nfcampos
Re:How we made claude.ai 3x faster in two weeks
on Wednesday September 23, 2026 @05:27PM (#49822833)
Because it’s in a page accessible from its search tool presumably https://claude.dev/blog/getting-the-most-out-of-opus-5-5/
Re:Laya the open source version of Jev
on Saturday September 19, 2026 @01:32PM (#49768506)
Isn’t this post comparing zero shot Jev to fine tunes of this model for each of the datasets it is tested on? If so seems like fairly impressive results for Jev
Re:The Coming Loop
on Tuesday June 23, 2026 @09:11AM (#48644464)
That commit happens to be a find replace because i usually write for my company’s blog (we)
Re:The Coming Loop
on Tuesday June 23, 2026 @08:53AM (#48644217)
No, they really are my thoughts, I've been doing this stuff pretty much every day for the past 6 months
Re:The Coming Loop
on Tuesday June 23, 2026 @08:49AM (#48644148)
My own thoughts on this, with examples https://github.com/nfcampos/loop-dev/blob/main/README.md
Re:Has AI already killed self-help nonfiction books?
on Wednesday June 17, 2026 @12:12AM (#48565582)
I think the same will be true of the ‘popular science’ category of nonfiction
Re:Has AI already killed self-help nonfiction books?
on Wednesday June 17, 2026 @12:08AM (#48565561)
For what it’s worth, I personally discovered something similar with another category of nonfiction books - economics and business. I read a lot of these circa 10-15 years ago and the rate of new signal id get from each new one eventually became low enough that I stopped reading in that category altogether.
Re:Has AI already killed self-help nonfiction books?
on Tuesday June 16, 2026 @11:59PM (#48565517)
He does mention audiobooks, see quoted below
> But what about ebooks and audio? Looking at all formats (print + ebook + audio) for the catalog in 2025, the second half of the year was down ~45% versus the first half.
This compares to 46% on print only
Re:Job Postings for Software Engineers Are Rapidly Rising
on Saturday May 02, 2026 @03:20AM (#47984136)
The title of the submission is an almost comical example of hn navel-gazing - of the many interesting things in the article surely the job prospects of hn readers should not be near the top of the list
Re:Small models also found the vulnerabilities that Mythos found
on Saturday April 11, 2026 @05:11PM (#47734052)
Anthropic marketing (and even supposedly technical write ups) sadly has become more hyperbole and less substance over time imo. This technology is so impressive on its own, really feels like shootings themselves in the foot in the long run, but what do I know
Case in point here where they conveniently fail to report the false positive rate, while also saying that if it wasn’t for Address Sanitizer discarding all the false positives this system would have been next to useless
Re:Claude is an Electron App because we've lost native
on Tuesday March 03, 2026 @05:32PM (#47240039)
But on the other hand the claude app is garbage… https://github.com/anthropics/claude-code/issues/22543
obviously native apps can be garbage too, but I must say electron apps have a surprisingly high incidence of terrible performance issues, unsure if it’s a correlation or causation issue
Building LangGraph: Designing an Agent Runtime from First Principles
Re:Why we chose LangGraph to build our coding agent
on Tuesday March 25, 2025 @03:27PM (#43474899)
LangGraph implements a variant of the Pregel/BSP algorithm for orchestrating workflows with cycles (ie. not DAGs) and parallelism without data races. You can design your graph as a state machine if you so desire
Porting LangGraph to Java in One Weekend? (With Claude Code)
Worker productivity up 1.4% with generative AI
Re:Small plane crashes in Northeast Philadelphia
on Friday January 31, 2025 @11:08PM (#42895549)
Should be merged with https://news.ycombinator.com/item?id=42895466
The rise of nuclear powered batteries
Re:Ask HN: How's LangGraph for Prod?
on Wednesday November 06, 2024 @08:05AM (#42061662)
Hi do you mind sharing more what you mean by "the api makes excessive calls"?
Re:Should I Use a Framework to Build an Agent? Code vs. LangGraph vs. ...
on Wednesday October 02, 2024 @12:37PM (#41722421)
Hi, you don't have to use langchain tools or ToolNode with langgraph, you can absolutely write your custom tool handling logic. In langgraph nodes are just functions that can do whatever you want, seems to be some misconception somewhere?
Re:Ask HN: Is it just me or LangChain/LangGraph DevEx horrible?
on Friday September 13, 2024 @09:56AM (#41531312)
FWIW we have first class support for subgraphs in the library, would love to know what issues you faced there. Support for subgraphs in the studio is coming soon.
Re:LangGraph Engineer
on Saturday August 24, 2024 @10:28AM (#41338569)
A topological sort can't be used for graphs with cycles
Re:LangGraph Engineer
on Friday August 23, 2024 @12:40AM (#41326218)
Fwiw we didn't start with Pregel, but instead reached for it when we saw issues (described elsewhere in this thread) with the previous approach
Re:LangGraph Engineer
on Saturday August 10, 2024 @04:15PM (#41211895)
https://github.com/elastic/kibana/tree/main/x-pack%2Fplugins...
one I saw recently, obvs not the only one
Re:LangGraph Engineer
on Friday August 09, 2024 @05:58PM (#41205700)
The value of using pregel is supporting cyclical graphs, with concurrent tasks, but completely deterministic behavior (eg. doesn't matter that task A this time happens to finish before task B, its results will be applied in a predetermined order, etc)
Re:LangGraph Engineer
on Friday August 09, 2024 @04:50PM (#41205315)
Pregel actually doesn't require the structure of the graph to be declared ahead of time, the next set of tasks (functions) to run is computed at the beginning of each step, so in theory the graph topology could be entirely dynamic. Langgraph supports dynamic topologies too, ie. don't declare any hard edges, add a conditional edge after every node
Re:LangGraph Engineer
on Friday August 09, 2024 @02:35PM (#41204268)
I'm one of the authors so my opinion would be biased ha
Re:LangGraph Engineer
on Friday August 09, 2024 @01:20PM (#41203720)
Langgraph is not a no-code tool for visual programming, it's an implementation of the Pregel algorithm for execution of cyclical computation graphs (ie not DAGs)
Re:College deans suspended after ChatGPT used to email students about ...
on Tuesday February 21, 2023 @06:27PM (#34889242)
Not sure where I stand on this, but “do not judge a book by its cover” comes to mind
Re:Install a server in your house, get free hot water!
on Wednesday February 15, 2023 @05:11PM (#34811435)
So what do people do with these things in summer? Won’t it then heat up their house excessively