Bobby Hyam (@bobbyhyam) profile picture

I help organisations achieve their goals with technology and I support Tottenham Hotspur. Not sure which is harder.

London, England
Joined August 2010
Photo by Bobby Hyam (@bobbyhyam)Photo by Bobby Hyam (@bobbyhyam)Photo by Bobby Hyam (@bobbyhyam)Photo by Bobby Hyam (@bobbyhyam)Photo by Bobby Hyam (@bobbyhyam)Photo by Bobby Hyam (@bobbyhyam)Photo by Bobby Hyam (@bobbyhyam)Photo by Bobby Hyam (@bobbyhyam)Photo by Bobby Hyam (@bobbyhyam)Photo by Bobby Hyam (@bobbyhyam)
So long @SirPatStew ❤️. Thank you for for your wonderful performances and most of all for your portrayal of Picard. Almost 40 years on I am still trying to be a better human with him as a guide.
13
I think @AnthropicAI’s Fable model is grossly underrepresented in these and other benchmarks. For clearly defined tasks I don’t argue that other models are better and cheaper but Fable’s value lies in dealing with ambiguity and big picture thinking. Where other models will do what you ask of them very effectively, Fable seems to have broader vision, seeing problems that could come up in the future that you haven’t directly told it to address. It has saved me many times from making mistakes where the same query on Opus 5.5 proceeds to completion. I use Fable for strategy and my prompts include open ended questions like, “What else should I be considering?”, “How does this fit into our overall goals?” and “What are the alternatives we haven’t considered?”. Once Fable has helped me to establish a well thought out direction, Opus is a fantastic executor.
Announcing Artificial Analysis Intelligence Index v5, featuring 2 new benchmarks and 3 upgrades. For the first time, the majority of the Index is built on private datasets The Artificial Analysis Intelligence Index is our composite measure of model capabilities across tasks reflecting real-world usage today. v5 is our biggest upgrade since v4 launched in January. With v5, 60% of the Index is now based on evaluations with private test sets or held-out answers. Alongside Intelligence Index v5, we’re launching the Artificial Analysis Progress Index v1, which tracks model capability over time on one continuous scale. New to the Intelligence Index: ➤ FrontierCode 2.0: Cognition's newly-launched private benchmark of real-world coding tasks, graded on whether a repository maintainer would merge the agent's change ➤ Terminal-Bench-Science: 70 agentic scientific research tasks, run in a terminal environment Upgraded: ➤ HLE-Diamond (replacing Humanity's Last Exam): a refined 1,000-question version of Humanity's Last Exam, split evenly between reasoning and knowledge questions ➤ AA-Omniscience v1.1: An updated dataset with saturated and public set questions removed, new questions added, and ambiguous or erroneous questions revised ➤ CritPt v2: a private, 40-question hard subset of CritPt v2, revised by the CritPt authors and run with a code-execution tool Staying in the Index: AA-Briefcase, AutomationBench-AA, GDP.pdf and Terminal-Bench 4.0 Removed from the Index: GDPval-AA v2.1, SciCode, and AA-LCR v1.1 Key results: ➤ Claude Opus 5.5 (max) leads at 58, ahead of GPT-6 Astra (max, 57) and GPT-6.1 Sol (max, 55): Anthropic and OpenAI hold the top five models. Gemini 4 Argon (high) is next at 50 ➤ The open weights gap widens from 3 points to 12: Kimi K3.1 Pro (weights not yet released) is the top open weights model at 46. Among released weights, DeepSeek V4.1 Flash 1017 (max) and GLM-5.3 (max) lead at 32 - 26 points behind the leader and below Claude Haiku 5.5 (max, 36) ➤ Cost per task varies by more than 13x among the leading models: of the 10 highest-scoring models shown, GPT-6.1 Terra (max) is the cheapest at $0.96 per Intelligence Index task and Claude Fable 5.1 (max) the most expensive at $13.04
119
Funded by the experts in non-profit, @OpenAI
People here discussing what happened with OpenClaw. The hype died down. We improved quality and grew a team. We created a non-profit whereas competiors are VC funded and have other agendas. This is our strongest week so far.
1
58
33,878
Is time travel possible and if so, which Hollywood movie most closely represents the possible method? #horizonslive
Gutted to find out @tubeexits is no longer available on the App Store. What happened? Please come back! All the other copycats are far inferior – at Lewisham, London
Two brave doctors, on my train today @DrChrisNewman and @chewyvish with no public speaking experience talking about the #1 issue facing our health service. #TrainTalk #UkElection #NHS #ClimateChange
4
1
4
Expedia price says all taxes and fees included then buried in the small print it says add’l insurance required in some locations. Complete crooks. An awful start to our vacation.
1
1
Just been robbed by @Europcar through @Expedia. $128 booking turned into $434 on arrival due to mandatory insurance. – at Los Cabos, Baja California Sur
1
1
Damaged key on my MacBook Pro fixed for free by the @Apple store. That's why I love them. Thanks, guys! – at San Jose, CA
1
Attending #FlashMem in Santa Clara? Don't miss @baxontap's keynote session August 10 11:30AM-12PM
Thank heavens for that. I'm dying here. xitter.cf/nowtvsport/status/8920… – at San Jose, CA
You’re unable to view this Post because this account owner limits who can view their Posts. Learn more
Free rides home: $25 @Uber gift cards for the first 25 customers who join @netapp at The Third Rail after #PureAccerate #PureAccerate2017 – at San Francisco, CA
1
1
Free drinks after #PureAccerate2017 from the fastest growing flash and SAN vendor, @NetApp xitter.cf/wysiwyg503/status/8747… – at San Francisco, CA
On your way out of #PureAccelerate pls stop by for a free drink and chance for prizes #datadriven
1
3
4
Team afternoon out. Love my job at @NetApp!
3
Poke bowl $10. Thank you @netapp #ILoveMyJob – at Sunnyvale, CA
1
1
what we saw today from your lot was neither of those things – at San Jose, CA