Viewing profile — a1j9o94
a1j9o94
HN member- Joined
- Mon, Mar 24, 2014, 3:55 PM UTC
- HN karma
- 74
- Public activity
- 63 items
- HN profile
- View on Hacker News ↗
About a1j9o94
No profile information was provided.
Recent public activity
-
comment
Comment #49150662
You are right that someone could go through that effort bat that only really makes sense if they give you some.idea how to use it. Reading the exchange it seems like you got caught…
-
comment
Comment #47799229
Disclaimer I work at Zapier, but we're doing a ton of this. I have an agent that runs every morning and creates prep documents for my calls. Then a separate one that runs at the en…
-
comment
Comment #47799188
This is effectively how I treat my AI agents. A lot of the reason this doesn't work well for people today is due to context/memory/harness management that makes it too complex for …
-
comment
Comment #47764230
You would only use the base model during training. This is a distillation technique
-
comment
Comment #47477962
I fall into this trap a lot. The platonic ideal argument is a fun mental exercise but doesn't get anything done
-
comment
Comment #47335713
This is an interesting space. Right now we've gotten to a point where agents can do most tasks, but they will get lazy/skip steps if you're not precise in the requirements. We need…
- story
-
story
Show HN: Sales Agent Benchmark – SWE-Bench for sales AI agents (open source)
Live leaderboard: https://sales-agent-benchmarks.fly.dev/benchmark GitHub: https://github.com/a1j9o94/sales-agent-benchmark I built an open-source benchmark for evaluating LLMs as …
-
comment
Comment #46755745
Honestly just didn't think about it. Added it.
-
comment
Comment #46755306
Hey HN, I spent the last few weeks exploring whether AI systems could benefit from generating video predictions before making decisions—like how humans mentally simulate "what happ…
- story
-
comment
Comment #46402439
Pretty much every major LLM client has web search built in. They aren't just using what's in their weights to generate the answers. When it gives you a link, it literally takes you…
-
comment
Comment #46358378
I would argue that's just your coworker giving you a bad answer. If you prompt a chatbot with the right business context, look at what it spits out, and layer in your judgement bef…
-
comment
Comment #46358335
Honestly if you have a working relationship/communication norms where that's expected, I agree just send the 5 bullets. In most of my work contexts, people want more formal documen…
-
comment
Comment #46357566
I know I'm an outlier on HN, but I really don't care if AI was used to write something I'm reading. I just care whether or not the ideas are good and clear. And if we're talking ab…
-
comment
Comment #46322678
Not the person you're responding to, but I think there's a non trivial argument to make that our thoughts are just auto complete. What is the next most likely word based on what yo…
-
comment
Comment #46173481
Having one tool that you can use to do all of these things makes a big difference. If I'm a financial analyst at a company I don't need to know how to implement and use 5 different…
- comment
-
comment
Comment #44567427
The above is saying more precise not completely precise. The overall point they're making is you still are responsible for the code you commit. If they are saying the code in this …
-
comment
Comment #44097119
Why do you say that? I would argue that as long as your tests and interfaces are clearly defined no reason it couldn't scale indefinitely.
-
comment
Comment #44097107
I agree with this completely. I get the impression that a lot of people here think of software development as a craft, which is great for your own learning and development but not …
-
comment
Comment #44097016
The point is devs aren't sales/client facing. So from the customers perspective, it's just a delivery detail.
-
comment
Comment #44076244
How do you do things like compare prices in plain text?
-
comment
Comment #43597593
Wouldn't phone books and catalogues count as advertising?
-
comment
Comment #42873996
This is really interesting. Has anyone seen a good registry of MCP servers somewhere? What I would love to be able to do is ask for a task and have the agent figure out what server…