HackerTrans
TopNewTrendsCommentsPastAskShowJobs

fsndz

no profile record

Submissions

[untitled]

1 points·by fsndz·قبل 3 أشهر·0 comments

[untitled]

1 points·by fsndz·قبل 5 أشهر·0 comments

[untitled]

1 points·by fsndz·قبل 9 أشهر·0 comments

comments

fsndz
·قبل 8 أشهر·discuss
we can't automate it anyway and vibe coding is overrated: https://medium.com/thoughts-on-machine-learning/vibe-coding-...
fsndz
·قبل 8 أشهر·discuss
I did that, burned 2.6B tokens in the process and learned a lot: https://transitions.substack.com/p/what-burning-26-billion-p...
fsndz
·قبل 9 أشهر·discuss
As part of the Holistic Agent Leaderboard (HAL) initiative at Princeton CITP, we evaluated more than 220 agent runs across 9 benchmarks, the equivalent of over 20,000 agent rollouts across 9 models and 9 benchmarks for a total cost of $40,000. The benchmarks are: AssistantBench, CORE-Bench Hard, GAIA, Online Mind2Web, Scicode, ScienceAgentBench, SWE-bench Verified Mini, TAU-bench Airline, and USACO.

In that process, we “burned” 2.6 billion prompt tokens and learned a lot along the way. In this article, I’d like to share some of the insights we gained, with a particular focus on the GAIA benchmark.
fsndz
·قبل 12 شهرًا·discuss
and people are still saying vibe coding is overrated? nonsense: https://www.lycee.ai/blog/why-vibe-coding-is-overrated
fsndz
·قبل 12 شهرًا·discuss
Exactly. I think the study is a good reminder that we really have to be careful about the productivity gains attributed to AI. Main takeaway imo, despite limitations from the study, is AI is not a panacea, it can increase productivity, but only if used 'well' and with the good workflows in place, and in the right context.
fsndz
·قبل 12 شهرًا·discuss
I mean, hacker news is still the same aren't they using AI to completely make this website more of whatever it was before ????
fsndz
·السنة الماضية·discuss
true. I think simulations will help a lot in that direction. Imagine if you can do RL a bit like DeepSeek for R1 but on corporate tasks. https://open.substack.com/pub/transitions/p/deepseek-is-comi...
fsndz
·السنة الماضية·discuss
emphasis on corporate
fsndz
·السنة الماضية·discuss
this ! and the truth is is there that much corporate domains without "clear success metrics" ?
fsndz
·السنة الماضية·discuss
frankly ollama + Deepseek is all you need to win with open source AI. I will do some experiments today and add it to my initial blogpost. https://medium.com/thoughts-on-machine-learning/deepseek-is-...
fsndz
·السنة الماضية·discuss
now openai has no other choice than shipping a cheaper version of o1 and o3. The alternative is everyone using r1 (self hosted or via openrouter, nebius AI, together AI and co)
fsndz
·السنة الماضية·discuss
yes o3 is better, but I would argue it is not yet clear for which cases it is absolutely crucial to use o3 instead of o1.
fsndz
·السنة الماضية·discuss
indeed there is no moat. Open source will win !
fsndz
·السنة الماضية·discuss
this means we are going to get o3 level open source models in a few months. So exciting !
fsndz
·السنة الماضية·discuss
[flagged]
fsndz
·قبل سنتين·discuss
sorry for the paywall, you can read the free version here: https://www.lycee.ai/blog/why-no-agi-openai
fsndz
·قبل سنتين·discuss
[flagged]
fsndz
·قبل 3 سنوات·discuss
We just have his version of the story though... He might be wrong. It's natural after spending so many years in a company to see change as bad, to miss the good old days... And he sure seems to have a problem with that black leader Jeanine... A guy who never rose from his technical roles is lecturing a VP and the CEO of Google for their "lack of vision and strategy". Come on. Managing is startup and managing a huge behemoth like Alphabet will never be the same