking? What does "useful" mean, in other words? How does it contribute to the reproductive success of the offspring?
wendgeabos
·قبل 5 أشهر·discuss
OK.
wendgeabos
·قبل 5 أشهر·discuss
So, is claude code really better than codex with latest gpt model, or do people just hate on openai so much that no one (but me apparently) is using them? I am asking this question seriously because if so I will make the switch, but codex seems to be quite good to me so I don't want to waste time switching.
wendgeabos
·قبل 5 أشهر·discuss
I do, and I have. Whereof man cannot speak, thereof he must pass over in silence, to which I say, pbthbptltpt! I hold with the primacy of doubt fer shure.
wendgeabos
·قبل 5 أشهر·discuss
I worked with Lee Sword (also RIP) for a while; he was on the mechanical team for Sojourner. Interesting guy.
wendgeabos
·قبل 5 أشهر·discuss
If y'all haven't read the Henghis Hapthorn stories by Matthew Hughes e.g. The Gist Hunter and Other Tales iirc, you should check them out. This is a cut at Henghis' "Integrator" assistant.
wendgeabos
·قبل 5 أشهر·discuss
yes. It also keeps the pasta from sticking together as quickly after you drain it. But an Italian friend made a face and said "it will keep the sauce from adhering to the pasta!!!' so... yeah.
wendgeabos
·قبل 6 أشهر·discuss
Codex is doing better. Why is everyone silent on Codex? https://marginlab.ai/trackers/codex/
wendgeabos
·قبل 6 أشهر·discuss
manus, mens et. one each.
wendgeabos
·قبل 6 أشهر·discuss
This needs to be mashed up with the Daxophone. Like, can I clamp pieces of wood into it and bow them?
wendgeabos
·قبل 6 أشهر·discuss
#applauseguy
wendgeabos
·قبل 6 أشهر·discuss
[flagged]
wendgeabos
·قبل 6 أشهر·discuss
The title makes me disinclined to read the whole paper. But I guess that's AI destroying institutions. Sigh. Social science != science.
wendgeabos
·قبل 6 أشهر·discuss
It would be good to see evidence to support the claims:

NanoLang solves three problems:

LLM Code Generation - Unambiguous syntax reduces AI errors Testing Discipline - Mandatory tests improve code quality

particularly the first.
wendgeabos
·قبل 6 أشهر·discuss
I saw this and thought, Nomic for Normies
wendgeabos
·قبل 6 أشهر·discuss
Oh interesting. Thanks!
wendgeabos
·قبل 6 أشهر·discuss
Old man asks: Does this support what the kids call "livecoding"?