colintjarvis Profile Banner
Colin Jarvis Profile
Colin Jarvis

@colintjarvis

Followers
3K
Following
1K
Media
13
Statuses
258

Making things with customers at OpenAI

Glasgow, UK
Joined June 2016
Don't wanna be here? Send us removal request.
@colintjarvis
Colin Jarvis
1 year
Optimizing LLMs for accuracy is hard - despite opening our talk at DevDay in November last year with those same words, achieving the right level of accuracy for production remains a challenge. I’ve tried to collect my learnings from the last year into
Tweet media one
5
54
257
@colintjarvis
Colin Jarvis
4 months
RT @athyuttamre: Little big detail: you can pass a PDF file to the Responses API and it'll parse the file and expose the text to the LLM!.
0
14
0
@colintjarvis
Colin Jarvis
4 months
Well done @_rohanmehta @stevenheidel and @jamesmhills, incredible ship!.
@sherwinwu
Sherwin Wu
4 months
We just launched the official OpenAI Agents SDK! . Inspired by our Swarm SDK, @_rohanmehta, @stevenheidel, and @jamesmhills evolved it into an even more powerful framework that's a delight to use. We think you'll love using it!.
1
0
10
@colintjarvis
Colin Jarvis
4 months
RT @sherwinwu: We just launched the official OpenAI Agents SDK! . Inspired by our Swarm SDK, @_rohanmehta, @stevenheidel, and @jamesmhills….
0
205
0
@colintjarvis
Colin Jarvis
5 months
RT @isafulf: was so fun to collaborate with @EdwardSun0909 and many many other amazing people 🙂. come work with us!.
0
14
0
@colintjarvis
Colin Jarvis
6 months
RT @kagigz: At OpenAI DevDay, we introduced the Realtime API with a demo of an interactive solar system you can navigate with your voice.….
0
177
0
@colintjarvis
Colin Jarvis
6 months
RT @shawnup: My o1-based AI programming agent is now state of the art on SWE-Bench Verified! It resolves 64.6% of issues. This is the firs….
0
159
0
@colintjarvis
Colin Jarvis
6 months
RT @kagigz: You can now see OpenAI API pricing directly in our docs. We've made a clearer breakdown that's handy, as you're building. Copy….
0
29
0
@colintjarvis
Colin Jarvis
6 months
RT @romainhuet: OpenAI o3-mini is fast and incredibly smart. Developers, you’ll be able to build with it in the API on day one—coming soon!….
0
70
0
@colintjarvis
Colin Jarvis
6 months
RT @OpenAIDevs: We’ve put together a reference implementation for building and orchestrating agentic patterns using the Realtime API. You c….
0
627
0
@colintjarvis
Colin Jarvis
6 months
RT @noahmacca: So excited to share this with the world. It's what I wish existed when I wanted to start prototyping @OpenAI realtime voice….
0
18
0
@colintjarvis
Colin Jarvis
6 months
RT @jeffintime: we shipped a 💎 yesterday: a repo for building Realtime API voice agents with orchestration, handoffs, escalation and prompt….
0
24
0
@colintjarvis
Colin Jarvis
6 months
RT @DeepLearningAI: Over 44,000 learners have already gained valuable skills from Reasoning with o1, our latest course made in collaboratio….
0
22
0
@colintjarvis
Colin Jarvis
6 months
RT @sherwinwu: We're hiring Forward Deployed Engineers (FDEs)!. If you're a software engineer who loves working directly with customers and….
0
75
0
@colintjarvis
Colin Jarvis
6 months
RT @BorisMPower: Please consider joining this team - a chance to become a world expert at implementing new models as well as work alongside….
0
4
0
@colintjarvis
Colin Jarvis
6 months
RT @romainhuet: One of the coolest things since we launched @OpenAI o1 in the API is seeing founders turn agentic workflows that weren’t re….
0
26
0
@colintjarvis
Colin Jarvis
6 months
I'm very pleased to announce that I'm going to lead the new Forward Deployed Engineering function here at OpenAI - our focus is getting our customers to production, whether it's through a zero-to-one novel application of our tech or helping you to scale.
17
29
380
@colintjarvis
Colin Jarvis
6 months
RT @reidhoffman: @OfficialLoganK Openai swarm is great for multiagent.
0
10
0
@colintjarvis
Colin Jarvis
6 months
RT @kagigz: Excited to share our Structured Outputs sample apps repo: This repo contains 3 example apps showing ho….
0
120
0
@colintjarvis
Colin Jarvis
7 months
RT @gdb: o3, our latest reasoning model, is a breakthrough, with a step function improvement on our hardest benchmarks. we are starting saf….
0
368
0
@colintjarvis
Colin Jarvis
7 months
RT @BorisMPower: An insider’s view attempting to explain to untrained mathematicians how hard FrontierMath dataset is. Average human perfo….
0
24
0