Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

New tools for building agents

openai.com

Post reply on HN
Print view View original

51–60 of 165 posts

Re: New tools for building agents

#51

Post by KoolKat23 »

yard2010 wrote: post #32
rvz wrote: post #8

They did not announce the price(s) in the presentation. Likely because they know it is going to be very expensive: Web Search [0] * $30 and $25 per 1K queries for GPT‑4o search and 4o-mini search. File search [1] * $2.50 per 1K queries and file storage at $0.10/GB/day * First 1GB is free. Computer use tool (computer-use-preview model) [2] * $3 per 1M input tokens and $12/1M output tokens. [0] https://platform.openai.…

So they're basically pivoting from selling text by the ounce to selling web searches and cloud storage? I like it, it's a bold move. When the slow people at Google finally catch up it might be too late for Google?

Google AI Studios "Grounding" basically web search is priced similarly. (Very expensive for either, although Google gives you your first 1500 queries free).

It seems completely upside down, they always said traditional search was cheaper/less intensive, I guess a lot of tokens must go into the actual LLM searching and retrieving.

Re: New tools for building agents

#52

Post by DrBenCarson »

fullstackwife wrote: post #48
mritchie712 wrote: post #36

Earlier quoted context omitted.

for anyone that likes the Agents SDK, but doesn't want their framework attached to OpenAI, we're really liking PydanticAI[0]. 0 - https://ai.pydantic.dev/

Openai SDK docs: > Notably, our SDK is compatible with any model providers that support the OpenAI Chat Completions API format. so you can use with everything, not only OpenAI?

Yes

Re: New tools for building agents

#53

Post by nknj »

cosbgn wrote: post #41

We handle over 1M requests per month using the Assistant API on https://rispose.com which apparently will get depreciated mid 2026. Should we move to the new API?

there's no rush to do this - in the coming weeks, we will add support for:

- assistant-like and thread-like objects to the responses api

- async responses

- code interpreter in responses

once we do this, we'll share a migration guide that allows you to move over without any loss of features or data. we'll also give you a full 12 months to do your migration. feel free to reach out at nikunj[at]openai.com if you have any questions about any of this, and thank you so much for building on the assistants api beta! I think you'll really like responses api too!

Re: New tools for building agents

#54

Post by darkteflon »

mritchie712 wrote: post #36
swyx wrote: post #4

swyx here. we got some preview and time with the API/DX team to ask FAQs about all the new APIs. https://latent.space/p/openai-agents-platform main fun part - since responses are stored for free by default now, how can we abuse the Responses API as a database :) other fun qtns that a HN crew might enjoy: - hparams for websearch - depth/breadth of search for making your own DIY Deep Research - now that OAI is offering…

for anyone that likes the Agents SDK, but doesn't want their framework attached to OpenAI, we're really liking PydanticAI[0]. 0 - https://ai.pydantic.dev/

There’s also HF’s smolagents[1].

1 - https://github.com/huggingface/smolagents

Re: New tools for building agents

#55

Post by daviding »

It would have been nice if the Completions use of the internal web-search tool wasn't always mandatory and could be set to 'auto'. Would save a lot of reworking just to go the new Responses API format just for that use case.

Re: New tools for building agents

#56

Post by marko-k »

nknj wrote: post #53
cosbgn wrote: post #41

We handle over 1M requests per month using the Assistant API on https://rispose.com which apparently will get depreciated mid 2026. Should we move to the new API?

there's no rush to do this - in the coming weeks, we will add support for: - assistant-like and thread-like objects to the responses api - async responses - code interpreter in responses once we do this, we'll share a migration guide that allows you to move over without any loss of features or data. we'll also give you a full 12 months to do your migration. feel free to reach out at nikunj[at]openai.com if you have a…

If Responses is replacing Assistants, is there a quickstart template available—similar to the one you had for Assistants?

https://github.com/openai/openai-assistants-quickstart

Re: New tools for building agents

#57

Post by theuppermiddle »

Does the SDK allow executing Python code generated in some sort of sandbox? If not are there any open source library which does this for us? I would ideally like the state of the code executed, including return values, available for the entire chat session, like IPython, so that subsequent LLM generated code can use them.

Re: New tools for building agents

#58

Post by baxtr »

3stripe wrote: post #20
baxtr wrote: post #5

A bit off topic but the post comes handy: can we settle the debate what an agent really is? It seems like everyone has their own definition. Ok I’ll start: an agent is a computer program that utilized LLMs heutiger for decision making.

First rule of writing definitions: use everyday English.

True! Meant heuristic

Re: New tools for building agents

#59

Post by baxtr »

kylecazar wrote: post #37
baxtr wrote: post #5

A bit off topic but the post comes handy: can we settle the debate what an agent really is? It seems like everyone has their own definition. Ok I’ll start: an agent is a computer program that utilized LLMs heutiger for decision making.

Even more off topic, does "heutiger" mean something in English that I'm unaware of? Google tells me it's just German for 'today' or 'current'.

Never heard that word either!

Re: New tools for building agents

#60

Post by swyx »

fullstackwife wrote: post #48
mritchie712 wrote: post #36

Earlier quoted context omitted.

for anyone that likes the Agents SDK, but doesn't want their framework attached to OpenAI, we're really liking PydanticAI[0]. 0 - https://ai.pydantic.dev/

Openai SDK docs: > Notably, our SDK is compatible with any model providers that support the OpenAI Chat Completions API format. so you can use with everything, not only OpenAI?

yea they mention this on the pod
Post reply on HN