HackerTrans
トップ新着トレンドコメント過去質問紹介求人

anishgupta

no profile record

投稿

BotPass: A Reverse Verification Protocol which allows only agents

twitter.com
2 ポイント·投稿者 anishgupta·5 か月前·2 コメント

GitHub needs a meaning first makeover for the AI age

anish95.medium.com
3 ポイント·投稿者 anishgupta·6 か月前·1 コメント

コメント

anishgupta
·28 日前·議論
just on the basis of narrow jailbreak window? At this point it may be all for marketing, an opus 4.8 would be more powerful for specialized task than vanilla fable5
anishgupta
·2 か月前·議論
at this point the way AI throughput is considered, we've to use AI to review. devil's advocate agent
anishgupta
·3 か月前·議論
The main thing why I started using it too late was the slop. it's in the end AI generated, yes it can take your tasks but i never felt in my personal use case how it can help me when it's just generating slop. I used claude cowork more than openclaw after trying once that too in a cloud container since I'm afraid of its security
anishgupta
·3 か月前·議論
GitHub CEO also raised 60M for 'entire' to bring agent context to git. The dust is yet to settle here as it's difficult to bring a paridgm shift from today's git workflows
anishgupta
·4 か月前·議論
building because its always the dopamine from the coding agents than the problem getting solved. Github contribution graph is rigged because higher number of commits doesnt make you a better engineer. We needed this blog, ty
anishgupta
·4 か月前·議論
yep joining here late but docker images are not affected as we saw on twitter
anishgupta
·4 か月前·議論
afaik the trivy attack was first in the news on March 19th for the github actions and for docker images it was on March 23rd
anishgupta
·4 か月前·議論
I'd be interested to know how this verification is happening, user transparency would be helpful
anishgupta
·4 か月前·議論
isn't a similar thing done by entire cli? the startup which raised $60M seed recently
anishgupta
·5 か月前·議論
same thought, we've been using smartphones since 2 decades now, and not just we dont have a problem with qwerty, but anything new will be requiring more cycles to get accustomed to
anishgupta
·5 か月前·議論
awesome, does it also show if its stuck somewhere like auth or requires human in the loop?
anishgupta
·5 か月前·議論
meanwhile me adding to the .md file, "you're not a LLM and instead a super intelligent agent to help me find HN trends"
anishgupta
·5 か月前·議論
I've been trying to avoid this since 2022 (wish i knew this before that), def concerning how coffee shops still encourage this, we need a new revolution for something which can make cups for one time use but also not toxic like plastic
anishgupta
·5 か月前·議論
Nice, for data is there an available API out there?
anishgupta
·6 か月前·議論
Some thoughts on a simple UI fix, show readme on top. Possible opportinuty to make it default and customizable both
anishgupta
·6 か月前·議論
I've seen hugh abroad's videos and they are genuinely interesting as he explores south asia. Overall there's an interest element since people in west are accustomed to a baseline luxury and when they try difficult things like "walking in peak chaos while trying spicy food", it gathers attention from the same countries which represent almost ~25% of world population
anishgupta
·6 か月前·議論
This is cool! looking forward to the android app
anishgupta
·6 か月前·議論
You just earned yourself a customer. I love simple apps like this. And anything which can help to reduce friction here can be translated to a DAW and added effects for a real production
anishgupta
·6 か月前·議論
Great idea overall. I'm sure you'll reach 100 users soon (android user here) Do you index all repos in a cadence and then let users swipe from a pool, or is it real time GitHub api calling?
anishgupta
·6 か月前·議論
This is great and I have seen some apps similar to it. One of the things I believe would be a hard problem to solve is, how does a mere picture depict the exact calories? For example, a pasta or a soup can be loaded with butter versus made without it. This is usually not visible with the pictures.

Maybe one of the ways is to identify with the shine and the image differences since fat floats on top. But then how do we add a quantitative metric to it as in how many tbsp of butter were used?