37,380 results · Most relevant
Use deterministic scripts to check facts against a source of truth (like a schema registry or catalog) as layer one of PR review. Configure a failed deterministic check to turn CI red and block the PR until it is fixed. Run a script that checks the catalog directly to verify every table has an owner and any PII is labeled.
Chetas Joshi endorses a three-tier routing principle: when a fact can be proven against a source of truth, let a script prove it and clear the PR without human involvement; when a decision requires context and judgment, route it to an agent; when a change is a protected call carrying real risk, route it to a human reviewer. Every fact a script proves is review work that never needs AI, keeping system cost down.
Use an AI agent as layer two of PR review, focused on the risk that deterministic checks cannot catch. Have the agent review the PR, score the risk, and either approve or escalate to a person. The agent produces a risk score that drives the next step.
To measure whether the reviewer is doing a good job, look at two kinds of mistakes: bad PRs it approved (a miss — dangerous because the change ships) and fine PRs it unnecessarily sent to a person (a false escalation that costs a person's time). The matrix separates four possibilities. Measure the false escalation cost the same way you measure a miss.
The auto-research layer should only edit a controlled policy surface — memory writing policy, retrieval policy, communication prompts, belief trust rules, source attribution, and replanning triggers — rather than rewriting the whole application. This gives the search process room to improve behavior while preventing it from gaming the evaluation.
When an AI model applies a percentage increase, check it was applied to the correct sub-population rather than the whole population, and compare any stated percentage against the real number disclosed in filings before accepting the forecast.
When auditing an AI-generated financial model, check that every assumption is backed up with a real number from a citation, not just a citation without a number. AI can fail to identify the correct number even when the citation is real, and can draw assumption boundaries (e.g., 5-30%) that exclude the actual disclosed number (45%).
Extra agents pay off the most in planning on ProgramBench, where discovery is the bottleneck. Allocating more agents to planning achieves almost the same performance as the heavy-prompt (PIV) setup at half the cost. Each planning dollar buys almost 1.6x more reward than any other stage (implementation or verification). Planning delegation yields 2.4x more reward per call than delegating throughout implementation.
Replacing Sol workers with cheap Luna workers while keeping Sol as lead achieves almost the same performance at 60% less cost. A strong lead (Sol) with cheap workers (Luna) achieves the same performance as Sol plus Sol but at much lower cost. A 16-planner team (Sol lead, Luna planners) is 38% cheaper than an all-Sol planning team and 70% cheaper than workers at every stage (PIV).
Jesse Hall advises keeping the gap between the caller's last syllable and the agent's first audible sentence roughly inside 1.5 seconds so the call still holds, and notes that getting down to 500-600 milliseconds between turns is when the conversation really starts to feel human-like.
Prospects without pull can be enthusiastic — 'that's the future of our industry' — but aren't saying 'I need this right now'; leaned-out enthusiasm like 'let me think about it' or 'send more info' is not pull, and neither is 'we could use this in Q4.'
Rob Snyder recommends using the pull framework to stake out a claim — state which specific person is stuck — and then go test whether they try to buy before a product exists. If prospects try to buy, you might have something; then see if it repeats. If a prospect doesn't try to buy after the Hail Mary question, treat it as a learning signal that you might not have pull: 'cool, we've learned something.' He notes the Hail Mary question has led startups to completely pivot and take off.
Rob Snyder advises selling to the specific individual at a company who has a project on their to-do list they can't do themselves — 'You're not selling to SpaceX. You're selling to the head of legal at SpaceX who has a project on her to-do list.' This operationalizes the person-level view of pull into a targeting rule for sales.
The framework lets you stake out a testable claim — 'I believe this specific person is stuck' — before any product exists, then verify by seeing if they try to buy.
The thing that really matters is that the potential customer tries to buy — 'okay, cool, how do we get started?' — even before a product exists.
Every stakeholder should evaluate the agent — it is not just one role's job. Get everybody in the room who has a stake in the agent and have them define what success looks like according to their outcome. Stakeholders to include: product, engineering, support, experts, and security.
Dr. Scott Forbes states creatine supplementation improves cognitive performance after sleep deprivation, and even a single dose of creatine helped preserve some cognitive function when people were sleep deprived. In rugby players who got less than three hours of sleep, passing accuracy declined — but creatine maintained passing accuracy despite poor sleep. He recommends considering creatine supplementation when you have a bad night's sleep before an important performance (e.g., athlete before competition, surgeon after a night operation), and taking creatine when traveling across time zones to offset time-delay effects on the brain. Cognitive tests used in creatine research include the MoCA test, mini mental state examination, reaction-time computerized tests for processing speed, and
Consequential creator advice requires independent verification before Today can promote it.
Hari Kumar identifies one of the biggest problems in hedge funds: an analyst works on an idea for a couple of days, it loses PM interest or something else takes precedence, and it doesn't come back for months — so the analyst misses a key price window. He recommends building agents that track all the notes an analyst has taken, even from a single day, against the market, and flash the idea as interesting again to the analyst, PM, and trader when it becomes interesting.
The hosts state that communicating a product is on-device is the most important trust message for local AI products. A founder who applied to YC with an open-source text message analyzer that read iMessages entirely locally used a hero saying 'open source, completely on device' and communicated that the internet doesn't touch the data — which they learned is what users really cared about. An 'on-device LLM' label is also a trust signal displayed on AI sites, though the host questions whether the wording is necessary.
Vague, generalized copy (e.g., 'institutional intelligence and decision infrastructure') leaves visitors unsure whether they need the product. Copy should use specific language about who should use the product and why, and give specific examples of what the product does and the problems it solves. Copy that lists claims without explaining what the product actually does fails the visitor — even after reading 'years of history, alive from day one, nothing installed, no interviews,' the reviewer still didn't know what the product does.
Choose sources → to get a library of your own and a daily brief.