Office Hours (@OfficeHours) header
Office Hours (@OfficeHours) profile picture

We help hundreds of the world's most influential VC firms, consulting firms, and startups access human knowledge on-demand.

San Francisco, California
Joined November 2020
Photo by Office Hours (@OfficeHours)Photo by Office Hours (@OfficeHours)Photo by Office Hours (@OfficeHours)Photo by Office Hours (@OfficeHours)Photo by Office Hours (@OfficeHours)Photo by Office Hours (@OfficeHours)Photo by Office Hours (@OfficeHours)Photo by Office Hours (@OfficeHours)Photo by Office Hours (@OfficeHours)Photo by Office Hours (@OfficeHours)
🥰💯
Replying to @lennysan
▫️ Auth: @stytchauth ▫️ Experiments: @Get_Eppo ▫️ ML: @mage_ai ▫️ Ops: @getLogicLoop @UseAvenue ▫️ Security and compliance: @TrustVanta @security_pal @niradotcom ▫️ Offsites: @OffsyteHQ ▫️ Experts: @OfficeHours ▫️ Internal comms: @GoRewatch
1
6
New biology eval on frontier AI models’ performance in biology problems: BioResearchBench: 50 Long Horizon Biological Research Tasks. We are incredibly grateful to the many expert scientists who contributed to this work at @OfficeHours ❤️. We find that models (@AnthropicAI @OpenAI @GeminiApp @Meta @SpaceXSI) continue to struggle with complex reasoning questions and understanding the significance of various biology inputs despite getting individual parts of questions correct. Biology is a hard dynamic field and we still have work to do in improving models 🙂 biorxiv.org/content/10.64898…
8
27
2
198
11,532
Replying to @GeminiApp
@GeminiApp and @AnthropicAI—nice job on our BioResearchBench Eval where questions were written from phenomenal scientist experts in diverse bio subdomains 😊. Reasoning in biology is challenging for models, understandably so! Gemini’s newest models like Carbon have been really impressive in biology, highly recommend that scientists give it a try if you haven’t in your research 🚀 (also really great in troubleshooting experiments that aren’t working, snap a pic and ask Carbon).
Google takes the lead! Just 2 days after the release of Fable 5.2, Carbon is the new SOTA on BioResearchBench. Congrats @divy93t and team.
6
9
301
Office Hours retweeted
Gemini
Fable 5.2 is the new SOTA model on BioResearchBench, showing a 5 p.p. improvement over Opus 5.5., including solving 5 tasks previously not solved by any model. Congrats to @AnthropicAI @amirshanehsaz @mgdurrant @nc_frey @JCoolScience and team
1
4
164
Office Hours retweeted
Fable 5.2 is the new SOTA model on BioResearchBench, showing a 5 p.p. improvement over Opus 5.5., including solving 5 tasks previously not solved by any model. Congrats to @AnthropicAI @amirshanehsaz @mgdurrant @nc_frey @JCoolScience and team
Introducing BioResearchBench, a new benchmark focused on scientific reasoning in biology from @OfficeHours built by 100+ PhD biologists in our network. For models and agents to materially speed up scientific discovery, scientists need to be able hand off work that would take them hours to complete, come back, and find it done right without mistakes. This work shows that frontier models aren’t there yet. They still struggle to stitch multiple steps together, get the computations right, interpret the data correctly, handle uncertainty, and draw the right conclusions. We built 50 long-horizon research tasks across 10 subdomains, from genomics and cancer biology to neuroscience and immunology. Each uses multiple data files, takes an expert hours to several days to complete, and is independently reviewed by at least 2 PhD biologists for verifiability and scientific accuracy. Every frontier model passes fewer than 1 in 5 tasks: Claude Opus 5.5: 18% Gemini 4 Argon: 13% Muse Wonder: 11% GPT-6 Astra*: 4% Grok 4.7: 4% The top models met ~80% of individual rubric criteria, but completed the full end-to-end workflow correctly <20% of the time. Half of the tasks were not solved by any model. The biggest gaps point to where models need to improve next: computation and data handling (failures on 67% of tasks), handling uncertainty (55%), and reporting complete answers (55%). An important note on scoring: GPT-6 Astra’s score is skewed lower because every task had to stump Astra (SOTA at the time) during development before it made the final set. Paper, leaderboard, and per-task results: horizon.officehours.com/rese… @samar_abedrabbo @alexpryhoda
4
2
6
9,400
Replying to @k3goodman @divy93t
Well done @divy93t 😆
2
4
464
Office Hours retweeted
Google takes the lead! Just 2 days after the release of Fable 5.2, Carbon is the new SOTA on BioResearchBench. Congrats @divy93t and team.
Fable 5.2 is the new SOTA model on BioResearchBench, showing a 5 p.p. improvement over Opus 5.5., including solving 5 tasks previously not solved by any model. Congrats to @AnthropicAI @amirshanehsaz @mgdurrant @nc_frey @JCoolScience and team
3
20
4
302
14,183
Office Hours retweeted
Introducing BioResearchBench, a new benchmark focused on scientific reasoning in biology from @OfficeHours built by 100+ PhD biologists in our network. For models and agents to materially speed up scientific discovery, scientists need to be able hand off work that would take them hours to complete, come back, and find it done right without mistakes. This work shows that frontier models aren’t there yet. They still struggle to stitch multiple steps together, get the computations right, interpret the data correctly, handle uncertainty, and draw the right conclusions. We built 50 long-horizon research tasks across 10 subdomains, from genomics and cancer biology to neuroscience and immunology. Each uses multiple data files, takes an expert hours to several days to complete, and is independently reviewed by at least 2 PhD biologists for verifiability and scientific accuracy. Every frontier model passes fewer than 1 in 5 tasks: Claude Opus 5.5: 18% Gemini 4 Argon: 13% Muse Wonder: 11% GPT-6 Astra*: 4% Grok 4.7: 4% The top models met ~80% of individual rubric criteria, but completed the full end-to-end workflow correctly <20% of the time. Half of the tasks were not solved by any model. The biggest gaps point to where models need to improve next: computation and data handling (failures on 67% of tasks), handling uncertainty (55%), and reporting complete answers (55%). An important note on scoring: GPT-6 Astra’s score is skewed lower because every task had to stump Astra (SOTA at the time) during development before it made the final set. Paper, leaderboard, and per-task results: horizon.officehours.com/rese… @samar_abedrabbo @alexpryhoda
3
6
3
18
3,937
Office Hours retweeted
The @OfficeHours team wins the title of best fan section. They played great but they trash talked even better.
1
5
381
We are proud to share that out of 2,500+ Seed & Series A companies, Will Reed just named @TryAssemble, @farm_raise, @lightyearai, @memoinsights, @OfficeHours, @usebeamco and @TortugaAgTech in the top 100 early-stage companies shaping the future of workplace culture. 🚀 🏗 🏆 #WillReedTop100 willreedtop100-2.squarespace…
3
5
12
3,227
We're rapidly approaching a world where codified, written knowledge can be accessed & synthesized almost instantly. But truly great decision-making requires more than just codified knowledge & data. So, what role does human insight play in a world where AI has made codified knowledge more or less instantly accessible? 👀👇
2
1
3
1,645
Looking for ways to grow your sales pipeline? @OfficeHours, many product feedback convos with target buyers are evolving into long-term relationships. Here’s how startups are getting valuable insights and generating qualified sales leads, all in one convo...
2
2
5
1,145
"You need to find mentors" "You need to talk w/ other founders" "You need relationships w/ experts in your space" As a founder, you understand the wisdom in this advice. But you have other pressing priorities. What if you could put networking on autopilot? officehours.com/blog/attenti…
1
1
4
752
You don't always need to hire that consultant. Sometimes you just need one informative conversation. officehours.com/search?utm_s…
2
4
663
1/3 The barrier to entry for content marketing has been shattered by LLMs like Chat-GPT 🤖. So what are you doing to ensure your content stands out? 👇
1
3
6
657
2/3 The best marketers are interviewing real experts & quoting them in their content. Example: Basis Set Ventures developed this piece by interviewing real experts on Office Hours: basisset.com/the-enterprise-…
1
2
296
3/3 It's easy: 1. Pick the topic for your next content piece 🧠 2. Find experts on Office Hours who can provide valuable insight 🔎 3. Automatically record & transcribe your convo ⏺ 4. With the expert's permission, include quotes from the interview in your piece ✍ 🗣
1
246
Founders & PMs: Struggling to access high quality product feedback? Read our guide to booking & conducting effective product feedback interviews. Full guide on our blog 👇 officehours.com/blog/step-by…
3
8
796
Investors, consultants & founders want a faster, easier, more flexible expert network. We've been hard at work building just that. Our latest post covers what sets Office Hours apart from traditional expert networks like GLG & AlphaSights. Read on 👇 officehours.com/blog/buildin…
2
5
1,980