
Isa Fulford
@isafulf
Followers
35K
Following
3K
Media
15
Statuses
295
fun to share more about agents and talk about research at openai with @christinahkim!. thank you @eriktorenberg and @sarahdingwang for having us on the pod.
New episode with @sarahdingwang and @christinahkim & @isafulf of OpenAI breaking down GPT-5, Deep Research, and ChatGPT Agent. Where it improved, what it unlocks, the decisions behind it. A clear look at how these models actually get built.
8
16
172
RT @ElaineYaLe6: GPT-5 is here! š. For the first time, users donāt have to choose between models ā or even think about model names. Just onā¦.
0
82
0
RT @j_mcgraph: @michpokrass is unbelievably goated at intersecting research and engineering and sheās grown a whole team around it. Honoredā¦.
0
18
0
RT @Eric_Wallace_: Today we release gpt-oss-120b and gpt-oss-20bātwo open-weight LLMs that deliver strong performance and agentic tool use.ā¦.
0
384
0
š¤ mode.
Today on Training Data, the @OpenAI team behind ChatGPT agent explain how Agent Mode works, combining:. 1) Deep Research (text based research agent).2) Operator (GUI/action based computer agent).3) Other new tools (terminal, computer apps).4) Tied together with shared state.to
9
6
130
RT @hunterlightman: huge congrats to @alexwei_, @SherylHsu02, and @polynoamial for an incredible achievement and the close of a big chapterā¦.
0
4
0
RT @EdwardSun0909: just tried and the agent solved level 1 in its own browser lol. thanks for creating the benchmark! .
0
30
0
RT @EdwardSun0909: Another tip: it generates a real pptx file. So you can download the artifact, open it in microsoft powerpoint app, and aā¦.
0
4
0
RT @tejalpatwardhan: these results were eye-opening for me. chatgpt agent performed better than i expected on some pretty realistic invesā¦.
0
57
0